System

Abstract

An object of a system according to an embodiment is to support determination for a user to easily receive a second opinion.SOLUTION: A system includes a symptom input part, a medical examination result input part, a disease name listing part, a serious illness determination part, and a guide part. The symptom input unit inputs symptoms of a disease or an injury from the user. The medical examination result input unit inputs a result of a medical examination at a medical institution where the patient first visited. The disease name listing unit analyzes the information input by the symptom input unit and the medical examination result input unit, and lists disease names. The serious illness determination section determines a serious illness from the disease names listed by the disease name listing section. The guidance unit guides the user to receive a second opinion when the serious illness determination unit determines that there is a serious illness.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem that it is difficult for users to decide whether to get a second opinion, and it takes time and effort.

[0005] The system according to the embodiment aims to assist a user in easily making a decision to obtain a second opinion. [Means for solving the problem]

[0006] The system according to the embodiment includes a symptom input unit, a medical examination result input unit, a disease name listing unit, a serious illness determination unit, and a guidance unit. The symptom input unit inputs symptoms of illness or injury from the user. The medical examination result input unit inputs the results of the medical examination at the first medical institution visited. The disease name listing unit analyzes the information entered by the symptom input unit and the medical examination result input unit and lists disease names. The serious illness determination unit determines a serious illness from the disease names listed by the disease name listing unit. The guidance unit provides guidance to the user to obtain a second opinion if the serious illness determination unit determines that the user has a serious illness. [Effects of the Invention]

[0007] The system according to the embodiment can easily assist the user in making a decision to receive a second opinion. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The AI ​​app according to the embodiment of the present invention is a system in which a user inputs symptoms of illness or injury and medical examination results, and the AI ​​analyzes the results to list possible illnesses, and if there is a possibility of a serious illness, the system provides guidance on obtaining a second opinion. This allows the AI ​​app to easily obtain a second opinion, saving time and effort.

[0029] The AI ​​app according to the embodiment includes a symptom input unit, a medical examination result input unit, a disease name listing unit, a serious illness determination unit, and a second opinion guidance unit. The symptom input unit receives input of symptoms of illness or injury from a user. For example, the user can input "persistent headache." The symptom input unit can also receive input of "cough." The symptom input unit can also receive input of "stomach pain." The medical examination result input unit receives input of the results of the medical examination at the first medical institution. For example, the user can input "diagnosed with migraine." The medical examination result input unit can also receive input of "diagnosed with cold." The medical examination result input unit can also receive input of "diagnosed with gastritis." The disease name listing unit analyzes the information input by the symptom input unit and the medical examination result input unit, and the generation AI lists possible diseases. For example, the generation AI lists "migraine, tension headache, and possible brain tumor" based on the input information. The generation AI can also list the possible illnesses, such as "Cold, influenza, and pneumonia." The generation AI can also list the possible illnesses, such as "Gastritis, stomach ulcer, and stomach cancer." The serious illness determination unit determines the possibility of a serious illness from the illnesses listed by the disease name enumeration unit. For example, the generation AI can determine, "It may be a brain tumor, so we recommend getting a second opinion." The generation AI can also determine, "It may be pneumonia, so we recommend getting a second opinion." The generation AI can also determine, "It may be stomach cancer, so we recommend getting a second opinion." The second opinion guidance unit guides the user to get a second opinion if the serious illness determination unit determines that there is a possibility of a serious illness. For example, the second opinion guidance unit can provide information about nearby specialists and medical institutions and support the appointment process. The second opinion guidance unit can also provide assistance with preparing the information and documents necessary to get a second opinion. The second opinion guidance section can also provide guidance such as "We will guide you through the specific steps to get a second opinion."As a result, the AI ​​app according to the embodiment allows users to easily get a second opinion, saving time and effort.

[0030] The symptom input unit can automatically generate questions for symptoms entered by the user and collect detailed information. For example, if the user enters "I have a persistent headache," the generation AI automatically generates additional questions such as "How frequent and severe is the headache?" to collect detailed information. If the user enters "I have a cough," the symptom input unit generates specific questions such as "How long has the cough lasted, do you have phlegm, and what is its color?" to grasp the details of the symptoms. If the user enters "I have abdominal pain," the generation AI generates questions such as "What is the location and duration of the pain? Is it related to food?" to collect more accurate information. This allows detailed information to be collected for the symptoms entered by the user.

[0031] The symptom input unit can analyze the user's voice input and convert it into text using natural language processing. For example, if the user inputs "I've had a bad headache recently," the generation AI converts the voice into text and records it as "I've had a bad headache recently." If the user inputs "I can't stop coughing," the generation AI analyzes the voice, converts it into text as "I can't stop coughing," and saves it. If the user inputs "I have a stomachache," the generation AI converts the voice into text and records it as "I have a stomachache." This allows the user's voice input to be converted into text.

[0032] The symptom input section can input symptoms or examination results using images or videos. For example, the user can upload an image of a skin rash, and the generative AI analyzes the image to identify the type of rash. Also, the symptom input section allows the user to record and upload the sound of coughing, and the generative AI analyzes the sound to identify the type of cough. Additionally, the user can upload a video indicating the location of abdominal pain, and the generative AI analyzes the video to identify the pain location. This enables the input of symptoms and examination results using images and videos.

[0033] The symptom input section supports input in different languages and can accommodate international users. For example, when the user inputs "I have a headache" in English, the generative AI analyzes the information and makes an appropriate diagnosis. Also, when the user inputs "Tengo tos" in Spanish, the generative AI analyzes the information and makes an appropriate diagnosis. Additionally, when the user inputs "我肚子疼" in Chinese, the generative AI analyzes the information and makes an appropriate diagnosis. This supports input in different languages and can handle international users.

[0034] The disease listing section can refer to past diagnostic data or medical literature to propose more accurate disease names. For example, the generative AI refers to past diagnostic data and proposes the disease name that best matches the user's symptoms. For instance, based on past migraine diagnostic data, it proposes the possibility of migraine. Also, the disease listing section allows the generative AI to refer to medical literature and propose disease names based on the latest research results. For example, it proposes disease names discovered in the latest research. Additionally, the disease listing section enables the generative AI to analyze by combining past diagnostic data and medical literature to propose more accurate disease names. For example, it proposes disease names based on past data and the latest research results. This allows for referring to past diagnostic data and medical literature to propose more accurate disease names.

