system

Abstract

The system according to this embodiment aims to suggest the most suitable medical department and medical institution based on the patient's symptoms, and to provide follow-up care after treatment. [Solution] The system according to the embodiment comprises an analysis unit, a proposal unit, a summarization unit, a provision unit, and a follow-up unit. The analysis unit analyzes the patient's symptoms. The proposal unit proposes the most suitable medical department and medical institution based on the information analyzed by the analysis unit. The summarization unit summarizes the patient's complaints. The provision unit provides the information summarized by the summarization unit to the medical institution. The follow-up unit performs follow-up after the medical examination.

Description

Technical Field

[0006] , , ,

[0005] , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 has not been sufficient proposal of an optimal medical department or medical institution based on the symptoms of a patient, nor efficient follow-up after medical treatment, and there is room for improvement.

[0005] The system according to the embodiment aims to propose an optimal medical department or medical institution based on the symptoms of a patient and perform follow-up after medical treatment.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a proposal unit, a summarization unit, a provision unit, and a follow-up unit. The analysis unit analyzes the patient's symptoms. The proposal unit proposes the most suitable medical department and medical institution based on the information analyzed by the analysis unit. The summarization unit summarizes the patient's complaints. The provision unit provides the information summarized by the summarization unit to the medical institution. The follow-up unit performs follow-up after the medical treatment. [Effects of the Invention]

[0007] The system according to this embodiment can suggest the most suitable medical department or medical institution based on the patient's symptoms and provide follow-up care after treatment. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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 reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[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 MedGuide AI system according to an embodiment of the present invention is an agent system that utilizes generative AI to provide support for medical consultations and post-consultation support. The MedGuide AI system provides an environment where patients can consult at their own pace and until they are satisfied. The generative AI accurately summarizes the patient's complaints and shares them with the medical institution in advance. The generative AI also provides post-consultation follow-up and continuous support, such as medication guidance. For example, when a patient communicates their symptoms or anxieties via chat or voice, the generative AI analyzes the information and suggests the most suitable medical department and medical institution. Because patients can consult at their own pace and as many times as needed, they can easily confide even minor symptoms or anxieties that might be difficult to discuss face-to-face. This leads to the early detection of symptoms that might otherwise be overlooked. Next, the MedGuide AI system summarizes the patient's symptoms and consultation content and provides it to the medical institution in advance. This facilitates information sharing during consultations, resulting in shorter and more efficient consultation times. Furthermore, as part of post-consultation follow-up, the generative AI provides medication guidance, monitors changes in symptoms, and encourages follow-up visits as needed, supporting continuous health management. This contributes to improved treatment effectiveness and prevention of recurrence. The MedGuide AI system targets both individuals and medical institutions. For individuals, it targets health-conscious individuals and those with chronic illnesses, and for medical institutions, it targets those aiming to improve patient services and operational efficiency. The generating AI analyzes symptoms and questions entered by the user in natural language, compares them with a medical database, and suggests the most suitable medical department and treatment method. It also conducts additional questions and confirmations via chat and voice to achieve highly accurate suggestions. As a result, the MedGuide AI system can analyze a patient's symptoms, suggest the most suitable medical department and medical institution, summarize the complaint and provide it to the medical institution, and conduct post-treatment follow-up.

[0029] The MedGuide AI system according to this embodiment comprises an analysis unit, a proposal unit, a summarization unit, a provision unit, and a follow-up unit. The analysis unit analyzes the patient's symptoms. The analysis unit analyzes the patient's symptoms using, for example, a generative AI. The proposal unit proposes the most suitable medical department or medical institution based on the information analyzed by the analysis unit. The proposal unit proposes the most suitable medical department or medical institution using, for example, a generative AI. The summarization unit summarizes the patient's complaints. The summarization unit summarizes the patient's complaints using, for example, a generative AI. The provision unit provides the information summarized by the summarization unit to the medical institution. The provision unit provides the information summarized using, for example, a generative AI to the medical institution. The follow-up unit performs follow-up after the medical examination. The follow-up unit performs follow-up after the medical examination using, for example, a generative AI. Thus, the MedGuide AI system according to this embodiment can analyze the patient's symptoms, propose the most suitable medical department or medical institution, summarize the complaints and provide them to the medical institution, and perform follow-up after the medical examination.

[0030] The analysis unit analyzes the patient's symptoms. For example, the analysis unit uses generative AI to analyze the patient's symptoms. Specifically, it collects information on symptoms, medical history, and current health status entered by the patient, and the generative AI analyzes this data. The generative AI uses natural language processing technology to understand the patient's input and evaluate the severity of the symptoms and the possibility of related diseases. For example, if a patient enters "chest pain," the generative AI analyzes details such as the nature, duration, and circumstances of the pain and evaluates the possibility of a heart-related disease. The generative AI can also refer to past clinical data and medical literature and apply the latest medical knowledge related to the symptoms. As a result, the analysis unit can quickly and accurately analyze the patient's symptoms and provide basic information for determining the appropriate medical department and treatment plan. Furthermore, the analysis unit can monitor changes in the patient's symptoms and the occurrence of new symptoms in real time and update the analysis results as needed. As a result, the analysis unit can always perform analysis based on the latest information and accurately grasp the patient's health status.

[0031] The Proposal Department suggests the most suitable medical department or healthcare facility based on the information analyzed by the Analysis Department. For example, the Proposal Department uses Generative AI to suggest the most suitable medical department or healthcare facility. Specifically, the Generative AI identifies the most appropriate medical department for the patient's symptoms based on the symptom analysis results provided by the Analysis Department. For example, if chest pain is determined to be highly likely to be a heart-related disease, the Generative AI will suggest a cardiology department. The Generative AI also selects the most suitable healthcare facility by considering information such as the patient's place of residence, desired consultation time, and past medical history. For example, if the patient wishes to be seen on a weekday, the Generative AI will prioritize suggesting healthcare facilities that are open on weekdays. Furthermore, the Generative AI can suggest highly reliable healthcare facilities by referring to healthcare facility ratings and patient feedback. As a result, the Proposal Department can quickly and accurately suggest the most suitable medical department or healthcare facility to the patient, improving the patient's healthcare experience.

[0032] The summarization unit summarizes the patient's complaints. For example, the summarization unit uses generative AI to summarize the patient's complaints. Specifically, the generative AI analyzes information about the patient's symptoms, medical history, and current health status using natural language processing technology, and extracts important information. The generative AI then summarizes the patient's complaints concisely and clearly, creating a report for medical institutions. For example, if a patient inputs, "I've recently experienced chest pain, especially after exercise," the generative AI summarizes this information as, "Chest pain, stronger after exercise." The generative AI can also highlight particularly important or urgent information within the patient's complaints. This allows the summarization unit to quickly and accurately communicate the patient's complaints to medical institutions, providing them with the information necessary for appropriate treatment. Furthermore, the summarization unit can monitor changes in the patient's complaints and the occurrence of new complaints in real time, and update the summary results as needed. This ensures that the summarization unit always provides summaries based on the latest information, offering accurate information to medical institutions.

[0033] The information provision unit provides information summarized by the summarization unit to medical institutions. The information provision unit provides information summarized using, for example, a generating AI to medical institutions. Specifically, the generating AI automatically transmits the summarized information provided by the summarization unit to the medical institution's electronic medical record system and appointment scheduling system. The generating AI converts the summarized information into an appropriate format so that it can be easily used by medical institutions. For example, it automatically inputs the summarized information into designated fields in the electronic medical record so that doctors can refer to it during consultations. In addition, the generating AI can link the summarized information to the appointment scheduling system so that patients can be automatically scheduled for appointments. This allows the information provision unit to provide information to medical institutions quickly and accurately, thereby improving the efficiency of medical care. Furthermore, the information provision unit can collect feedback from medical institutions and continuously improve the accuracy and method of providing the summarized information. This allows the information provision unit to provide high-quality information to medical institutions and improve the quality of medical care.

[0034] The Follow-up Department conducts follow-up after medical treatment. For example, the Follow-up Department uses generative AI to perform post-treatment follow-up. Specifically, the generative AI monitors the patient's progress and changes in symptoms after treatment and provides information to medical institutions as needed. The generative AI analyzes the progress reports and symptom changes entered by the patient and notifies medical institutions if an abnormality is detected. For example, if a patient reports new symptoms after treatment, the generative AI analyzes this information and suggests to the medical institution the need for additional treatment or tests. The generative AI also sends follow-up questions to patients periodically, continuously monitoring their health status. This allows the Follow-up Department to appropriately manage the patient's health status after treatment and provide necessary follow-up promptly. Furthermore, the Follow-up Department can collect feedback from patients and continuously improve the content and methods of follow-up. This enables the Follow-up Department to support patient health management and improve the quality of post-treatment care.

[0035] The interface unit allows for additional questions and confirmations via chat or voice. For example, the interface unit uses generative AI to ask additional questions and confirms via chat or voice. For instance, if a patient enters a question via chat, the generative AI provides an appropriate answer. Furthermore, if a patient enters a question via voice, the generative AI can analyze the voice and provide an appropriate answer. This allows the interface unit to ask additional questions and confirms via chat or voice.

[0036] The monitoring unit can monitor changes in the patient's symptoms. For example, the monitoring unit uses generative AI to monitor changes in the patient's symptoms. For example, the monitoring unit periodically checks the symptoms entered by the patient and records any changes. The monitoring unit can also analyze the changes in symptoms reported by the patient and notify the medical institution as necessary. In this way, the monitoring unit can monitor changes in the patient's symptoms.

