System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a patient to input ambiguous symptoms; generation and AI means for analyzing the symptoms and converting the results into specific medical terms; means for selecting an optimal doctor based on the analysis results; means for providing information on the selected doctor to the patient; means for inputting the progress of the diagnosed symptoms as feedback; database updating means for improving diagnostic accuracy based on the feedback; and generation and AI means for automatically generating a medical record based on the diagnostic results.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] It is difficult for inexperienced doctors or specialists in other fields to accurately diagnose vague symptoms such as "stomach pain" or "feeling a bit sick" that patients complain of. There is also a lack of systems in place to evaluate the accuracy of diagnostic results and lead to improvements. Furthermore, creating medical records is a time-consuming and labor-intensive task for medical professionals, which reduces the efficiency of doctors' work. There is a need for an efficient and effective system to solve these problems. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing the following means.

[0006] A means for patients to input vague symptoms;

[0007] a generating AI means for analyzing the symptoms and converting the results into specific medical terms;

[0008] A means for selecting an optimal doctor based on the analysis results;

[0009] a means for providing information about the selected doctor to the patient;

[0010] a means for inputting the progress of symptoms after the diagnosis as feedback;

[0011] a database update means for improving diagnostic accuracy based on the feedback data;

[0012] By providing a system that includes an AI generation means that automatically generates medical records based on the data at the time of diagnosis, it is possible to specifically analyze vague symptoms, guide patients to the most appropriate doctor, improve diagnostic accuracy, and further reduce the burden on medical professionals by automatically generating medical records.

[0013] "Patient" refers to a person who receives medical examination or treatment at a medical institution.

[0014] "Symptoms" refer to any medical abnormality or discomfort that a patient notices.

[0015] "Ambiguous symptoms" refer to vague or unclear medical abnormalities or discomforts for which there is insufficient information to make a specific diagnosis.

[0016] "Specific medical terms" refer to clear, standard diagnostic or symptom names commonly used in the medical field.

[0017] "Generative AI" is a type of artificial intelligence that uses machine learning algorithms to analyze data and make appropriate decisions and predictions.

[0018] A "medical record" refers to a document that compiles records of a patient's medical examination and treatment.

[0019] "Database update" refers to the operation of adding new data to the information stored in the system and modifying or deleting existing data.

[0020] "Feedback" refers to providing information to improve systems and processes based on information such as past diagnoses and treatment results.

[0021] "Selection" refers to the process of choosing the most suitable based on specific criteria.

[0022] "Providing" refers to offering specific information or services to others.

[0023] "Reservation system" refers to a system for managing doctor's appointment reservations.

[0024] An "interface" refers to a mechanism that enables the exchange of data and commands between humans and computer systems.

[0025] A "machine learning algorithm" refers to a computational procedure that learns patterns from data and makes predictions or decisions based on them. [Brief explanation of the drawings]

[0026] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0027] 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.

[0028] First, the terms used in the following description will be explained.

[0029] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0030] 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.

[0031] 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.

[0032] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0033] 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."

[0034] [First embodiment]

[0035] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0036] 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.

[0037] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0038] 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.

[0039] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0040] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0041] 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.

[0042] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0043] 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.

[0044] 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.

[0045] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0046] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0047] This invention is a system that allows patients to input vague symptoms, converts them into specific medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses generative AI to analyze and automatically generate medical records, improving the work efficiency of medical professionals.

[0048] System Configuration

[0049] The system consists of the following main components:

[0050] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[0051] 2. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[0052] 3. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[0053] 4. Information provision module: A module that provides patients with information about selected doctors.

[0054] 5. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[0055] 6. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[0056] 7. Automatic medical record generation module: A generative AI module that automatically generates medical records based on diagnostic data.

[0057] Program processing

[0058] Displaying the symptom entry page

[0059] The server transmits a web page to the user's terminal for the patient to input symptoms.

[0060] The terminal displays the received web page in the browser, allowing the patient to enter their symptoms.

[0061] Symptom data analysis

[0062] The user enters the symptoms into the input page and presses the send button.

[0063] The terminal transmits the input data to the server.

[0064] The server passes the received data to the data analysis module.

[0065] The generative AI analyzes symptom data and converts it into specific medical terms such as "stomachache," "pain in the lower right abdomen," and "nausea."