[0035] The disease name enumeration unit can also present the probability of occurrence or risk factors for each disease name when listing the disease names. For example, when the generation AI lists the disease names, the disease name enumeration unit presents the probability of occurrence for each disease name. For example, it may present the probability of occurrence of migraine headaches as "70%, and the probability of occurrence of tension headaches as "20%." In addition, when the generation AI lists the disease names, the disease name enumeration unit presents the risk factors for each disease name. For example, it may present the risk factors as "risk factors for brain tumors include family history and age." In addition, when the generation AI lists the disease names, the disease name enumeration unit presents the probability of occurrence and risk factors together. For example, it may present the risk factors as "the probability of occurrence of migraine headaches is 70%, and risk factors include stress and lack of sleep." In this way, the probability of occurrence and risk factors for each disease name can also be presented.

[0036] The disease name enumeration unit can also present related treatments or preventive measures when enumerating disease names. For example, when the generation AI enumerates disease names, the disease name enumeration unit presents related treatments. For example, it may present such treatments in the form of, "It may be a migraine. Treatments include drug therapy and lifestyle improvements." In addition, when the generation AI enumerates disease names, the disease name enumeration unit presents related preventive measures. For example, it may present such treatments in the form of, "It may be a tension headache. Preventive measures include stress management and relaxation." In addition, when the generation AI enumerates disease names, the disease name enumeration unit presents such treatments and preventive measures together. For example, it may present such treatments in the form of, "It may be a brain tumor. Treatments include surgery and radiation therapy. Preventive measures include regular health checkups." This allows related treatments and preventive measures to be presented together.

[0037] The disease name enumeration unit can customize the results of the disease name enumeration by comparing them with the user's lifestyle habits or environmental factors. For example, when the generation AI enumerates disease names, the disease name enumeration unit customizes the results by taking into account the user's lifestyle habits. For example, it may present a message such as, "You may have a migraine, but you need to improve your lifestyle habits." In addition, when the generation AI enumerates disease names, the disease name enumeration unit customizes the results by taking into account the user's environmental factors. For example, it may present a message such as, "You may have a tension headache, but workplace stress may be the cause." In addition, when the generation AI enumerates disease names, the disease name enumeration unit customizes the results by taking into account both lifestyle habits and environmental factors. For example, it may present a message such as, "You may have a brain tumor, but it is important to review your lifestyle habits and environmental factors." In this way, the results of the disease name enumeration can be customized by comparing them with the user's lifestyle habits and environmental factors.

[0038] The serious illness determination unit can determine the possibility of a serious illness by taking into account the user's past health data or family history. For example, the generation AI refers to the user's past health data to determine the possibility of a serious illness. For example, it evaluates the possibility of a brain tumor based on past diagnostic results and treatment history. The serious illness determination unit also determines the risk of a serious illness by taking into account the user's family history. For example, if there is a family history of brain tumors, the risk is evaluated as high. The serious illness determination unit also analyzes the generation AI's past health data and family history to comprehensively determine the possibility of a serious illness. For example, it evaluates the risk of a brain tumor based on past diagnostic results and family history. This allows the possibility of a serious illness to be determined by taking into account the user's past health data and family history.

[0039] The serious illness determination unit can suggest specific next steps to the user based on the determination results. For example, if the generating AI determines the possibility of a serious illness, the serious illness determination unit will suggest additional tests to the user. For example, it may suggest, "There is a possibility of a brain tumor, so we recommend that you undergo an MRI scan." If the generating AI determines the possibility of a serious illness, the serious illness determination unit will suggest that the user consult a specialist. For example, it may suggest, "There is a possibility of a brain tumor, so please consult a neurosurgeon." If the generating AI determines the possibility of a serious illness, the serious illness determination unit will suggest specific next steps to the user and guide them to an appropriate medical institution. For example, it may suggest, "There is a possibility of a brain tumor, so please consult a specialist nearby and undergo additional tests." This allows the system to suggest specific next steps to the user based on the determination results.

[0040] The serious illness determination unit can personalize the determination result based on the user's health condition or lifestyle habits. For example, the generation AI in the serious illness determination unit personalizes the determination result based on the user's health condition. For example, it may present a message such as, "You may have a brain tumor, but we recommend that you undergo additional testing in consideration of your health condition." The generation AI in the serious illness determination unit also personalizes the determination result based on the user's lifestyle habits. For example, it may present a message such as, "You may have a tension headache, but you need to improve your lifestyle habits." The generation AI in the serious illness determination unit also personalizes the determination result based on the user's health condition and lifestyle habits. For example, it may present a message such as, "You may have a brain tumor, but it is important that you review your health condition and lifestyle habits." This allows the determination result to be personalized based on the user's health condition and lifestyle habits.

[0041] The serious illness determination unit can share the determination results with family or medical professionals with the user's consent, thereby strengthening the support system. For example, the generation AI can present the determination results with family members with the user's consent, thereby strengthening the support system. For example, it can present the results in the form of, "There is a possibility that you have a brain tumor. Please consult with your family and see a specialist." The serious illness determination unit can also share the determination results with medical professionals with the user's consent, thereby strengthening the support system. For example, it can present the results in the form of, "There is a possibility that you have a tension headache. Please consult with your family doctor and decide on a treatment plan." The serious illness determination unit can also share the determination results with family members and medical professionals with the user's consent, thereby building a comprehensive support system. For example, it can present the results in the form of, "There is a possibility that you have a brain tumor. Please work with your family members and medical professionals to receive appropriate treatment." This allows the determination results to be shared with family members and medical professionals with the user's consent, thereby strengthening the support system.

[0042] The second opinion guidance unit can automatically search for the nearest specialist or medical institution based on the user's location information and support the appointment process. For example, the generation AI in the second opinion guidance unit searches for the nearest specialist based on the user's location information and supports the appointment process. For example, it may provide guidance such as, "You may have a brain tumor, so make an appointment with a nearby neurosurgeon." The second opinion guidance unit can also search for the nearest medical institution based on the user's location information and support the appointment process. For example, it may provide guidance such as, "You may have a tension headache, so make an appointment with a nearby internist." The second opinion guidance unit can also search for the nearest specialist or medical institution based on the user's location information and support the appointment process. For example, it may provide guidance such as, "You may have a brain tumor, so make an appointment with a nearby specialist and undergo additional tests." This allows the generation AI to automatically search for the nearest specialist or medical institution based on the user's location information and support the appointment process.