[0037] The Follow-Up Care Promotion Department can encourage patients to return for follow-up visits as needed. For example, the Department can use generated AI to prompt patients for follow-up visits as necessary. The Department can also prompt patients for follow-up visits if their symptoms worsen or based on a doctor's judgment. Furthermore, the Department can monitor changes in patients' symptoms and notify them if a follow-up visit is necessary. This allows the Department to prompt patients for follow-up visits as needed.

[0038] The analysis unit can analyze a patient's past medical history to improve the accuracy of symptom analysis. For example, the analysis unit uses generative AI to analyze a patient's past medical history. For example, the analysis unit can refer to a patient's past medical history to check if similar symptoms have recurred. The analysis unit can also evaluate the risk of specific diseases from a patient's past medical history and reflect this in the symptom analysis. Furthermore, the analysis unit can evaluate the effectiveness of treatment based on a patient's past medical history to improve the accuracy of symptom analysis. In this way, the analysis unit can improve the accuracy of symptom analysis by analyzing a patient's past medical history.

[0039] The analysis unit can incorporate patients' lifestyle data and reflect it in symptom analysis. For example, the analysis unit can use generative AI to incorporate patients' lifestyle data. For example, the analysis unit can incorporate data on patients' diet and exercise and analyze the impact of lifestyle on symptoms. The analysis unit can also incorporate patients' sleep data and analyze the impact of sleep deprivation on symptoms. Furthermore, the analysis unit can incorporate patients' stress levels and analyze the impact of stress on symptoms. In this way, the analysis unit can incorporate patients' lifestyle data and reflect it in symptom analysis.

[0040] The analysis unit can consider the patient's geographical location and reflect region-specific disease risks in the symptom analysis. For example, the analysis unit considers the patient's geographical location using generative AI. For example, the analysis unit considers the infectious disease risk in the patient's residential area and reflects it in the symptom analysis. The analysis unit can also consider the environmental pollution risk in the patient's residential area and reflect it in the symptom analysis. Furthermore, the analysis unit can consider the climatic conditions in the patient's residential area and reflect them in the symptom analysis. In this way, the analysis unit can reflect region-specific disease risks in the symptom analysis by considering the patient's geographical location.

[0041] The analysis unit can analyze patients' social media activity and supplement information related to symptom analysis. For example, the analysis unit can analyze patients' social media activity using generative AI. For example, the analysis unit can extract information related to symptoms from patients' social media posts. The analysis unit can also estimate stress levels from patients' social media activity and reflect this in the symptom analysis. Furthermore, the analysis unit can detect changes in lifestyle from patients' social media activity and reflect this in the symptom analysis. In this way, the analysis unit can supplement information related to symptom analysis by analyzing patients' social media activity.

[0042] The suggestion unit can propose the most suitable medical department or healthcare facility by referring to the patient's past medical history. For example, the suggestion unit uses generative AI to refer to the patient's past medical history. For example, the suggestion unit can propose the same medical department based on the patient's past medical history. The suggestion unit can also propose a specific healthcare facility based on the patient's past medical history. Furthermore, the suggestion unit can refer to the patient's past medical history and propose a medical department with a high treatment effectiveness. In this way, the suggestion unit can propose the most suitable medical department or healthcare facility by referring to the patient's past medical history.

[0043] The suggestion function can propose medical departments and healthcare institutions by considering the patient's lifestyle data during the proposal process. For example, the suggestion function can use generative AI to consider the patient's lifestyle data. For example, the suggestion function can propose an appropriate medical department by considering the patient's diet and exercise data. It can also propose an appropriate medical department by considering the patient's sleep data. Furthermore, the suggestion function can propose an appropriate medical department by considering the patient's stress level. In this way, the suggestion function can propose the optimal medical department and healthcare institution by considering the patient's lifestyle data.

[0044] The suggestion function can propose the most suitable medical institution by considering the patient's geographical location information. For example, the suggestion function can use generative AI to consider the patient's geographical location information. For example, the suggestion function can propose a medical institution close to the patient's residential area. The suggestion function can also consider the reputation of medical institutions in the patient's residential area when making suggestions. Furthermore, the suggestion function can also consider transportation access in the patient's residential area when making suggestions. In this way, the suggestion function can propose the most suitable medical institution by considering the patient's geographical location information.

[0045] The suggestion department can analyze a patient's social media activity and suggest relevant medical institutions when making a suggestion. For example, the suggestion department can use generative AI to analyze a patient's social media activity. For example, the suggestion department can extract information about medical institutions from a patient's social media posts. Furthermore, the suggestion department can suggest reputable medical institutions based on the patient's social media activity. In addition, the suggestion department can suggest medical institutions that match the patient's interests based on their social media activity. Thus, by analyzing a patient's social media activity, the suggestion department can suggest relevant medical institutions.

[0046] The summarization unit can improve the accuracy of the summary by referring to the patient's past medical history during the summarization process. For example, the summarization unit can refer to the patient's past medical history using generative AI. For example, the summarization unit can include similar symptoms in the summary based on the patient's past medical history. The summarization unit can also reflect the risk of specific diseases in the summary based on the patient's past medical history. Furthermore, the summarization unit can reflect the effectiveness of treatment in the summary based on the patient's past medical history. In this way, the summarization unit can improve the accuracy of the summary by referring to the patient's past medical history.

[0047] The summarization unit can incorporate and reflect the patient's lifestyle data during the summarization process. For example, the summarization unit can use generative AI to incorporate the patient's lifestyle data. For example, the summarization unit can incorporate data on the patient's diet and exercise, and reflect the impact of lifestyle on symptoms in the summary. The summarization unit can also incorporate the patient's sleep data and reflect the impact of sleep deprivation on symptoms in the summary. Furthermore, the summarization unit can incorporate the patient's stress level and reflect the impact of stress on symptoms in the summary. In this way, the summarization unit can incorporate and reflect the patient's lifestyle data in the summary.

[0048] The summarization unit can adjust the content of the summary by taking into account the patient's geographical location information during the summarization process. For example, the summarization unit can use generative AI to consider the patient's geographical location information. For example, the summarization unit can consider and reflect the infection risk of the patient's residential area in the summary. The summarization unit can also consider and reflect the environmental pollution risk of the patient's residential area in the summary. Furthermore, the summarization unit can consider and reflect the climatic conditions of the patient's residential area in the summary. In this way, the summarization unit can adjust the content of the summary by taking into account the patient's geographical location information.

[0049] The summarization unit can analyze the patient's social media activity during the summarization process and supplement the information relevant to the summary. For example, the summarization unit can use generative AI to analyze the patient's social media activity. For example, the summarization unit can extract information related to symptoms from the patient's social media posts. The summarization unit can also estimate stress levels from the patient's social media activity and reflect this in the summary. Furthermore, the summarization unit can detect changes in lifestyle from the patient's social media activity and reflect this in the summary. In this way, the summarization unit can supplement the information relevant to the summary by analyzing the patient's social media activity.

[0050] The information provider can optimize the content provided by referring to the patient's past medical history when providing information. For example, the information provider can refer to the patient's past medical history using generative AI. For example, the information provider can provide relevant information based on the patient's past medical history. The information provider can also provide information about specific diseases from the patient's past medical history. Furthermore, the information provider can refer to the patient's past medical history and provide information about the effectiveness of treatment. In this way, the information provider can optimize the content provided by referring to the patient's past medical history.

[0051] The information provider can customize the content provided by considering the patient's lifestyle data. For example, the provider can use generative AI to consider the patient's lifestyle data. For example, the provider can provide appropriate information by considering the patient's diet and exercise data. The provider can also provide appropriate information by considering the patient's sleep data. Furthermore, the provider can provide appropriate information by considering the patient's stress level. In this way, the provider can customize the content provided by considering the patient's lifestyle data.

[0052] The information provider can adjust the content of the information provided by considering the patient's geographical location. For example, the provider can use generative AI to consider the patient's geographical location. For example, the provider can provide information considering the infectious disease risk in the patient's residential area. The provider can also provide information considering the environmental pollution risk in the patient's residential area. Furthermore, the provider can provide information considering the climatic conditions in the patient's residential area. In this way, the provider can adjust the content of the information provided by considering the patient's geographical location.

[0053] The information provider can analyze the patient's social media activity when providing information and supplement the content provided. For example, the provider can use generative AI to analyze the patient's social media activity. For example, the provider can extract relevant information from the patient's social media posts. The provider can also estimate the patient's stress level from their social media activity and provide information. Furthermore, the provider can detect changes in lifestyle habits from the patient's social media activity and provide information. In this way, the provider can supplement the content provided by analyzing the patient's social media activity.

[0054] The follow-up unit can select the optimal follow-up method by referring to the patient's past medical history during follow-up. For example, the follow-up unit can use generative AI to refer to the patient's past medical history. For example, the follow-up unit can perform follow-up for similar symptoms based on the patient's past medical history. The follow-up unit can also perform follow-up for specific diseases based on the patient's past medical history. Furthermore, the follow-up unit can refer to the patient's past medical history and perform follow-up based on the effectiveness of treatment. In this way, the follow-up unit can select the optimal follow-up method by referring to the patient's past medical history.

[0055] The follow-up unit can customize follow-up content by considering the patient's lifestyle data during follow-up. For example, the follow-up unit can use generative AI to consider the patient's lifestyle data. For example, the follow-up unit can consider the patient's diet and exercise data to provide appropriate follow-up. The follow-up unit can also consider the patient's sleep data to provide appropriate follow-up. Furthermore, the follow-up unit can consider the patient's stress level to provide appropriate follow-up. In this way, the follow-up unit can customize follow-up content by considering the patient's lifestyle data.