[0066] The server passes the data to the doctor selection module based on the analysis results.

[0067] Selection and guidance of the most suitable doctor

[0068] The server generates a list of the most suitable doctors based on the analysis results and passes the data to the information providing module.

[0069] The information providing module provides the user with information on the most suitable doctor.

[0070] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[0071] Collecting diagnostic feedback

[0072] The user enters post-diagnosis feedback into a feedback collection module.

[0073] The terminal transmits the feedback data to the server.

[0074] The server passes the received feedback data to the database update module.

[0075] The database update module updates the database based on the collected data to improve diagnostic accuracy.

[0076] Automatic generation of medical records

[0077] The server transmits the diagnostic data to the automatic medical record generation module.

[0078] The generation AI automatically generates medical records based on the data sent.

[0079] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[0080] Specific examples

[0081] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[0082] The user enters the symptoms into the input page and submits it.

[0083] The terminal sends the transmitted data to the server.

[0084] The server passes the data to the data analysis module.

[0085] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[0086] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[0087] The information provision module provides the user with information on the most suitable doctor.

[0088] The user is examined and provides feedback after the diagnosis.

[0089] The feedback collection module sends the data to a server.

[0090] A database update module updates the database based on the feedback data.

[0091] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0092] The above is a specific embodiment for carrying out the present invention. The present invention is a system that specifically analyzes vague symptoms, guides patients to the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[0093] The processing flow will be explained below.

[0094] Step 1:

[0095] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[0096] Step 2:

[0097] The server sends the HTML file of the symptom input page to the user's terminal.

[0098] Step 3:

[0099] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[0100] Step 4:

[0101] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form and presses the send button.

[0102] Step 5:

[0103] The terminal transmits the symptom data entered by the user to the server.

[0104] Step 6:

[0105] The server passes the received symptom data to the data analysis module.

[0106] Step 7:

[0107] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea."

[0108] Step 8:

[0109] Based on the analysis results from the generation AI, the server sends information to the doctor selection module to select the most suitable doctor.

[0110] Step 9:

[0111] The doctor selection module lists multiple doctors suitable for the patient's condition based on specific medical terms.

[0112] Step 10:

[0113] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[0114] Step 11:

[0115] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[0116] Step 12:

[0117] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[0118] Step 13:

[0119] The terminal transmits information about the doctor selected by the user to the server.

[0120] Step 14:

[0121] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[0122] Step 15:

[0123] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[0124] Step 16:

[0125] The terminal transmits the input feedback data to the server.

[0126] Step 17:

[0127] The server passes the received feedback data to the database update module.

[0128] Step 18:

[0129] The database update module updates the database based on the feedback data to improve the accuracy of the diagnosis.

[0130] Step 19:

[0131] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0132] Step 20:

[0133] The generation AI automatically generates medical records based on the data sent.

[0134] Step 21:

[0135] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[0136] Example 1

[0137] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0138] In conventional medical systems, the symptoms entered by patients were often vague, resulting in an inefficient diagnosis process. It was also difficult for patients to accurately communicate their symptoms to doctors, which could delay the process of finding the most appropriate doctor. Furthermore, there was also the problem that feedback after diagnosis was not collected, preventing improvements in diagnostic accuracy. This increased the burden on medical professionals and reduced patient satisfaction.

[0139] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0140] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of the symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the diagnostic data; a means for transferring the received data to an analysis module and converting it into specific medical terms using a natural language processing algorithm; a means for transmitting data from a user's terminal and communicating with the analysis module to exchange data; a means for generating a list of doctors based on the analysis results and transferring the data to an information provision module; and a means for automatically generating a final medical record and registering it in the medical system. This allows for concretizing a patient's vague symptoms, quickly guiding the patient to the optimal doctor, and improving diagnostic accuracy.

[0141] "Patient" means an individual who uses the System to receive medical services.

[0142] "Symptoms" refer to the physical abnormalities or discomforts that a patient experiences.

[0143] The "symptom input means" is an interface that allows patients to input their symptoms into the system.

[0144] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform predetermined transformations.

[0145] "Generative AI means" refers to means that use artificial intelligence technology to analyze symptom data and convert it into specific medical terms.