[0043] The second opinion guidance unit can automatically generate documents or information required for receiving a second opinion and provide them to the user. In the second opinion guidance unit, for example, the generation AI automatically generates documents required for receiving a second opinion and provides them to the user. For example, the information is provided in the form of, "There is a possibility that you have a brain tumor, so we will automatically generate a referral letter for you to see a specialist." In addition, the second opinion guidance unit automatically generates information required for receiving a second opinion and provides it to the user. For example, the information is provided in the form of, "There is a possibility that you have a tension headache, so we will automatically generate the examination results for you to see a specialist." In addition, the second opinion guidance unit automatically generates documents and information required for receiving a second opinion and provides them to the user. For example, the information is provided in the form of, "There is a possibility that you have a brain tumor, so we will automatically generate and provide the documents required for you to see a specialist." In this way, the documents and information required for receiving a second opinion can be automatically generated and provided to the user.

[0044] The second opinion information unit can link the second opinion consultation guide with the user's health insurance information and present a cost estimate or insurance coverage. In the second opinion information unit, for example, the generation AI presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion in the form of, "There is a possibility that you have a brain tumor, so the cost of a consultation with a specialist will be covered by insurance and will be XXX yen." In addition, the second opinion information unit presents the insurance coverage based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information.

[0045] The second opinion guidance unit supports follow-up after receiving a second opinion, and can continuously support the user's health management. For example, the second opinion guidance unit supports follow-up after receiving a second opinion by the generating AI, and continuously supports the user's health management. For example, the second opinion guidance unit provides support in the form of, "We will support you in planning your treatment after you have been diagnosed with a brain tumor." The second opinion guidance unit also supports follow-up after receiving a second opinion by the generating AI, and continuously supports the user's health management. For example, the second opinion guidance unit provides support in the form of, "We will support you in managing your stress after you have been diagnosed with a tension headache." The second opinion guidance unit also supports follow-up after receiving a second opinion by the generating AI, and continuously supports the user's health management. For example, the second opinion guidance unit provides support in the form of, "We will support you in regular health checks after you have been diagnosed with a brain tumor." This allows follow-up after receiving a second opinion to be supported, and continuously supports the user's health management.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The symptom input unit collects information about the user's lifestyle and daily activities, enabling more accurate identification of the cause of symptoms. For example, if a user inputs "I have a persistent headache," the generation AI automatically generates additional questions such as "How is your sleep time and stress level these days?" to collect more detailed information. If a user inputs "I have a cough," the generation AI generates specific questions such as "What about your smoking habits and whether you have any allergies?" to understand the details of the symptoms. If a user inputs "I have a stomachache," the generation AI generates questions such as "How are your diet and exercise habits?" to collect more accurate information. This allows the system to collect information about the user's lifestyle and daily activities and more accurately identify the cause of symptoms.

[0048] The symptom input unit can refer to similar past cases and provide reference information for the symptoms entered by the user. For example, if the user enters "persistent headache," the generation AI will refer to similar past cases and provide reference information such as "migraines and tension headaches have been common in past cases." If the user enters "cough," the generation AI will refer to similar past cases and provide reference information such as "colds and influenza have been common in past cases." If the user enters "stomach pain," the generation AI will refer to similar past cases and provide reference information such as "gastritis and stomach ulcers have been common in past cases." This makes it possible to refer to similar past cases and provide reference information for the symptoms entered by the user.

[0049] The symptom input unit can track the progression of symptoms and check in periodically based on the user's input. For example, if the user inputs "I have a persistent headache," the generation AI will periodically send check-in messages such as "How is your headache?" to track the progression of the symptoms. If the user inputs "I have a cough," the generation AI will periodically send check-in messages such as "How is your cough?" to track the progression of the symptoms. If the user inputs "I have a stomachache," the generation AI will periodically send check-in messages such as "How is your stomachache?" to track the progression of the symptoms. This makes it possible to track the progression of symptoms and check in periodically based on the user's input.

[0050] The disease name enumeration unit can suggest more accurate disease names by taking into account personal information such as the user's age and gender. For example, the generation AI takes into account the user's age and prioritizes suggesting disease names that are common among younger people. The generation AI also takes into account the user's gender and prioritizes suggesting disease names that are common among women. The generation AI also analyzes the user's age and gender in combination to suggest more accurate disease names. This allows for more accurate disease names to be suggested by taking into account personal information such as the user's age and gender.

[0051] The disease name enumeration unit can evaluate the risk of developing a disease and suggest preventive measures by taking into account the user's lifestyle and environmental factors. For example, the generation AI can consider the user's lifestyle and suggest something like, "You may have a migraine, but you need to improve your lifestyle." The generation AI can also consider the user's environmental factors and suggest something like, "You may have a tension headache, but workplace stress may be the cause." The generation AI can also analyze the user's lifestyle and environmental factors in combination and suggest something like, "You may have a brain tumor, but it is important to review your lifestyle and environmental factors." This allows the generation AI to evaluate the risk of developing a disease and suggest preventive measures by taking into account the user's lifestyle and environmental factors.