[0056] The follow-up unit can select the optimal follow-up method by considering the patient's geographical location information during follow-up. For example, the follow-up unit can use generative AI to consider the patient's geographical location information. For example, the follow-up unit can perform follow-up considering the infectious disease risk in the patient's residential area. Furthermore, the follow-up unit can perform follow-up considering the environmental pollution risk in the patient's residential area. In addition, the follow-up unit can perform follow-up considering the climatic conditions of the patient's residential area. As a result, the follow-up unit can select the optimal follow-up method by considering the patient's geographical location information.

[0057] The follow-up unit can analyze the patient's social media activity during follow-up sessions to supplement the follow-up content. For example, the follow-up unit can use generative AI to analyze the patient's social media activity. For example, the follow-up unit can extract relevant information from the patient's social media posts. The follow-up unit can also estimate the patient's stress level from their social media activity and use that information for follow-up. Furthermore, the follow-up unit can detect changes in lifestyle habits from the patient's social media activity and use that information for follow-up. In this way, the follow-up unit can supplement the follow-up content by analyzing the patient's social media activity.

[0058] The interface unit can select the optimal display method by referring to the patient's past operation history when displaying the interface. For example, the interface unit can refer to the patient's past operation history using a generation AI. For example, the interface unit can prioritize displaying interface designs that the patient has frequently used in the past. The interface unit can also detect specific operation patterns from the patient's past operation history and provide the optimal display method. Furthermore, the interface unit can provide a display method that improves operation efficiency based on the patient's past operation history. In this way, the interface unit can select the optimal display method by referring to the patient's past operation history.

[0059] The interface unit can select the optimal display method when displaying the interface, taking into account the patient's device information. For example, the interface unit considers the patient's device information using a generation AI. For example, if the patient is using a smartphone, the interface unit provides a display method that matches the screen size. The interface unit can also provide a display method optimized for larger screens if the patient is using a tablet. Furthermore, if the patient is using a smartwatch, the interface unit can provide a concise and highly visible display method. In this way, the interface unit can select the optimal display method by taking into account the patient's device information.

[0060] The interface unit can refer to the patient's calendar information and make suggestions based on their schedule when displaying the interface. For example, the interface unit uses a generation AI to refer to the patient's calendar information. For example, the interface unit can refer to the appointments registered in the patient's calendar and adjust the content displayed on the interface. Furthermore, the interface unit can display information related to specific events from the patient's calendar information. In addition, the interface unit can suggest the optimal operating procedure based on the patient's schedule, using the patient's calendar information. Thus, the interface unit can make suggestions based on the patient's schedule by referring to their calendar information.

[0061] The interface unit can refer to the patient's social media activity and display relevant information when the interface is displayed. For example, the interface unit uses generative AI to refer to the patient's social media activity. For example, the interface unit extracts relevant information from the patient's social media posts and displays it on the interface. Furthermore, the interface unit can display information of high interest from the patient's social media activity. In addition, the interface unit can detect changes in lifestyle from the patient's social media activity and display relevant information. Thus, the interface unit can display relevant information by referring to the patient's social media activity.

[0062] The monitoring unit can improve the accuracy of monitoring by referring to the patient's past medical history during monitoring. For example, the monitoring unit can refer to the patient's past medical history using generative AI. For example, the monitoring unit can include similar symptoms in the monitoring based on the patient's past medical history. The monitoring unit can also reflect the risk of specific diseases in the monitoring based on the patient's past medical history. Furthermore, the monitoring unit can reflect the effectiveness of treatment in the monitoring based on the patient's past medical history. In this way, the monitoring unit can improve the accuracy of monitoring by referring to the patient's past medical history.

[0063] The monitoring unit can acquire and incorporate patient lifestyle data during monitoring. For example, the monitoring unit can acquire patient lifestyle data using generative AI. For example, the monitoring unit can acquire data on the patient's diet and exercise and incorporate the impact of lifestyle on symptoms into monitoring. The monitoring unit can also acquire patient sleep data and incorporate the impact of sleep deprivation on symptoms into monitoring. Furthermore, the monitoring unit can acquire the patient's stress level and incorporate the impact of stress on symptoms into monitoring. In this way, the monitoring unit can incorporate patient lifestyle data and incorporate it into monitoring.

[0064] The monitoring unit can adjust its monitoring content by considering the patient's geographical location information during monitoring. For example, the monitoring unit can use generative AI to consider the patient's geographical location information. For example, the monitoring unit can consider the infectious disease risk of the patient's residential area and reflect it in the monitoring. The monitoring unit can also consider the environmental pollution risk of the patient's residential area and reflect it in the monitoring. Furthermore, the monitoring unit can consider the climatic conditions of the patient's residential area and reflect them in the monitoring. In this way, the monitoring unit can adjust its monitoring content by considering the patient's geographical location information.

[0065] The monitoring unit can analyze the patient's social media activity during monitoring to supplement the monitoring data. For example, the monitoring unit can use generative AI to analyze the patient's social media activity. For example, the monitoring unit can extract relevant information from the patient's social media posts. The monitoring unit can also estimate the stress level from the patient's social media activity and reflect it in the monitoring. Furthermore, the monitoring unit can detect changes in lifestyle habits from the patient's social media activity and reflect them in the monitoring. In this way, the monitoring unit can supplement the monitoring data by analyzing the patient's social media activity.

[0066] The follow-up consultation promotion unit can select the optimal follow-up consultation method by referring to the patient's past medical history when promoting a follow-up consultation. For example, the follow-up consultation promotion unit can refer to the patient's past medical history using generative AI. For example, the follow-up consultation promotion unit can encourage a follow-up consultation for similar symptoms based on the patient's past medical history. The follow-up consultation promotion unit can also encourage a follow-up consultation for a specific disease based on the patient's past medical history. Furthermore, the follow-up consultation promotion unit can also refer to the patient's past medical history and encourage a follow-up consultation based on the effectiveness of the treatment. In this way, the follow-up consultation promotion unit can select the optimal follow-up consultation method by referring to the patient's past medical history.

[0067] The follow-up consultation promotion unit can customize the content of follow-up consultations by considering the patient's lifestyle data when promoting them. For example, the follow-up consultation promotion unit considers the patient's lifestyle data using generative AI. For example, the follow-up consultation promotion unit considers the patient's diet and exercise data to encourage appropriate follow-up consultations. Furthermore, the follow-up consultation promotion unit can also consider the patient's sleep data to encourage appropriate follow-up consultations. In addition, the follow-up consultation promotion unit can consider the patient's stress level to encourage appropriate follow-up consultations. As a result, the follow-up consultation promotion unit can customize the content of follow-up consultations by considering the patient's lifestyle data.

[0068] The follow-up consultation promotion unit can select the optimal follow-up consultation method by considering the patient's geographical location information when promoting a follow-up consultation. For example, the follow-up consultation promotion unit considers the patient's geographical location information using generative AI. For example, the follow-up consultation promotion unit can encourage a follow-up consultation by considering the infectious disease risk in the patient's residential area. Furthermore, the follow-up consultation promotion unit can encourage a follow-up consultation by considering the environmental pollution risk in the patient's residential area. In addition, the follow-up consultation promotion unit can encourage a follow-up consultation by considering the climatic conditions in the patient's residential area. As a result, the follow-up consultation promotion unit can select the optimal follow-up consultation method by considering the patient's geographical location information.

[0069] The Follow-Up Promotion Unit can analyze a patient's social media activity and supplement the content of the follow-up visit when promoting a follow-up visit. For example, the Follow-Up Promotion Unit can analyze a patient's social media activity using generative AI. For example, the Follow-Up Promotion Unit can extract relevant information from a patient's social media posts. The Follow-Up Promotion Unit can also estimate a patient's stress level from their social media activity and encourage a follow-up visit. Furthermore, the Follow-Up Promotion Unit can detect changes in lifestyle from a patient's social media activity and encourage a follow-up visit. In this way, the Follow-Up Promotion Unit can supplement the content of the follow-up visit by analyzing a patient's social media activity.

[0070] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0071] The analysis unit can improve the accuracy of symptom analysis by analyzing the patient's past medical history. For example, it can refer to the patient's past medical history to check if similar symptoms have recurred. It can also assess the risk of specific diseases from the patient's past medical history and reflect this in the symptom analysis. Furthermore, it can evaluate the effectiveness of treatment based on the patient's past medical history and improve the accuracy of symptom analysis. In this way, the analysis unit can improve the accuracy of symptom analysis by analyzing the patient's past medical history.

[0072] The proposal unit can suggest the most suitable medical department or healthcare facility by referring to the patient's past medical history. For example, it can suggest the same medical department based on the patient's past medical history. It can also suggest a specific healthcare facility based on the patient's past medical history. Furthermore, it can suggest a medical department with a high treatment effectiveness by referring to the patient's past medical history. In this way, the proposal unit can suggest the most suitable medical department or healthcare facility by referring to the patient's past medical history.

[0073] The summarization section can improve the accuracy of the summary by referring to the patient's past medical history. For example, it can include similar symptoms in the summary based on the patient's past medical history. It can also reflect the risk of specific diseases in the summary based on the patient's past medical history. Furthermore, it can reflect the effectiveness of treatment in the summary based on the patient's past medical history. In this way, the summarization section can improve the accuracy of the summary by referring to the patient's past medical history.

[0074] The information provider can optimize the content provided by referring to the patient's past medical history. For example, it can provide relevant information based on the patient's past medical history. It can also provide information about specific diseases based on the patient's past medical history. Furthermore, it can provide information about the effectiveness of treatment by referring to the patient's past medical history. In this way, the information provider can optimize the content provided by referring to the patient's past medical history.