[0146] "Analysis results" are data containing specific medical terms converted by the generating AI means.

[0147] The "doctor selection means" is a means for selecting the most suitable doctor based on the analysis results.

[0148] The "information provision means" is a means for providing information about the selected doctor to the patient.

[0149] The "feedback input means" is a means for the patient to input the progress of symptoms after diagnosis.

[0150] "Feedback data" refers to information entered by the patient regarding the progression of symptoms after diagnosis.

[0151] The "database updating means" is a means for updating the database based on feedback data and improving diagnostic accuracy.

[0152] The "automatic medical record generation means" is a means for automatically generating a medical record based on data at the time of diagnosis.

[0153] The "analysis module" is a module for processing received symptom data and converting it into specific medical terms.

[0154] A "natural language processing algorithm" is an algorithm for understanding and processing human language.

[0155] A "user terminal" is a device used by a patient to enter symptoms and provide feedback.

[0156] The "information provision module" is a module for providing patients with information on the most suitable doctor.

[0157] A "database" is a structure for centrally managing and storing data used throughout the system.

[0158] This invention is a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses a generative AI model to perform analysis and automatically generate medical records, improving the work efficiency of medical professionals. The system includes the following main components:

[0159] System Configuration

[0160] 1. Symptom input tool: A web browser-based interface for patients to input their symptoms. Patients can input physical problems using everyday language.

[0161] 2. Generative AI: A generative AI that analyzes inputted vague symptoms and converts them into specific medical terms. Specifically, it uses natural language processing algorithms such as the BERT model and GPT-3.

[0162] 3. Doctor Selection Means: This is a module that selects the most suitable doctor based on the results analyzed by the Generative AI Means. This module searches for an appropriate doctor from the database.

[0163] 4. Information provision method: An interface for providing patients with information about selected doctors. This is done via a web browser or mobile application.

[0164] 5. Feedback input means: An interface for inputting feedback on the progress of symptoms after diagnosis. Patients input changes in their physical condition and symptoms after diagnosis.

[0165] 6. Database update means: This module updates the database to improve diagnostic accuracy based on collected feedback data. It uses machine learning algorithms to analyze the data and update the database.

[0166] 7. Automatic medical record generation method: This is an AI method for automatically generating medical records based on diagnostic data. The generated medical records are automatically registered in the medical system and made accessible to doctors.

[0167] Specific examples

[0168] For example, if the user inputs "I have a stomachache and feel sick," the system proceeds as follows:

[0169] The user enters the symptoms into the input page and submits it.

[0170] The terminal sends the transmitted data to the server.

[0171] The server passes the data to the data analysis module.

[0172] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[0173] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[0174] The information provision module provides the user with information on the most suitable doctor.

[0175] The user is examined and provides feedback after the diagnosis.

[0176] The feedback collection module sends the data to a server.

[0177] A database update module updates the database based on the feedback data.

[0178] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0179] An example of a specific prompt sentence is, "I have a stomachache and feel sick." Based on this input, the generative AI converts it into specific medical terms such as "stomachache" and "nausea."

[0180] The above is a specific embodiment for carrying out the present invention, which clarifies the patient's vague symptoms, enables prompt guidance to the most appropriate doctor, improves diagnostic accuracy, and reduces the workload of medical professionals.

[0181] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0182] Step 1:

[0183] Displaying the symptom entry page

[0184] The server generates a web page for the patient to enter their symptoms. The page contains a text field where the patient can enter their symptoms and a submit button. The generated HTML and CSS files are prepared.

[0185] The server transmits the generated web page to the terminal.

[0186] The device then displays the received web page in the user's browser, allowing the user to enter their symptoms. The input is free-form text, using everyday language to describe physical problems.

[0187] Step 2:

[0188] Enter and submit symptom data

[0189] The user enters details of the symptom into the input fields and clicks the submit button.

[0190] The device sends the entered data to the server via an Ajax request, which is packaged in JSON format.

[0191] Step 3:

[0192] Symptom data analysis

[0193] The server passes the received symptom data to the analysis module, where the input data is the patient's free-form text.