[0052] The serious illness determination unit can assess the risk of serious illness and suggest preventive measures by taking into account the user's past health data and family history. For example, the generation AI can refer to the user's past health data and suggest something like, "You may have a brain tumor, but we recommend that you undergo additional testing based on your past diagnostic results." The generation AI can also consider the user's family history and suggest something like, "If you have a family history of brain tumors, we assess your risk highly." The generation AI can also combine and analyze the user's past health data and family history and suggest something like, "We will assess your risk of brain tumors and suggest preventive measures." This allows the system to assess the risk of serious illness and suggest preventive measures by taking into account the user's past health data and family history.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The symptom input unit inputs the symptoms of illness or injury from the user. For example, the user can input symptoms such as "persistent headache," "cough," or "stomachache." Step 2: The examination result input unit inputs the examination results from the first medical institution visited. For example, the user can input examination results such as "diagnosed with migraine," "diagnosed with cold," or "diagnosed with gastritis." Step 3: The disease name enumeration unit analyzes the information entered by the symptom input unit and the examination result input unit, and the generation AI lists possible disease names. For example, it lists disease names such as "Migraine, tension headache, possible brain tumor," "Possible cold, flu, pneumonia," and "Possible gastritis, stomach ulcer, stomach cancer." Step 4: In the serious illness determination section, the AI ​​determines the possibility of a serious illness from the list of illnesses enumerated by the illness enumeration section. For example, it may determine, "There is a possibility of a brain tumor, so we recommend getting a second opinion," "There is a possibility of pneumonia, so we recommend getting a second opinion," or "There is a possibility of stomach cancer, so we recommend getting a second opinion." Step 5: If the serious illness determination unit determines that the patient may have a serious illness, the second opinion guidance unit provides the user with guidance on how to obtain a second opinion. For example, the unit may provide information on nearby specialists and medical institutions and support the appointment process, or provide assistance in preparing the information and documents required for obtaining a second opinion, or provide guidance on the specific steps required for obtaining a second opinion.

[0055] (Example 2) The AI ​​app according to the embodiment of the present invention is a system in which a user inputs symptoms of illness or injury and medical examination results, and the AI ​​analyzes the results to list possible illnesses, and if there is a possibility of a serious illness, the system provides guidance on obtaining a second opinion. This allows the AI ​​app to easily obtain a second opinion, saving time and effort.

[0056] The AI ​​app according to the embodiment includes a symptom input unit, a medical examination result input unit, a disease name listing unit, a serious illness determination unit, and a second opinion guidance unit. The symptom input unit receives input of symptoms of illness or injury from a user. For example, the user can input "persistent headache." The symptom input unit can also receive input of "cough." The symptom input unit can also receive input of "stomach pain." The medical examination result input unit receives input of the results of the medical examination at the first medical institution. For example, the user can input "diagnosed with migraine." The medical examination result input unit can also receive input of "diagnosed with cold." The medical examination result input unit can also receive input of "diagnosed with gastritis." The disease name listing unit analyzes the information input by the symptom input unit and the medical examination result input unit, and the generation AI lists possible diseases. For example, the generation AI lists "migraine, tension headache, and possible brain tumor" based on the input information. The generation AI can also list the possible illnesses, such as "Cold, influenza, and pneumonia." The generation AI can also list the possible illnesses, such as "Gastritis, stomach ulcer, and stomach cancer." The serious illness determination unit determines the possibility of a serious illness from the illnesses listed by the disease name enumeration unit. For example, the generation AI can determine, "It may be a brain tumor, so we recommend getting a second opinion." The generation AI can also determine, "It may be pneumonia, so we recommend getting a second opinion." The generation AI can also determine, "It may be stomach cancer, so we recommend getting a second opinion." The second opinion guidance unit guides the user to get a second opinion if the serious illness determination unit determines that there is a possibility of a serious illness. For example, the second opinion guidance unit can provide information about nearby specialists and medical institutions and support the appointment process. The second opinion guidance unit can also provide assistance with preparing the information and documents necessary to get a second opinion. The second opinion guidance section can also provide guidance such as "We will guide you through the specific steps to get a second opinion."As a result, the AI ​​app according to the embodiment allows users to easily get a second opinion, saving time and effort.

[0057] The symptom input unit can automatically generate questions for symptoms entered by the user and collect detailed information. For example, if the user enters "I have a persistent headache," the generation AI automatically generates additional questions such as "How frequent and severe is the headache?" to collect detailed information. If the user enters "I have a cough," the symptom input unit generates specific questions such as "How long has the cough lasted, do you have phlegm, and what is its color?" to grasp the details of the symptoms. If the user enters "I have abdominal pain," the generation AI generates questions such as "What is the location and duration of the pain? Is it related to food?" to collect more accurate information. This allows detailed information to be collected for the symptoms entered by the user.

[0058] The symptom input unit can analyze the user's voice input and convert it into text using natural language processing. For example, if the user inputs "I've had a bad headache recently," the generation AI converts the voice into text and records it as "I've had a bad headache recently." If the user inputs "I can't stop coughing," the generation AI analyzes the voice, converts it into text as "I can't stop coughing," and saves it. If the user inputs "I have a stomachache," the generation AI converts the voice into text and records it as "I have a stomachache." This allows the user's voice input to be converted into text.

[0059] The symptom input section can analyze the emotions of the user when inputting using the emotion estimation function and provide advice to reduce stress and anxiety. For example, when the user inputs "I have a headache and I'm anxious", the generative AI analyzes the emotion and provides advice such as "Please try methods to relax". Also, when the user inputs "I can't stop coughing and I'm worried", the generative AI analyzes the emotion and provides advice such as "Please take a deep breath and relax". Moreover, when the user inputs "My stomach hurts and I'm scared", the generative AI analyzes the emotion and provides advice such as "Please consult a doctor if the pain persists". Thus, it can analyze the user's emotions and provide advice to reduce stress and anxiety.

[0060] The symptom input section can input symptoms or examination results using images or videos. For example, when the user uploads an image of a skin rash, the generative AI analyzes the image to identify the type of rash. Also, when the user records and uploads the sound of coughing, the generative AI analyzes the sound to identify the type of cough. Moreover, when the user uploads a video showing the location of abdominal pain, the generative AI analyzes the video to identify the location of the pain. Thus, it can input symptoms and examination results using images and videos.

[0061] The symptom input section supports input in different languages and can also accommodate international users. For example, when the user inputs "I have a headache" in English, the generative AI analyzes the information and makes an appropriate diagnosis. Also, when the user inputs "Tengo tos" in Spanish, the generative AI analyzes the information and makes an appropriate diagnosis. Moreover, when the user inputs "我肚子疼" in Chinese, the generative AI analyzes the information and makes an appropriate diagnosis. Thus, it supports input in different languages and can also accommodate international users.