[0075] The follow-up unit can select the optimal follow-up method by referring to the patient's past medical history during follow-up. For example, it can perform follow-up for similar symptoms based on the patient's past medical history. It can also perform follow-up for specific diseases based on the patient's past medical history. Furthermore, it can perform follow-up based on the effectiveness of treatment by referring to the patient's past medical history. In this way, the follow-up unit can select the optimal follow-up method by referring to the patient's past medical history.

[0076] The following briefly describes the processing flow for example form 1.

[0077] Step 1: The analysis unit analyzes the patient's symptoms. For example, it uses generative AI to analyze the patient's symptoms. Step 2: The proposal unit proposes the most suitable medical departments and medical institutions based on the information analyzed by the analysis unit. For example, it may use generative AI to propose the most suitable medical departments and medical institutions. Step 3: The summarization section summarizes the patient's complaint. For example, a generative AI is used to summarize the patient's complaint. Step 4: The providing unit provides the information summarized by the summarizing unit to the medical institution. For example, the information summarized using a generation AI is provided to the medical institution. Step 5: The follow-up department performs follow-up after the medical examination. For example, they use generative AI to perform post-examination follow-up.

[0078] (Example of form 2) The MedGuide AI system according to an embodiment of the present invention is an agent system that utilizes generative AI to provide support for medical consultations and post-consultation support. The MedGuide AI system provides an environment where patients can consult at their own pace and until they are satisfied. The generative AI accurately summarizes the patient's complaints and shares them with the medical institution in advance. The generative AI also provides post-consultation follow-up and continuous support, such as medication guidance. For example, when a patient communicates their symptoms or anxieties via chat or voice, the generative AI analyzes the information and suggests the most suitable medical department and medical institution. Because patients can consult at their own pace and as many times as needed, they can easily confide even minor symptoms or anxieties that might be difficult to discuss face-to-face. This leads to the early detection of symptoms that might otherwise be overlooked. Next, the MedGuide AI system summarizes the patient's symptoms and consultation content and provides it to the medical institution in advance. This facilitates information sharing during consultations, resulting in shorter and more efficient consultation times. Furthermore, as part of post-consultation follow-up, the generative AI provides medication guidance, monitors changes in symptoms, and encourages follow-up visits as needed, supporting continuous health management. This contributes to improved treatment effectiveness and prevention of recurrence. The MedGuide AI system targets both individuals and medical institutions. For individuals, it targets health-conscious individuals and those with chronic illnesses, and for medical institutions, it targets those aiming to improve patient services and operational efficiency. The generating AI analyzes symptoms and questions entered by the user in natural language, compares them with a medical database, and suggests the most suitable medical department and treatment method. It also conducts additional questions and confirmations via chat and voice to achieve highly accurate suggestions. As a result, the MedGuide AI system can analyze a patient's symptoms, suggest the most suitable medical department and medical institution, summarize the complaint and provide it to the medical institution, and conduct post-treatment follow-up.

[0079] The MedGuide AI system according to this embodiment comprises an analysis unit, a proposal unit, a summarization unit, a provision unit, and a follow-up unit. The analysis unit analyzes the patient's symptoms. The analysis unit analyzes the patient's symptoms using, for example, a generative AI. The proposal unit proposes the most suitable medical department or medical institution based on the information analyzed by the analysis unit. The proposal unit proposes the most suitable medical department or medical institution using, for example, a generative AI. The summarization unit summarizes the patient's complaints. The summarization unit summarizes the patient's complaints using, for example, a generative AI. The provision unit provides the information summarized by the summarization unit to the medical institution. The provision unit provides the information summarized using, for example, a generative AI to the medical institution. The follow-up unit performs follow-up after the medical examination. The follow-up unit performs follow-up after the medical examination using, for example, a generative AI. Thus, the MedGuide AI system according to this embodiment can analyze the patient's symptoms, propose the most suitable medical department or medical institution, summarize the complaints and provide them to the medical institution, and perform follow-up after the medical examination.

[0080] The analysis unit analyzes the patient's symptoms. For example, the analysis unit uses generative AI to analyze the patient's symptoms. Specifically, it collects information on symptoms, medical history, and current health status entered by the patient, and the generative AI analyzes this data. The generative AI uses natural language processing technology to understand the patient's input and evaluate the severity of the symptoms and the possibility of related diseases. For example, if a patient enters "chest pain," the generative AI analyzes details such as the nature, duration, and circumstances of the pain and evaluates the possibility of a heart-related disease. The generative AI can also refer to past clinical data and medical literature and apply the latest medical knowledge related to the symptoms. As a result, the analysis unit can quickly and accurately analyze the patient's symptoms and provide basic information for determining the appropriate medical department and treatment plan. Furthermore, the analysis unit can monitor changes in the patient's symptoms and the occurrence of new symptoms in real time and update the analysis results as needed. As a result, the analysis unit can always perform analysis based on the latest information and accurately grasp the patient's health status.

[0081] The Proposal Department suggests the most suitable medical department or healthcare facility based on the information analyzed by the Analysis Department. For example, the Proposal Department uses Generative AI to suggest the most suitable medical department or healthcare facility. Specifically, the Generative AI identifies the most appropriate medical department for the patient's symptoms based on the symptom analysis results provided by the Analysis Department. For example, if chest pain is determined to be highly likely to be a heart-related disease, the Generative AI will suggest a cardiology department. The Generative AI also selects the most suitable healthcare facility by considering information such as the patient's place of residence, desired consultation time, and past medical history. For example, if the patient wishes to be seen on a weekday, the Generative AI will prioritize suggesting healthcare facilities that are open on weekdays. Furthermore, the Generative AI can suggest highly reliable healthcare facilities by referring to healthcare facility ratings and patient feedback. As a result, the Proposal Department can quickly and accurately suggest the most suitable medical department or healthcare facility to the patient, improving the patient's healthcare experience.

[0082] The summarization unit summarizes the patient's complaints. For example, the summarization unit uses generative AI to summarize the patient's complaints. Specifically, the generative AI analyzes information about the patient's symptoms, medical history, and current health status using natural language processing technology, and extracts important information. The generative AI then summarizes the patient's complaints concisely and clearly, creating a report for medical institutions. For example, if a patient inputs, "I've recently experienced chest pain, especially after exercise," the generative AI summarizes this information as, "Chest pain, stronger after exercise." The generative AI can also highlight particularly important or urgent information within the patient's complaints. This allows the summarization unit to quickly and accurately communicate the patient's complaints to medical institutions, providing them with the information necessary for appropriate treatment. Furthermore, the summarization unit can monitor changes in the patient's complaints and the occurrence of new complaints in real time, and update the summary results as needed. This ensures that the summarization unit always provides summaries based on the latest information, offering accurate information to medical institutions.

[0083] The information provision unit provides information summarized by the summarization unit to medical institutions. The information provision unit provides information summarized using, for example, a generating AI to medical institutions. Specifically, the generating AI automatically transmits the summarized information provided by the summarization unit to the medical institution's electronic medical record system and appointment scheduling system. The generating AI converts the summarized information into an appropriate format so that it can be easily used by medical institutions. For example, it automatically inputs the summarized information into designated fields in the electronic medical record so that doctors can refer to it during consultations. In addition, the generating AI can link the summarized information to the appointment scheduling system so that patients can be automatically scheduled for appointments. This allows the information provision unit to provide information to medical institutions quickly and accurately, thereby improving the efficiency of medical care. Furthermore, the information provision unit can collect feedback from medical institutions and continuously improve the accuracy and method of providing the summarized information. This allows the information provision unit to provide high-quality information to medical institutions and improve the quality of medical care.

[0084] The Follow-up Department conducts follow-up after medical treatment. For example, the Follow-up Department uses generative AI to perform post-treatment follow-up. Specifically, the generative AI monitors the patient's progress and changes in symptoms after treatment and provides information to medical institutions as needed. The generative AI analyzes the progress reports and symptom changes entered by the patient and notifies medical institutions if an abnormality is detected. For example, if a patient reports new symptoms after treatment, the generative AI analyzes this information and suggests to the medical institution the need for additional treatment or tests. The generative AI also sends follow-up questions to patients periodically, continuously monitoring their health status. This allows the Follow-up Department to appropriately manage the patient's health status after treatment and provide necessary follow-up promptly. Furthermore, the Follow-up Department can collect feedback from patients and continuously improve the content and methods of follow-up. This enables the Follow-up Department to support patient health management and improve the quality of post-treatment care.

[0085] The interface unit allows for additional questions and confirmations via chat or voice. For example, the interface unit uses generative AI to ask additional questions and confirms via chat or voice. For instance, if a patient enters a question via chat, the generative AI provides an appropriate answer. Furthermore, if a patient enters a question via voice, the generative AI can analyze the voice and provide an appropriate answer. This allows the interface unit to ask additional questions and confirms via chat or voice.

[0086] The monitoring unit can monitor changes in the patient's symptoms. For example, the monitoring unit uses generative AI to monitor changes in the patient's symptoms. For example, the monitoring unit periodically checks the symptoms entered by the patient and records any changes. The monitoring unit can also analyze the changes in symptoms reported by the patient and notify the medical institution as necessary. In this way, the monitoring unit can monitor changes in the patient's symptoms.

[0087] The Follow-Up Care Promotion Department can encourage patients to return for follow-up visits as needed. For example, the Department can use generated AI to prompt patients for follow-up visits as necessary. The Department can also prompt patients for follow-up visits if their symptoms worsen or based on a doctor's judgment. Furthermore, the Department can monitor changes in patients' symptoms and notify them if a follow-up visit is necessary. This allows the Department to prompt patients for follow-up visits as needed.

[0088] The analysis unit can estimate the patient's emotions and adjust the accuracy of the symptom analysis based on the estimated emotions. For example, the analysis unit uses generative AI to estimate the patient's emotions. If the patient is feeling anxious, the generative AI can perform a detailed symptom analysis and provide information to alleviate their anxiety. If the patient is relaxed, the generative AI can perform a concise symptom analysis and provide only the necessary information. Furthermore, if the patient is in a hurry, the generative AI can perform a rapid symptom analysis and provide results quickly. This allows the analysis unit to adjust the accuracy of the symptom analysis based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0089] The analysis unit can analyze a patient's past medical history to improve the accuracy of symptom analysis. For example, the analysis unit uses generative AI to analyze a patient's past medical history. For example, the analysis unit can refer to a patient's past medical history to check if similar symptoms have recurred. The analysis unit can also evaluate the risk of specific diseases from a patient's past medical history and reflect this in the symptom analysis. Furthermore, the analysis unit can evaluate the effectiveness of treatment based on a patient's past medical history to improve the accuracy of symptom analysis. In this way, the analysis unit can improve the accuracy of symptom analysis by analyzing a patient's past medical history.

[0090] The analysis unit can incorporate patients' lifestyle data and reflect it in symptom analysis. For example, the analysis unit can use generative AI to incorporate patients' lifestyle data. For example, the analysis unit can incorporate data on patients' diet and exercise and analyze the impact of lifestyle on symptoms. The analysis unit can also incorporate patients' sleep data and analyze the impact of sleep deprivation on symptoms. Furthermore, the analysis unit can incorporate patients' stress levels and analyze the impact of stress on symptoms. In this way, the analysis unit can incorporate patients' lifestyle data and reflect it in symptom analysis.

[0091] The analysis unit can estimate the patient's emotions and determine the priority of symptom analysis based on the estimated emotions. For example, the analysis unit uses generative AI to estimate the patient's emotions. For example, if the patient is experiencing strong anxiety, the generative AI will prioritize analyzing that symptom. The analysis unit can also have the generative AI prioritize the analysis of other patients' symptoms if the patient is relaxed. Furthermore, if the patient is in a hurry, the generative AI can perform a rapid symptom analysis and provide the results preferentially. This allows the analysis unit to determine the priority of symptom analysis based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0092] The analysis unit can consider the patient's geographical location and reflect region-specific disease risks in the symptom analysis. For example, the analysis unit considers the patient's geographical location using generative AI. For example, the analysis unit considers the infectious disease risk in the patient's residential area and reflects it in the symptom analysis. The analysis unit can also consider the environmental pollution risk in the patient's residential area and reflect it in the symptom analysis. Furthermore, the analysis unit can consider the climatic conditions in the patient's residential area and reflect them in the symptom analysis. In this way, the analysis unit can reflect region-specific disease risks in the symptom analysis by considering the patient's geographical location.

[0093] The analysis unit can analyze patients' social media activity and supplement information related to symptom analysis. For example, the analysis unit can analyze patients' social media activity using generative AI. For example, the analysis unit can extract information related to symptoms from patients' social media posts. The analysis unit can also estimate stress levels from patients' social media activity and reflect this in the symptom analysis. Furthermore, the analysis unit can detect changes in lifestyle from patients' social media activity and reflect this in the symptom analysis. In this way, the analysis unit can supplement information related to symptom analysis by analyzing patients' social media activity.

[0094] The suggestion unit can estimate the patient's emotions and adjust the way it presents its suggestions based on those emotions. For example, the suggestion unit might use generative AI to estimate the patient's emotions. If the patient is feeling anxious, the generative AI might present suggestions in gentle language. If the patient is relaxed, the generative AI might present suggestions containing more detailed information. Furthermore, if the patient is in a hurry, the generative AI might present concise and quick suggestions. This allows the suggestion unit to adjust the way it presents its suggestions based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0095] The suggestion unit can propose the most suitable medical department or healthcare facility by referring to the patient's past medical history. For example, the suggestion unit uses generative AI to refer to the patient's past medical history. For example, the suggestion unit can propose the same medical department based on the patient's past medical history. The suggestion unit can also propose a specific healthcare facility based on the patient's past medical history. Furthermore, the suggestion unit can refer to the patient's past medical history and propose a medical department with a high treatment effectiveness. In this way, the suggestion unit can propose the most suitable medical department or healthcare facility by referring to the patient's past medical history.

[0096] The suggestion function can propose medical departments and healthcare institutions by considering the patient's lifestyle data during the proposal process. For example, the suggestion function can use generative AI to consider the patient's lifestyle data. For example, the suggestion function can propose an appropriate medical department by considering the patient's diet and exercise data. It can also propose an appropriate medical department by considering the patient's sleep data. Furthermore, the suggestion function can propose an appropriate medical department by considering the patient's stress level. In this way, the suggestion function can propose the optimal medical department and healthcare institution by considering the patient's lifestyle data.

[0097] The suggestion unit can estimate the patient's emotions and prioritize suggestions based on those emotions. For example, the suggestion unit might use generative AI to estimate the patient's emotions. If the patient is experiencing strong anxiety, the generative AI might prioritize suggestions related to that symptom. The suggestion unit might also have the generative AI prioritize suggestions for other patients if the patient is relaxed. Furthermore, if the patient is in a hurry, the generative AI might quickly provide suggestions and prioritize the results. This allows the suggestion unit to prioritize suggestions based on the patient's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The suggestion function can propose the most suitable medical institution by considering the patient's geographical location information. For example, the suggestion function can use generative AI to consider the patient's geographical location information. For example, the suggestion function can propose a medical institution close to the patient's residential area. The suggestion function can also consider the reputation of medical institutions in the patient's residential area when making suggestions. Furthermore, the suggestion function can also consider transportation access in the patient's residential area when making suggestions. In this way, the suggestion function can propose the most suitable medical institution by considering the patient's geographical location information.

[0099] The suggestion department can analyze a patient's social media activity and suggest relevant medical institutions when making a suggestion. For example, the suggestion department can use generative AI to analyze a patient's social media activity. For example, the suggestion department can extract information about medical institutions from a patient's social media posts. Furthermore, the suggestion department can suggest reputable medical institutions based on the patient's social media activity. In addition, the suggestion department can suggest medical institutions that match the patient's interests based on their social media activity. Thus, by analyzing a patient's social media activity, the suggestion department can suggest relevant medical institutions.

[0100] The summarization unit can estimate the patient's emotions and adjust the way the summary is presented based on the estimated emotions. For example, the summarization unit might use generative AI to estimate the patient's emotions. If the patient is feeling anxious, the generative AI might create a summary in gentle language. If the patient is relaxed, the generative AI might create a summary with more detailed information. Furthermore, if the patient is in a hurry, the generative AI might create a concise and rapid summary. This allows the summarization unit to adjust the way the summary is presented based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0101] The summarization unit can improve the accuracy of the summary by referring to the patient's past medical history during the summarization process. For example, the summarization unit can refer to the patient's past medical history using generative AI. For example, the summarization unit can include similar symptoms in the summary based on the patient's past medical history. The summarization unit can also reflect the risk of specific diseases in the summary based on the patient's past medical history. Furthermore, the summarization unit can reflect the effectiveness of treatment in the summary based on the patient's past medical history. In this way, the summarization unit can improve the accuracy of the summary by referring to the patient's past medical history.

[0102] The summarization unit can incorporate and reflect the patient's lifestyle data during the summarization process. For example, the summarization unit can use generative AI to incorporate the patient's lifestyle data. For example, the summarization unit can incorporate data on the patient's diet and exercise, and reflect the impact of lifestyle on symptoms in the summary. The summarization unit can also incorporate the patient's sleep data and reflect the impact of sleep deprivation on symptoms in the summary. Furthermore, the summarization unit can incorporate the patient's stress level and reflect the impact of stress on symptoms in the summary. In this way, the summarization unit can incorporate and reflect the patient's lifestyle data in the summary.

[0103] The summarization unit can estimate the patient's emotions and prioritize summaries based on the estimated emotions. For example, the summarization unit uses generative AI to estimate the patient's emotions. For instance, if the patient is experiencing strong anxiety, the generative AI will prioritize summaries related to that symptom. The summarization unit can also have the generative AI prioritize summaries for other patients if the patient is relaxed. Furthermore, if the patient is in a hurry, the generative AI can quickly perform a summary and prioritize the results. This allows the summarization unit to prioritize summaries based on the patient's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The summarization unit can adjust the content of the summary by taking into account the patient's geographical location information during the summarization process. For example, the summarization unit can use generative AI to consider the patient's geographical location information. For example, the summarization unit can consider and reflect the infection risk of the patient's residential area in the summary. The summarization unit can also consider and reflect the environmental pollution risk of the patient's residential area in the summary. Furthermore, the summarization unit can consider and reflect the climatic conditions of the patient's residential area in the summary. In this way, the summarization unit can adjust the content of the summary by taking into account the patient's geographical location information.

[0105] The summarization unit can analyze the patient's social media activity during the summarization process and supplement the information relevant to the summary. For example, the summarization unit can use generative AI to analyze the patient's social media activity. For example, the summarization unit can extract information related to symptoms from the patient's social media posts. The summarization unit can also estimate stress levels from the patient's social media activity and reflect this in the summary. Furthermore, the summarization unit can detect changes in lifestyle from the patient's social media activity and reflect this in the summary. In this way, the summarization unit can supplement the information relevant to the summary by analyzing the patient's social media activity.