[0062] The symptom input unit uses an emotion estimation function to monitor the user's emotions in real time as they input information and provide positive feedback. For example, if the user inputs, "I'm worried because I have a persistent headache," the generation AI monitors the user's emotions in real time and provides positive feedback such as, "It's okay, we'll make an appropriate diagnosis." If the user inputs, "I'm worried because my cough won't stop," the generation AI monitors the user's emotions in real time and provides positive feedback such as, "Don't worry, we'll suggest an appropriate treatment." If the user inputs, "I'm scared because my stomach hurts," the generation AI monitors the user's emotions in real time and provides positive feedback such as, "Don't worry, we'll provide appropriate advice." This improves learning effectiveness by monitoring the user's emotions in real time and providing positive feedback.

[0063] The disease name enumeration unit can suggest more accurate disease names by referring to past diagnostic data or medical literature. In the disease name enumeration unit, for example, the generation AI refers to past diagnostic data and suggests the disease name that most closely matches the user's symptoms. For example, it suggests the possibility of migraine based on past migraine diagnostic data. In addition, the disease name enumeration unit refers to medical literature and suggests disease names based on the latest research results. For example, it suggests disease names discovered in the latest research. In addition, the disease name enumeration unit analyzes past diagnostic data and medical literature in combination to suggest more accurate disease names. For example, it suggests disease names based on past data and the latest research results. This allows the generation AI to suggest more accurate disease names by referring to past diagnostic data and medical literature.

[0064] The disease name enumeration unit can also present the probability of occurrence or risk factors for each disease name when listing the disease names. For example, when the generation AI lists the disease names, the disease name enumeration unit presents the probability of occurrence for each disease name. For example, it may present the probability of occurrence of migraine headaches as "70%, and the probability of occurrence of tension headaches as "20%." In addition, when the generation AI lists the disease names, the disease name enumeration unit presents the risk factors for each disease name. For example, it may present the risk factors as "risk factors for brain tumors include family history and age." In addition, when the generation AI lists the disease names, the disease name enumeration unit presents the probability of occurrence and risk factors together. For example, it may present the risk factors as "the probability of occurrence of migraine headaches is 70%, and risk factors include stress and lack of sleep." In this way, the probability of occurrence and risk factors for each disease name can also be presented.

[0065] The disease name enumeration unit can use the emotion estimation function to present disease names in a manner that is easy for the user to accept and add explanations to reduce anxiety. For example, the generation AI can use the emotion estimation function to present disease names in a manner that is easy for the user to accept. For example, the disease name enumeration unit can present the disease name in a manner that is easy for the user to accept, such as, "It may be a migraine, but there are appropriate treatments available, so don't worry." The generation AI can also use the emotion estimation function to add explanations to reduce anxiety. For example, the disease name enumeration unit can present the disease name in a manner that is easy for the user to accept, such as, "It may be a tension headache, but stress management and relaxation are effective." The generation AI can also use the emotion estimation function to present disease names in a manner that is easy for the user to accept and provide advice to reduce anxiety. For example, the disease name enumeration unit can present the disease name in a manner that is easy for the user to accept, such as, "It may be a brain tumor, but treatment is possible with early detection, so please see a specialist." This allows the disease name to be presented in a manner that is easy for the user to accept and add explanations to reduce anxiety.

[0066] The disease name enumeration unit can also present related treatments or preventive measures when enumerating disease names. For example, when the generation AI enumerates disease names, the disease name enumeration unit presents related treatments. For example, it may present such treatments in the form of, "It may be a migraine. Treatments include drug therapy and lifestyle improvements." In addition, when the generation AI enumerates disease names, the disease name enumeration unit presents related preventive measures. For example, it may present such treatments in the form of, "It may be a tension headache. Preventive measures include stress management and relaxation." In addition, when the generation AI enumerates disease names, the disease name enumeration unit presents such treatments and preventive measures together. For example, it may present such treatments in the form of, "It may be a brain tumor. Treatments include surgery and radiation therapy. Preventive measures include regular health checkups." This allows related treatments and preventive measures to be presented together.

[0067] The disease name enumeration unit can customize the results of the disease name enumeration by comparing them with the user's lifestyle habits or environmental factors. For example, when the generation AI enumerates disease names, the disease name enumeration unit customizes the results by taking into account the user's lifestyle habits. For example, it may present a message such as, "You may have a migraine, but you need to improve your lifestyle habits." In addition, when the generation AI enumerates disease names, the disease name enumeration unit customizes the results by taking into account the user's environmental factors. For example, it may present a message such as, "You may have a tension headache, but workplace stress may be the cause." In addition, when the generation AI enumerates disease names, the disease name enumeration unit customizes the results by taking into account both lifestyle habits and environmental factors. For example, it may present a message such as, "You may have a brain tumor, but it is important to review your lifestyle habits and environmental factors." In this way, the results of the disease name enumeration can be customized by comparing them with the user's lifestyle habits and environmental factors.

[0068] The disease name enumeration unit can use the emotion estimation function to provide detailed information about the disease in which the user is most interested. For example, the generation AI can use the emotion estimation function to provide detailed information about the disease in which the user is most interested. For example, the disease name enumeration unit can present detailed information in the form of, "You may have a migraine. As detailed information, we will provide you with treatments and preventative measures." The generation AI can also use the emotion estimation function to provide detailed information about the disease in which the user is most interested, such as, "You may have a tension headache. As detailed information, we will provide you with stress management and relaxation methods." The generation AI can also use the emotion estimation function to provide detailed information about the disease in which the user is most interested, and give advice to reduce anxiety. For example, the generation AI can present detailed information in the form of, "You may have a brain tumor. As detailed information, we will provide you with treatments and preventative measures and explain the importance of early detection." This allows the user to receive detailed information about the disease in which the user is most interested.

[0069] The serious illness determination unit can determine the possibility of a serious illness by taking into account the user's past health data or family history. For example, the generation AI refers to the user's past health data to determine the possibility of a serious illness. For example, it evaluates the possibility of a brain tumor based on past diagnostic results and treatment history. The serious illness determination unit also determines the risk of a serious illness by taking into account the user's family history. For example, if there is a family history of brain tumors, the risk is evaluated as high. The serious illness determination unit also analyzes the generation AI's past health data and family history to comprehensively determine the possibility of a serious illness. For example, it evaluates the risk of a brain tumor based on past diagnostic results and family history. This allows the possibility of a serious illness to be determined by taking into account the user's past health data and family history.