[0106] The information provider can estimate the patient's emotions and adjust the timing of information delivery based on the estimated emotions. For example, the provider can estimate the patient's emotions using generative AI. For example, if the patient is feeling anxious, the generative AI can provide information quickly. Furthermore, if the patient is relaxed, the generative AI can provide information at an appropriate time. Additionally, if the patient is in a hurry, the generative AI can provide information immediately. This allows the provider to adjust the timing of information delivery based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0107] The information provider can optimize the content provided by referring to the patient's past medical history when providing information. For example, the information provider can refer to the patient's past medical history using generative AI. For example, the information provider can provide relevant information based on the patient's past medical history. The information provider can also provide information about specific diseases from the patient's past medical history. Furthermore, the information provider can refer to the patient's past medical history and provide information about the effectiveness of treatment. In this way, the information provider can optimize the content provided by referring to the patient's past medical history.

[0108] The information provider can customize the content provided by considering the patient's lifestyle data. For example, the provider can use generative AI to consider the patient's lifestyle data. For example, the provider can provide appropriate information by considering the patient's diet and exercise data. The provider can also provide appropriate information by considering the patient's sleep data. Furthermore, the provider can provide appropriate information by considering the patient's stress level. In this way, the provider can customize the content provided by considering the patient's lifestyle data.

[0109] The information provider can estimate the patient's emotions and prioritize information delivery based on the estimated emotions. For example, the provider might use generative AI to estimate the patient's emotions. If, for example, the patient is experiencing strong anxiety, the generative AI will prioritize providing that information. Furthermore, if the patient is relaxed, the generative AI can prioritize providing information to other patients. Additionally, if the patient is in a hurry, the generative AI can provide information quickly and prioritize the delivery of results. This allows the provider to prioritize information delivery based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0110] The information provider can adjust the content of the information provided by considering the patient's geographical location. For example, the provider can use generative AI to consider the patient's geographical location. For example, the provider can provide information considering the infectious disease risk in the patient's residential area. The provider can also provide information considering the environmental pollution risk in the patient's residential area. Furthermore, the provider can provide information considering the climatic conditions in the patient's residential area. In this way, the provider can adjust the content of the information provided by considering the patient's geographical location.

[0111] The information provider can analyze the patient's social media activity when providing information and supplement the content provided. For example, the provider can use generative AI to analyze the patient's social media activity. For example, the provider can extract relevant information from the patient's social media posts. The provider can also estimate the patient's stress level from their social media activity and provide information. Furthermore, the provider can detect changes in lifestyle habits from the patient's social media activity and provide information. In this way, the provider can supplement the content provided by analyzing the patient's social media activity.

[0112] The follow-up unit can estimate the patient's emotions and adjust the follow-up method based on the estimated emotions. For example, the follow-up unit might use generative AI to estimate the patient's emotions. If the patient is feeling anxious, the generative AI can provide a detailed follow-up. If the patient is relaxed, the generative AI can provide a concise follow-up. Furthermore, if the patient is in a hurry, the generative AI can provide a rapid follow-up. This allows the follow-up unit to adjust the follow-up method based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0113] The follow-up unit can select the optimal follow-up method by referring to the patient's past medical history during follow-up. For example, the follow-up unit can use generative AI to refer to the patient's past medical history. For example, the follow-up unit can perform follow-up for similar symptoms based on the patient's past medical history. The follow-up unit can also perform follow-up for specific diseases based on the patient's past medical history. Furthermore, the follow-up unit can refer to the patient's past medical history and perform follow-up based on the effectiveness of treatment. In this way, the follow-up unit can select the optimal follow-up method by referring to the patient's past medical history.

[0114] The follow-up unit can customize follow-up content by considering the patient's lifestyle data during follow-up. For example, the follow-up unit can use generative AI to consider the patient's lifestyle data. For example, the follow-up unit can consider the patient's diet and exercise data to provide appropriate follow-up. The follow-up unit can also consider the patient's sleep data to provide appropriate follow-up. Furthermore, the follow-up unit can consider the patient's stress level to provide appropriate follow-up. In this way, the follow-up unit can customize follow-up content by considering the patient's lifestyle data.

[0115] The follow-up unit can estimate the patient's emotions and determine the priority of follow-ups based on the estimated emotions. For example, the follow-up unit might use generative AI to estimate the patient's emotions. For instance, if a patient is experiencing strong anxiety, the generative AI might prioritize that follow-up. Conversely, if a patient is relaxed, the generative AI might prioritize other patients' follow-ups. Furthermore, if a patient is in a hurry, the generative AI might perform a rapid follow-up and prioritize the provision of results. This allows the follow-up unit to determine the priority of follow-ups based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0116] The follow-up unit can select the optimal follow-up method by considering the patient's geographical location information during follow-up. For example, the follow-up unit can use generative AI to consider the patient's geographical location information. For example, the follow-up unit can perform follow-up considering the infectious disease risk in the patient's residential area. Furthermore, the follow-up unit can perform follow-up considering the environmental pollution risk in the patient's residential area. In addition, the follow-up unit can perform follow-up considering the climatic conditions of the patient's residential area. As a result, the follow-up unit can select the optimal follow-up method by considering the patient's geographical location information.

[0117] The follow-up unit can analyze the patient's social media activity during follow-up sessions to supplement the follow-up content. For example, the follow-up unit can use generative AI to analyze the patient's social media activity. For example, the follow-up unit can extract relevant information from the patient's social media posts. The follow-up unit can also estimate the patient's stress level from their social media activity and use that information for follow-up. Furthermore, the follow-up unit can detect changes in lifestyle habits from the patient's social media activity and use that information for follow-up. In this way, the follow-up unit can supplement the follow-up content by analyzing the patient's social media activity.

[0118] The interface unit can estimate the patient's emotions and adjust the interface display method based on the estimated emotions. For example, the interface unit estimates the patient's emotions using generative AI. For example, if the patient is tense, the interface unit provides a calming color scheme to reduce visual stress. Conversely, if the patient is enjoying themselves, the interface unit provides a bright color scheme to make the input process more enjoyable. Furthermore, if the patient is tired, the interface unit provides a simple and highly visible interface to facilitate the input process. Thus, the interface unit can adjust the interface display method based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0119] The interface unit can select the optimal display method by referring to the patient's past operation history when displaying the interface. For example, the interface unit can refer to the patient's past operation history using a generation AI. For example, the interface unit can prioritize displaying interface designs that the patient has frequently used in the past. The interface unit can also detect specific operation patterns from the patient's past operation history and provide the optimal display method. Furthermore, the interface unit can provide a display method that improves operation efficiency based on the patient's past operation history. In this way, the interface unit can select the optimal display method by referring to the patient's past operation history.

[0120] The interface unit can select the optimal display method when displaying the interface, taking into account the patient's device information. For example, the interface unit considers the patient's device information using a generation AI. For example, if the patient is using a smartphone, the interface unit provides a display method that matches the screen size. The interface unit can also provide a display method optimized for larger screens if the patient is using a tablet. Furthermore, if the patient is using a smartwatch, the interface unit can provide a concise and highly visible display method. In this way, the interface unit can select the optimal display method by taking into account the patient's device information.

[0121] The interface unit can estimate the patient's emotions and adjust the interface's operating procedures based on the estimated emotions. For example, the interface unit estimates the patient's emotions using generative AI. For example, if the patient is tense, the interface unit simplifies the operating procedures to reduce stress. If the patient is enjoying themselves, the interface unit can also make the operating procedures more detailed to provide a more enjoyable experience. Furthermore, if the patient is tired, the interface unit can minimize the operating procedures to reduce the burden of operation. Thus, the interface unit can adjust the interface's operating procedures based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0122] The interface unit can refer to the patient's calendar information and make suggestions based on their schedule when displaying the interface. For example, the interface unit uses a generation AI to refer to the patient's calendar information. For example, the interface unit can refer to the appointments registered in the patient's calendar and adjust the content displayed on the interface. Furthermore, the interface unit can display information related to specific events from the patient's calendar information. In addition, the interface unit can suggest the optimal operating procedure based on the patient's schedule, using the patient's calendar information. Thus, the interface unit can make suggestions based on the patient's schedule by referring to their calendar information.

[0123] The interface unit can refer to the patient's social media activity and display relevant information when the interface is displayed. For example, the interface unit uses generative AI to refer to the patient's social media activity. For example, the interface unit extracts relevant information from the patient's social media posts and displays it on the interface. Furthermore, the interface unit can display information of high interest from the patient's social media activity. In addition, the interface unit can detect changes in lifestyle from the patient's social media activity and display relevant information. Thus, the interface unit can display relevant information by referring to the patient's social media activity.

[0124] The monitoring unit can estimate the patient's emotions and adjust the monitoring frequency based on the estimated emotions. For example, the monitoring unit uses generative AI to estimate the patient's emotions. If the patient is feeling anxious, for example, the generative AI will monitor frequently to provide reassurance. The monitoring unit can also monitor at a moderate frequency if the patient is relaxed. Furthermore, if the patient is in a hurry, the generative AI can perform only the minimum necessary monitoring. This allows the monitoring unit to adjust the monitoring frequency based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0125] The monitoring unit can improve the accuracy of monitoring by referring to the patient's past medical history during monitoring. For example, the monitoring unit can refer to the patient's past medical history using generative AI. For example, the monitoring unit can include similar symptoms in the monitoring based on the patient's past medical history. The monitoring unit can also reflect the risk of specific diseases in the monitoring based on the patient's past medical history. Furthermore, the monitoring unit can reflect the effectiveness of treatment in the monitoring based on the patient's past medical history. In this way, the monitoring unit can improve the accuracy of monitoring by referring to the patient's past medical history.