[0070] The serious illness determination unit can suggest specific next steps to the user based on the determination results. For example, if the generating AI determines the possibility of a serious illness, the serious illness determination unit will suggest additional tests to the user. For example, it may suggest, "There is a possibility of a brain tumor, so we recommend that you undergo an MRI scan." If the generating AI determines the possibility of a serious illness, the serious illness determination unit will suggest that the user consult a specialist. For example, it may suggest, "There is a possibility of a brain tumor, so please consult a neurosurgeon." If the generating AI determines the possibility of a serious illness, the serious illness determination unit will suggest specific next steps to the user and guide them to an appropriate medical institution. For example, it may suggest, "There is a possibility of a brain tumor, so please consult a specialist nearby and undergo additional tests." This allows the system to suggest specific next steps to the user based on the determination results.

[0071] The serious illness determination unit can use the emotion estimation function to provide counseling information to reduce the user's anxiety if the user has a serious illness. For example, the generation AI uses the emotion estimation function to provide counseling information to reduce the user's anxiety if there is a possibility of a serious illness. For example, this information may be provided in the form of, "You may have a brain tumor, but you can receive appropriate treatment by seeing a specialist." The generation AI also uses the emotion estimation function to provide specific counseling information to reduce the user's anxiety. For example, this information may be provided in the form of, "You may have a tension headache, but stress management and relaxation are effective." The generation AI also uses the emotion estimation function to provide advice to reduce the user's anxiety if there is a possibility of a serious illness. For example, this information may be provided in the form of, "You may have a brain tumor, but treatment is possible with early detection, so please see a specialist." This makes it possible to provide counseling information to reduce the user's anxiety if there is a possibility of a serious illness.

[0072] The serious illness determination unit can personalize the determination result based on the user's health condition or lifestyle habits. For example, the generation AI in the serious illness determination unit personalizes the determination result based on the user's health condition. For example, it may present a message such as, "You may have a brain tumor, but we recommend that you undergo additional testing in consideration of your health condition." The generation AI in the serious illness determination unit also personalizes the determination result based on the user's lifestyle habits. For example, it may present a message such as, "You may have a tension headache, but you need to improve your lifestyle habits." The generation AI in the serious illness determination unit also personalizes the determination result based on the user's health condition and lifestyle habits. For example, it may present a message such as, "You may have a brain tumor, but it is important that you review your health condition and lifestyle habits." This allows the determination result to be personalized based on the user's health condition and lifestyle habits.

[0073] The serious illness determination unit can share the determination results with family or medical professionals with the user's consent, thereby strengthening the support system. For example, the generation AI can present the determination results with family members with the user's consent, thereby strengthening the support system. For example, it can present the results in the form of, "There is a possibility that you have a brain tumor. Please consult with your family and see a specialist." The serious illness determination unit can also share the determination results with medical professionals with the user's consent, thereby strengthening the support system. For example, it can present the results in the form of, "There is a possibility that you have a tension headache. Please consult with your family doctor and decide on a treatment plan." The serious illness determination unit can also share the determination results with family members and medical professionals with the user's consent, thereby building a comprehensive support system. For example, it can present the results in the form of, "There is a possibility that you have a brain tumor. Please work with your family members and medical professionals to receive appropriate treatment." This allows the determination results to be shared with family members and medical professionals with the user's consent, thereby strengthening the support system.

[0074] The serious illness determination unit can use the emotion estimation function to notify the user of a serious illness in a way that makes it easier for the user to accept. For example, the generation AI can use the emotion estimation function to notify the user of the possibility of a serious illness in a way that makes it easier for the user to accept. For example, the generation AI can notify the user by saying, "It may be a brain tumor, but if detected early, it is treatable, so please see a specialist." The generation AI can also use the emotion estimation function to notify the user with an explanation to reduce the user's anxiety. For example, the generation AI can notify the user by saying, "It may be a tension headache, but stress management and relaxation are effective." The generation AI can also use the emotion estimation function to notify the user of a serious illness in a way that makes it easier for the user to accept and provide advice to reduce anxiety. For example, the generation AI can notify the user by saying, "It may be a brain tumor, but if detected early, it is treatable, so please see a specialist." This allows the user to be notified of the possibility of a serious illness in a way that makes it easier for the user to accept.

[0075] The second opinion guidance unit can automatically search for the nearest specialist or medical institution based on the user's location information and support the appointment process. For example, the generation AI in the second opinion guidance unit searches for the nearest specialist based on the user's location information and supports the appointment process. For example, it may provide guidance such as, "You may have a brain tumor, so make an appointment with a nearby neurosurgeon." The second opinion guidance unit can also search for the nearest medical institution based on the user's location information and support the appointment process. For example, it may provide guidance such as, "You may have a tension headache, so make an appointment with a nearby internist." The second opinion guidance unit can also search for the nearest specialist or medical institution based on the user's location information and support the appointment process. For example, it may provide guidance such as, "You may have a brain tumor, so make an appointment with a nearby specialist and undergo additional tests." This allows the generation AI to automatically search for the nearest specialist or medical institution based on the user's location information and support the appointment process.

[0076] The second opinion guidance unit can automatically generate documents or information required for receiving a second opinion and provide them to the user. In the second opinion guidance unit, for example, the generation AI automatically generates documents required for receiving a second opinion and provides them to the user. For example, the information is provided in the form of, "There is a possibility that you have a brain tumor, so we will automatically generate a referral letter for you to see a specialist." In addition, the second opinion guidance unit automatically generates information required for receiving a second opinion and provides it to the user. For example, the information is provided in the form of, "There is a possibility that you have a tension headache, so we will automatically generate the examination results for you to see a specialist." In addition, the second opinion guidance unit automatically generates documents and information required for receiving a second opinion and provides them to the user. For example, the information is provided in the form of, "There is a possibility that you have a brain tumor, so we will automatically generate and provide the documents required for you to see a specialist." In this way, the documents and information required for receiving a second opinion can be automatically generated and provided to the user.

[0077] The second opinion guidance unit can use the emotion estimation function to provide advice to reduce the anxiety the user may feel when getting a second opinion. For example, the generation AI uses the emotion estimation function to provide advice to reduce the anxiety the user may feel when getting a second opinion. For example, the second opinion guidance unit provides advice in the form of, "You may have a brain tumor, but you can receive appropriate treatment by seeing a specialist." The generation AI also uses the emotion estimation function to provide specific advice to reduce the user's anxiety. For example, the second opinion guidance unit provides advice in the form of, "You may have a tension headache, but stress management and relaxation are effective." The generation AI also uses the emotion estimation function to provide advice to reduce the anxiety the user may feel when getting a second opinion. For example, the second opinion guidance unit provides advice in the form of, "You may have a brain tumor, but treatment is possible if detected early, so please see a specialist." This allows the generation AI to provide advice to reduce the anxiety the user may feel when getting a second opinion.

[0078] The second opinion information unit can link the second opinion consultation guide with the user's health insurance information and present a cost estimate or insurance coverage. In the second opinion information unit, for example, the generation AI presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion in the form of, "There is a possibility that you have a brain tumor, so the cost of a consultation with a specialist will be covered by insurance and will be XXX yen." In addition, the second opinion information unit presents the insurance coverage based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information. For example, the second opinion information unit presents a cost estimate for a second opinion based on the user's health insurance information.

[0079] The second opinion guidance unit supports follow-up after receiving a second opinion, and can continuously support the user's health management. For example, the second opinion guidance unit supports follow-up after receiving a second opinion by the generating AI, and continuously supports the user's health management. For example, the second opinion guidance unit provides support in the form of, "We will support you in planning your treatment after you have been diagnosed with a brain tumor." The second opinion guidance unit also supports follow-up after receiving a second opinion by the generating AI, and continuously supports the user's health management. For example, the second opinion guidance unit provides support in the form of, "We will support you in managing your stress after you have been diagnosed with a tension headache." The second opinion guidance unit also supports follow-up after receiving a second opinion by the generating AI, and continuously supports the user's health management. For example, the second opinion guidance unit provides support in the form of, "We will support you in regular health checks after you have been diagnosed with a brain tumor." This allows follow-up after receiving a second opinion to be supported, and continuously supports the user's health management.

[0080] The second opinion guidance unit can use the emotion estimation function to monitor the user's emotions when receiving a second opinion and provide positive feedback. For example, the generation AI in the second opinion guidance unit can use the emotion estimation function to monitor the user's emotions when receiving a second opinion and provide positive feedback. For example, the second opinion guidance unit can provide feedback such as, "You may have a brain tumor, but you can receive appropriate treatment by seeing a specialist." The generation AI can also use the emotion estimation function to monitor the user's emotions and provide positive feedback. For example, the second opinion guidance unit can provide feedback such as, "You may have a tension headache, but stress management and relaxation may be effective." The generation AI can also use the emotion estimation function to monitor the user's emotions when receiving a second opinion and provide positive feedback. For example, the second opinion guidance unit can provide feedback such as, "You may have a brain tumor, but treatment is possible with early detection, so please see a specialist." This allows the generation AI to monitor the user's emotions when receiving a second opinion and provide positive feedback.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The symptom input unit collects information about the user's lifestyle and daily activities, enabling more accurate identification of the cause of symptoms. For example, if a user inputs "I have a persistent headache," the generation AI automatically generates additional questions such as "How is your sleep time and stress level these days?" to collect more detailed information. If a user inputs "I have a cough," the generation AI generates specific questions such as "What about your smoking habits and whether you have any allergies?" to understand the details of the symptoms. If a user inputs "I have a stomachache," the generation AI generates questions such as "How are your diet and exercise habits?" to collect more accurate information. This allows the system to collect information about the user's lifestyle and daily activities and more accurately identify the cause of symptoms.

[0083] The symptom input unit can refer to similar past cases and provide reference information for the symptoms entered by the user. For example, if the user enters "persistent headache," the generation AI will refer to similar past cases and provide reference information such as "migraines and tension headaches have been common in past cases." If the user enters "cough," the generation AI will refer to similar past cases and provide reference information such as "colds and influenza have been common in past cases." If the user enters "stomach pain," the generation AI will refer to similar past cases and provide reference information such as "gastritis and stomach ulcers have been common in past cases." This makes it possible to refer to similar past cases and provide reference information for the symptoms entered by the user.

[0084] The symptom input unit uses its emotion estimation function to analyze the emotions expressed by the user when inputting information and can provide encouraging messages at the appropriate time. For example, if a user inputs, "I'm worried because I have a persistent headache," the generation AI analyzes the emotion and provides an encouraging message such as, "You're not alone, we'll provide an appropriate diagnosis." If a user inputs, "I'm worried because my cough won't stop," the generation AI analyzes the emotion and provides an encouraging message such as, "Don't worry, we'll support you." If a user inputs, "I'm scared because my stomach hurts," the generation AI analyzes the emotion and provides an encouraging message such as, "Don't worry, we'll provide appropriate advice." This allows the system to analyze the user's emotions and provide encouraging messages at the appropriate time.

[0085] The symptom input unit can track the progression of symptoms and check in periodically based on the user's input. For example, if the user inputs "I have a persistent headache," the generation AI will periodically send check-in messages such as "How is your headache?" to track the progression of the symptoms. If the user inputs "I have a cough," the generation AI will periodically send check-in messages such as "How is your cough?" to track the progression of the symptoms. If the user inputs "I have a stomachache," the generation AI will periodically send check-in messages such as "How is your stomachache?" to track the progression of the symptoms. This makes it possible to track the progression of symptoms and check in periodically based on the user's input.

[0086] The symptom input unit uses its emotion estimation function to analyze the emotions expressed by the user and suggest appropriate relaxation methods. For example, if a user enters, "I have a persistent headache and I'm worried," the generation AI analyzes the emotions and suggests relaxation methods such as, "Try taking deep breaths to relax." If a user enters, "I'm worried because my cough won't stop," the generation AI analyzes the emotions and suggests relaxation methods such as, "Try meditating to relax." If a user enters, "I have a stomachache and I'm scared," the generation AI analyzes the emotions and suggests relaxation methods such as, "Try taking a warm bath to relax." This allows the system to analyze the user's emotions and suggest appropriate relaxation methods.