[0126] The monitoring unit can acquire and incorporate patient lifestyle data during monitoring. For example, the monitoring unit can acquire patient lifestyle data using generative AI. For example, the monitoring unit can acquire data on the patient's diet and exercise and incorporate the impact of lifestyle on symptoms into monitoring. The monitoring unit can also acquire patient sleep data and incorporate the impact of sleep deprivation on symptoms into monitoring. Furthermore, the monitoring unit can acquire the patient's stress level and incorporate the impact of stress on symptoms into monitoring. In this way, the monitoring unit can incorporate patient lifestyle data and incorporate it into monitoring.

[0127] The monitoring unit can estimate a patient's emotions and determine monitoring priorities based on the estimated emotions. For example, the monitoring unit uses generative AI to estimate the patient's emotions. For instance, if a patient is experiencing strong anxiety, the generative AI will prioritize monitoring that patient. The monitoring unit can also prioritize monitoring other patients if the patient is relaxed. Furthermore, if a patient is in a hurry, the generative AI can perform a rapid monitoring and provide results preferentially. This allows the monitoring unit to determine monitoring priorities based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0128] The monitoring unit can adjust its monitoring content by considering the patient's geographical location information during monitoring. For example, the monitoring unit can use generative AI to consider the patient's geographical location information. For example, the monitoring unit can consider the infectious disease risk of the patient's residential area and reflect it in the monitoring. The monitoring unit can also consider the environmental pollution risk of the patient's residential area and reflect it in the monitoring. Furthermore, the monitoring unit can consider the climatic conditions of the patient's residential area and reflect them in the monitoring. In this way, the monitoring unit can adjust its monitoring content by considering the patient's geographical location information.

[0129] The monitoring unit can analyze the patient's social media activity during monitoring to supplement the monitoring data. For example, the monitoring unit can use generative AI to analyze the patient's social media activity. For example, the monitoring unit can extract relevant information from the patient's social media posts. The monitoring unit can also estimate the stress level from the patient's social media activity and reflect it in the monitoring. Furthermore, the monitoring unit can detect changes in lifestyle habits from the patient's social media activity and reflect them in the monitoring. In this way, the monitoring unit can supplement the monitoring data by analyzing the patient's social media activity.

[0130] The follow-up consultation promotion unit can estimate the patient's emotions and adjust the timing of follow-up consultations based on the estimated emotions. For example, the follow-up consultation promotion unit uses generative AI to estimate the patient's emotions. For example, if the patient is feeling anxious, the generative AI can prompt a follow-up consultation earlier. Furthermore, if the patient is relaxed, the generative AI can prompt a follow-up consultation at an appropriate time. Additionally, if the patient is in a hurry, the generative AI can prompt a follow-up consultation quickly. This allows the follow-up consultation promotion unit to adjust the timing of follow-up consultations based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0131] The follow-up consultation promotion unit can select the optimal follow-up consultation method by referring to the patient's past medical history when promoting a follow-up consultation. For example, the follow-up consultation promotion unit can refer to the patient's past medical history using generative AI. For example, the follow-up consultation promotion unit can encourage a follow-up consultation for similar symptoms based on the patient's past medical history. The follow-up consultation promotion unit can also encourage a follow-up consultation for a specific disease based on the patient's past medical history. Furthermore, the follow-up consultation promotion unit can also refer to the patient's past medical history and encourage a follow-up consultation based on the effectiveness of the treatment. In this way, the follow-up consultation promotion unit can select the optimal follow-up consultation method by referring to the patient's past medical history.

[0132] The follow-up consultation promotion unit can customize the content of follow-up consultations by considering the patient's lifestyle data when promoting them. For example, the follow-up consultation promotion unit considers the patient's lifestyle data using generative AI. For example, the follow-up consultation promotion unit considers the patient's diet and exercise data to encourage appropriate follow-up consultations. Furthermore, the follow-up consultation promotion unit can also consider the patient's sleep data to encourage appropriate follow-up consultations. In addition, the follow-up consultation promotion unit can consider the patient's stress level to encourage appropriate follow-up consultations. As a result, the follow-up consultation promotion unit can customize the content of follow-up consultations by considering the patient's lifestyle data.

[0133] The follow-up consultation promotion unit can estimate a patient's emotions and determine the priority of follow-up consultations based on the estimated emotions. For example, the unit uses generative AI to estimate a patient's emotions. For instance, if a patient is experiencing strong anxiety, the generative AI will prioritize that follow-up consultation. Similarly, if a patient is relaxed, the generative AI can prioritize other patients' follow-up consultations. Furthermore, if a patient is in a hurry, the generative AI can quickly prompt a follow-up consultation and provide results preferentially. This allows the follow-up consultation promotion unit to determine the priority of follow-up consultations based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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.

[0134] The follow-up consultation promotion unit can select the optimal follow-up consultation method by considering the patient's geographical location information when promoting a follow-up consultation. For example, the follow-up consultation promotion unit considers the patient's geographical location information using generative AI. For example, the follow-up consultation promotion unit can encourage a follow-up consultation by considering the infectious disease risk in the patient's residential area. Furthermore, the follow-up consultation promotion unit can encourage a follow-up consultation by considering the environmental pollution risk in the patient's residential area. In addition, the follow-up consultation promotion unit can encourage a follow-up consultation by considering the climatic conditions in the patient's residential area. As a result, the follow-up consultation promotion unit can select the optimal follow-up consultation method by considering the patient's geographical location information.

[0135] The Follow-Up Promotion Unit can analyze a patient's social media activity and supplement the content of the follow-up visit when promoting a follow-up visit. For example, the Follow-Up Promotion Unit can analyze a patient's social media activity using generative AI. For example, the Follow-Up Promotion Unit can extract relevant information from a patient's social media posts. The Follow-Up Promotion Unit can also estimate a patient's stress level from their social media activity and encourage a follow-up visit. Furthermore, the Follow-Up Promotion Unit can detect changes in lifestyle from a patient's social media activity and encourage a follow-up visit. In this way, the Follow-Up Promotion Unit can supplement the content of the follow-up visit by analyzing a patient's social media activity.

[0136] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0137] The analysis unit can estimate the patient's emotions and adjust the accuracy of the symptom analysis based on those emotions. For example, if the patient is feeling anxious, the generating AI can perform a detailed symptom analysis and provide information to reassure them. If the patient is relaxed, the generating AI can perform a concise symptom analysis and provide only the essential information. Furthermore, if the patient is in a hurry, the generating AI can perform a rapid symptom analysis and provide results in a short time. In this way, the analysis unit can adjust the accuracy of the symptom analysis based on the patient's emotions.

[0138] The suggestion unit can estimate the patient's emotions and adjust the way suggestions are presented based on those emotions. For example, if the patient is feeling anxious, the generating AI will offer suggestions in gentle language. If the patient is relaxed, the generating AI can offer suggestions that include more detailed information. Furthermore, if the patient is in a hurry, the generating AI can offer concise and quick suggestions. In this way, the suggestion unit can adjust the way suggestions are presented based on the patient's emotions.

[0139] The summarization unit can estimate the patient's emotions and adjust the way the summary is expressed based on those emotions. For example, if the patient is feeling anxious, the generating AI will create a summary using gentle language. If the patient is relaxed, the generating AI can create a summary that includes more detailed information. Furthermore, if the patient is in a hurry, the generating AI can create a concise and quick summary. In this way, the summarization unit can adjust the way the summary is expressed based on the patient's emotions.

[0140] The information delivery unit can estimate the patient's emotions and adjust the timing of information delivery based on those emotions. For example, if the patient is feeling anxious, the generating AI can provide information quickly. If the patient is relaxed, the generating AI can provide information at an appropriate time. Furthermore, if the patient is in a hurry, the generating AI can provide information immediately. In this way, the information delivery unit can adjust the timing of information delivery based on the patient's emotions.

[0141] The follow-up unit can estimate the patient's emotions and adjust the follow-up method based on those estimates. For example, if the patient is feeling anxious, the generating AI can provide a detailed follow-up. If the patient is relaxed, the generating AI can provide a concise follow-up. Furthermore, if the patient is in a hurry, the generating AI can provide a rapid follow-up. In this way, the follow-up unit can adjust the follow-up method based on the patient's emotions.

[0142] The analysis unit can improve the accuracy of symptom analysis by analyzing the patient's past medical history. For example, it can refer to the patient's past medical history to check if similar symptoms have recurred. It can also assess the risk of specific diseases from the patient's past medical history and reflect this in the symptom analysis. Furthermore, it can evaluate the effectiveness of treatment based on the patient's past medical history and improve the accuracy of symptom analysis. In this way, the analysis unit can improve the accuracy of symptom analysis by analyzing the patient's past medical history.

[0143] The proposal unit can suggest the most suitable medical department or healthcare facility by referring to the patient's past medical history. For example, it can suggest the same medical department based on the patient's past medical history. It can also suggest a specific healthcare facility based on the patient's past medical history. Furthermore, it can suggest a medical department with a high treatment effectiveness by referring to the patient's past medical history. In this way, the proposal unit can suggest the most suitable medical department or healthcare facility by referring to the patient's past medical history.

[0144] The summarization section can improve the accuracy of the summary by referring to the patient's past medical history. For example, it can include similar symptoms in the summary based on the patient's past medical history. It can also reflect the risk of specific diseases in the summary based on the patient's past medical history. Furthermore, it can reflect the effectiveness of treatment in the summary based on the patient's past medical history. In this way, the summarization section can improve the accuracy of the summary by referring to the patient's past medical history.