[0087] The disease name enumeration unit can suggest more accurate disease names by taking into account personal information such as the user's age and gender. For example, the generation AI takes into account the user's age and prioritizes suggesting disease names that are common among younger people. The generation AI also takes into account the user's gender and prioritizes suggesting disease names that are common among women. The generation AI also analyzes the user's age and gender in combination to suggest more accurate disease names. This allows for more accurate disease names to be suggested by taking into account personal information such as the user's age and gender.

[0088] The disease name enumeration unit can use the emotion estimation function to provide detailed information about the disease name that the user is most interested in. For example, the generation AI can use the emotion estimation function to provide detailed information about the disease name that the user is most interested in. For example, it can present the information in the form of, "You may have a migraine. As detailed information, we will provide treatments and preventative measures." The generation AI can also use the emotion estimation function to provide detailed information about the disease name that the user is most interested in. For example, it can present the information in the form of, "You may have a tension headache. As detailed information, we will provide stress management and relaxation methods." The generation AI can also use the emotion estimation function to provide detailed information about the disease name that the user is most interested in and give advice to reduce anxiety. For example, it can present the information in the form of, "You may have a brain tumor. As detailed information, we will provide treatments and preventative measures and explain the importance of early detection." This allows the generation AI to provide detailed information about the disease name that the user is most interested in.

[0089] The disease name enumeration unit can evaluate the risk of developing a disease and suggest preventive measures by taking into account the user's lifestyle and environmental factors. For example, the generation AI can consider the user's lifestyle and suggest something like, "You may have a migraine, but you need to improve your lifestyle." The generation AI can also consider the user's environmental factors and suggest something like, "You may have a tension headache, but workplace stress may be the cause." The generation AI can also analyze the user's lifestyle and environmental factors in combination and suggest something like, "You may have a brain tumor, but it is important to review your lifestyle and environmental factors." This allows the generation AI to evaluate the risk of developing a disease and suggest preventive measures by taking into account the user's lifestyle and environmental factors.

[0090] The serious illness determination unit can assess the risk of serious illness and suggest preventive measures by taking into account the user's past health data and family history. For example, the generation AI can refer to the user's past health data and suggest something like, "You may have a brain tumor, but we recommend that you undergo additional testing based on your past diagnostic results." The generation AI can also consider the user's family history and suggest something like, "If you have a family history of brain tumors, we assess your risk highly." The generation AI can also combine and analyze the user's past health data and family history and suggest something like, "We will assess your risk of brain tumors and suggest preventive measures." This allows the system to assess the risk of serious illness and suggest preventive measures by taking into account the user's past health data and family history.

[0091] The serious illness determination unit can use the emotion estimation function to notify the user of the possibility of a serious illness in a way that is easy for the user to accept and provide advice to reduce anxiety. For example, the generation AI can use the emotion estimation function to notify the user in the form of, "It may be a brain tumor, but it is treatable with early detection, so please see a specialist." The generation AI can also use the emotion estimation function to notify the user in the form of, "It may be a tension headache, but stress management and relaxation are effective." The generation AI can also use the emotion estimation function to notify the user in the form of, "It may be a brain tumor, but it is treatable with early detection, so please see a specialist," and provide advice to reduce anxiety. This allows the user to be notified of the possibility of a serious illness in a way that is easy for the user to accept and provide advice to reduce anxiety.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The symptom input unit inputs the symptoms of illness or injury from the user. For example, the user can input symptoms such as "persistent headache," "cough," or "stomachache." Step 2: The examination result input unit inputs the examination results from the first medical institution visited. For example, the user can input examination results such as "diagnosed with migraine," "diagnosed with cold," or "diagnosed with gastritis." Step 3: The disease name enumeration unit analyzes the information entered by the symptom input unit and the examination result input unit, and the generation AI lists possible disease names. For example, it lists disease names such as "Migraine, tension headache, possible brain tumor," "Possible cold, flu, pneumonia," and "Possible gastritis, stomach ulcer, stomach cancer." Step 4: In the serious illness determination section, the AI ​​determines the possibility of a serious illness from the list of illnesses enumerated by the illness enumeration section. For example, it may determine, "There is a possibility of a brain tumor, so we recommend getting a second opinion," "There is a possibility of pneumonia, so we recommend getting a second opinion," or "There is a possibility of stomach cancer, so we recommend getting a second opinion." Step 5: If the serious illness determination unit determines that the patient may have a serious illness, the second opinion guidance unit provides the user with guidance on how to obtain a second opinion. For example, the unit may provide information on nearby specialists and medical institutions and support the appointment process, or provide assistance in preparing the information and documents required for obtaining a second opinion, or provide guidance on the specific steps required for obtaining a second opinion.

[0094] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0095] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0096] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 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.

[0099] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0100] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0101] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0103] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0104] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0105] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0106] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0107] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0108] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0111] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0112] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0113] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0114] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0115] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0116] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0117] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0118] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0119] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0120] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0121] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0122] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0123] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0124] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0127] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0128] 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.

[0129] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0135] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0136] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0138] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0139] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0141] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0143] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0144] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0145] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0146] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0147] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0148] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0149] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0150] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0151] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0152] 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.

[0153] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0154] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0155] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0156] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0157] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0158] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0159] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0160] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0161] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a symptom input unit for inputting symptoms of illness or injury from a user; a medical examination result input unit for inputting the medical examination results at the first medical institution visited; a disease name enumeration unit that analyzes the information input by the symptom input unit and the examination result input unit and enumerates disease names; a serious illness determination unit that determines a serious illness from the disease names listed by the disease name listing unit; and a unit that, when the serious illness determination unit determines that the user has a serious illness, provides the user with a guide to receive a second opinion. A system characterized by:

2. The symptom input unit Automatically generate questions based on the symptoms entered by the user to gather detailed information The system of claim 1 .

3. The symptom input unit Analyzes user voice input and converts it to text using natural language processing The system of claim 1 .

4. The symptom input unit Analyzes emotions as users type and provides advice to reduce stress and anxiety The system of claim 1 .

5. The symptom input unit Symptoms or examination results can be entered using images or videos. The system of claim 1 .

6. The symptom input unit Supports input in different languages, catering to international users The system of claim 1 .

7. The symptom input unit Monitor user emotions in real time as they type and provide positive feedback The system of claim 1 .

8. The disease name listing unit Referencing past diagnostic data or medical literature to suggest more accurate disease names The system of claim 1 .

Images