[0145] The information provider can optimize the content provided by referring to the patient's past medical history. For example, it can provide relevant information based on the patient's past medical history. It can also provide information about specific diseases based on the patient's past medical history. Furthermore, it can provide information about the effectiveness of treatment by referring to the patient's past medical history. In this way, the information provider can optimize the content provided by referring to the patient's past medical history.

[0146] The follow-up unit can select the optimal follow-up method by referring to the patient's past medical history during follow-up. For example, it can perform follow-up for similar symptoms based on the patient's past medical history. It can also perform follow-up for specific diseases based on the patient's past medical history. Furthermore, it can perform follow-up based on the effectiveness of treatment by referring to the patient's past medical history. In this way, the follow-up unit can select the optimal follow-up method by referring to the patient's past medical history.

[0147] The following briefly describes the processing flow for example form 2.

[0148] Step 1: The analysis unit analyzes the patient's symptoms. For example, it uses generative AI to analyze the patient's symptoms. Step 2: The proposal unit proposes the most suitable medical departments and medical institutions based on the information analyzed by the analysis unit. For example, it may use generative AI to propose the most suitable medical departments and medical institutions. Step 3: The summarization section summarizes the patient's complaint. For example, a generative AI is used to summarize the patient's complaint. Step 4: The providing unit provides the information summarized by the summarizing unit to the medical institution. For example, the information summarized using a generation AI is provided to the medical institution. Step 5: The follow-up department performs follow-up after the medical examination. For example, they use generative AI to perform post-examination follow-up.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the analysis unit, proposal unit, summary unit, provision unit, follow-up unit, interface unit, monitoring unit, and re-examination promotion unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The summary unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The provision unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The follow-up unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The interface unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The monitoring unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The re-examination promotion unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0153] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the analysis unit, proposal unit, summary unit, provision unit, follow-up unit, interface unit, monitoring unit, and re-examination promotion unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The summary unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The follow-up unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The interface unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The monitoring unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The re-examination promotion unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0169] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] Each of the multiple elements described above, including the analysis unit, proposal unit, summary unit, provision unit, follow-up unit, interface unit, monitoring unit, and re-examination promotion unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The summary unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The provision unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The follow-up unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The interface unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The monitoring unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The re-examination promotion unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0185] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.).

[0198] 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.

[0199] 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.

[0200] 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.

[0201] Each of the multiple elements described above, including the analysis unit, proposal unit, summary unit, provision unit, follow-up unit, interface unit, monitoring unit, and re-examination promotion unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The summary unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The provision unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The follow-up unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The interface unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The monitoring unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The re-examination promotion unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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."

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] (Note 1) An analysis unit that analyzes the patient's symptoms, Based on the information analyzed by the aforementioned analysis unit, the proposal unit proposes the most suitable medical department or medical institution. A summary section that summarizes the patient's complaints, A provisioning unit that provides information summarized by the aforementioned summarizing unit to medical institutions, It includes a follow-up department that provides follow-up care after medical treatment. A system characterized by the following features. (Note 2) It features an interface for asking additional questions or confirming details via chat or voice. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a monitoring unit to monitor changes in the patient's symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 4) Equipped with a follow-up consultation promotion department to encourage follow-up visits as needed. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, The system estimates the patient's emotions and adjusts the accuracy of symptom analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Analyzing patients' past medical history improves the accuracy of symptom analysis. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, We incorporate patients' lifestyle data and use it to analyze their symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, The system estimates the patient's emotions and prioritizes symptom analysis based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, By considering the patient's geographical location, region-specific disease risks are reflected in the symptom analysis. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, Analyze patients' social media activity to supplement information related to symptom analysis. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned proposal section is, The system estimates the patient's emotions and adjusts the way the proposal is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned proposal section is, When making a proposal, we will refer to the patient's past medical history to suggest the most suitable medical department and healthcare facility. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned proposal section is, When making a proposal, we will suggest medical departments and healthcare facilities while taking into account the patient's lifestyle data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned proposal section is, The system estimates the patient's emotions and prioritizes proposals based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned proposal section is, When making a proposal, we will consider the patient's geographical location to suggest the most suitable medical institution. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, When making a proposal, we analyze the patient's social media activity and suggest relevant healthcare institutions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The summary section above is, The system estimates the patient's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The summary section above is, When summarizing, refer to the patient's past medical history to improve the accuracy of the summary. The system described in Appendix 1, characterized by the features described herein. (Note 19) The summary section above is, When summarizing, incorporate patient lifestyle data and reflect it in the summary. The system described in Appendix 1, characterized by the features described herein. (Note 20) The summary section above is, The system estimates the patient's emotions and prioritizes summaries based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The summary section above is, When summarizing, adjust the content of the summary to take into account the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 22) The summary section above is, During the summarization process, analyze the patient's social media activity to supplement the information relevant to the summary. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, The system estimates the patient's emotions and adjusts the timing of information delivery based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing information, we optimize the content by referring to the patient's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing information, customize the content to take into account the patient's lifestyle data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, The system estimates the patient's emotions and prioritizes information provision based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing information, we adjust the content of the information provided, taking into account the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When providing information, analyze the patient's social media activity to supplement the information provided. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned follow-up unit is, Estimate the patient's emotions and adjust the follow-up method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned follow-up unit is, During follow-up, the optimal follow-up method is selected by referring to the patient's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned follow-up unit is, During follow-up, the follow-up content will be customized to take into account the patient's lifestyle data. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned follow-up unit is, The system estimates the patient's emotions and determines follow-up priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned follow-up unit is, During follow-up, the optimal follow-up method will be selected considering the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned follow-up unit is, During follow-up, analyze the patient's social media activity to supplement the follow-up content. The system described in Appendix 1, characterized by the features described herein. (Note 35) The interface unit is The system estimates the patient's emotions and adjusts the interface display based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The interface unit is When displaying the interface, the system selects the optimal display method by referring to the patient's past operation history. The system described in Appendix 2, characterized by the features described herein. (Note 37) The interface unit is When displaying the interface, the optimal display method is selected considering the patient's device information. The system described in Appendix 2, characterized by the features described herein. (Note 38) The interface unit is The system estimates the patient's emotions and adjusts the interface's operation procedures based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 39) The interface unit is When displaying the interface, the system references the patient's calendar information to provide schedule-based suggestions. The system described in Appendix 2, characterized by the features described herein. (Note 40) The interface unit is When the interface is displayed, it refers to the patient's social media activity and displays relevant information. The system described in Appendix 2, characterized by the features described herein. (Note 41) The monitoring unit, Estimate the patient's emotion and adjust the monitoring frequency based on the estimated patient emotion The system according to Appendix 3, characterized by the above (Appendix 42) The monitoring unit When monitoring, refer to the patient's past medical history to improve the accuracy of monitoring The system according to Appendix 3, characterized by the above (Appendix 43) The monitoring unit When monitoring, capture the patient's lifestyle data and reflect it in the monitoring The system according to Appendix 3, characterized by the above (Appendix 44) The monitoring unit Estimate the patient's emotion and determine the monitoring priority based on the estimated patient emotion The system according to Appendix 3, characterized by the above (Appendix 45) The monitoring unit When monitoring, consider the patient's geographical location information and adjust the monitoring content The system according to Appendix 3, characterized by the above (Appendix 46) The monitoring unit When monitoring, analyze the patient's social media activities and complement the monitoring content The system according to Appendix 3, characterized by the above (Appendix 47) The re - visit promotion unit Estimate the patient's emotion and adjust the timing of the re - visit based on the estimated patient emotion The system according to Appendix 4, characterized by the above (Appendix 48) The re - visit promotion unit When promoting the re - visit, refer to the patient's past medical history to select the optimal re - visit method The system according to Appendix 4, characterized by the above (Appendix 49) The aforementioned re-examination promotion unit, When encouraging follow-up visits, customize the content of the follow-up visit by taking into account the patient's lifestyle data. The system described in Appendix 4, characterized by the features described herein. (Note 50) The aforementioned re-examination promotion unit, The system estimates the patient's emotions and determines the priority of follow-up visits based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 51) The aforementioned re-examination promotion unit, When encouraging follow-up visits, the optimal method for these visits should be selected considering the patient's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 52) The aforementioned re-examination promotion unit, When encouraging follow-up visits, analyze the patient's social media activity to supplement the content of the follow-up visit. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0221] 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. An analysis unit that analyzes the patient's symptoms, Based on the information analyzed by the aforementioned analysis unit, the proposal unit proposes the most suitable medical department or medical institution. A summary section that summarizes the patient's complaints, A provisioning unit that provides information summarized by the aforementioned summarizing unit to medical institutions, It includes a follow-up department that provides follow-up care after medical treatment. A system characterized by the following features.

2. It features an interface for asking additional questions or confirming details via chat or voice. The system according to feature 1.

3. It includes a monitoring unit to monitor changes in the patient's symptoms. The system according to feature 1.

4. Equipped with a follow-up consultation promotion department to encourage follow-up visits as needed. The system according to feature 1.

5. The aforementioned analysis unit, The system estimates the patient's emotions and adjusts the accuracy of symptom analysis based on the estimated emotions. The system according to feature 1.

6. The aforementioned analysis unit, Analyzing patients' past medical history improves the accuracy of symptom analysis. The system according to feature 1.

7. The aforementioned analysis unit, We incorporate patients' lifestyle data and use it to analyze their symptoms. The system according to feature 1.

8. The aforementioned analysis unit, The system estimates the patient's emotions and prioritizes symptom analysis based on these estimated emotions. The system according to feature 1.

Images