[0194] The generative AI analyzes the received text data using a natural language processing algorithm (for example, the BERT model or GPT-3). Through this analysis, it converts vague expressions such as "my stomach hurts" or "I feel sick" into specific medical terms such as "stomachache" or "nausea." The processing results are output as a list of specific medical terms.

[0195] The server receives the analysis results and passes them on to the next processing step.

[0196] Step 4:

[0197] Selection of the best doctor

[0198] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The input data is a list of analyzed specific medical terms.

[0199] The doctor selection module searches the database based on this list, generates a list of multiple doctors who are most suitable for the patient's symptoms, and outputs the list of appropriate doctors as the search results.

[0200] The server receives the output data from the physician selection module and passes it on to the next processing step.

[0201] Step 5:

[0202] Providing doctor information

[0203] The server passes the generated list of doctors to the information providing module, and the input data is the list of doctors.

[0204] The information provision module generates an interface to provide to the user, creating a web page containing information such as the selected doctor's name, specialty, and available dates and times.

[0205] The server sends this information to the terminal and displays it in the user's browser.

[0206] Step 6:

[0207] Making an appointment

[0208] The user selects the doctor of their choice from the provided list and makes an appointment.

[0209] The device sends the selected doctor and appointment information to the server, which also packages this data in JSON format.

[0210] The server stores the received reservation information in a database and returns a reservation confirmation page to the user.

[0211] Step 7:

[0212] Collecting diagnostic feedback

[0213] After the consultation, the user enters the progress of symptoms and feedback into the feedback collection module.

[0214] The device sends the input feedback data to the server, including any changes in symptoms after diagnosis and any new abnormalities noticed.

[0215] Step 8:

[0216] Sending feedback data

[0217] The server passes the received feedback data to the database update module, and the input data is the specific feedback information.

[0218] The database update module analyzes the feedback data and updates the database using algorithms to improve diagnostic accuracy.

[0219] Step 9:

[0220] Automatic generation of medical records

[0221] The server sends the diagnosis data to the automatic medical record generation module. The input data is the diagnosis results and prescription information.

[0222] The AI ​​automatically generates a medical record based on the received data, which includes the patient's symptoms, diagnosis, prescriptions, and more.

[0223] The automatic medical record generation module registers the generated medical records in the medical system, making them accessible to doctors.

[0224] The above are the specific processing steps and functions of the system. This process clarifies the patient's vague symptoms, enabling prompt guidance to the most appropriate doctor and improving diagnostic accuracy.

[0225] (Application example 1)

[0226] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0227] In today's medical field, it remains difficult for patients to accurately communicate vague symptoms they experience to medical professionals and receive optimal treatment. Much effort is also spent on selecting doctors, creating medical records, and collecting feedback to improve diagnostic accuracy. Online medical services, in particular, require systems that can convert vague symptoms entered by patients into concrete medical terms and provide optimal treatment.

[0228] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0229] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on data at the time of the diagnosis; a means for the symptom input means to use a smartphone or smart glasses; and a means for inputting a prompt sentence to the generating AI model to convert the symptoms into specific medical terms. By converting vague symptoms into specific medical terms and inputting them, the server can guide the patient to the optimal doctor, improving diagnostic accuracy and automatically generating medical records.

[0230] "Means for patients to input vague symptoms" refers to an interface that allows patients to input vague symptoms via text or voice.

[0231] "Generative AI means for analyzing symptoms and converting the results into specific medical terms" refers to a device or program that uses artificial intelligence technology to analyze inputted vague symptoms and convert them into specific medical terms.

[0232] "Means for selecting the best doctor" refers to a method or device for selecting the doctor most suitable for a patient based on analyzed symptom data.

[0233] "Means for providing information about the selected physician to the patient" refers to a method or interface for transmitting information about the selected physician to the patient.

[0234] "Means for inputting feedback on the progression of symptoms after diagnosis" refers to an interface for inputting the symptoms and condition of a patient after diagnosis.

[0235] The term "database updating means for improving diagnostic accuracy based on feedback data" refers to a method or device for updating a database based on collected feedback data to improve diagnostic accuracy.

[0236] "Generative AI means for automatically generating medical records based on data at the time of diagnosis" refers to artificial intelligence technology for automatically creating medical records using data collected at the time of diagnosis.

[0237] "Means in which symptom input means uses a smartphone or smart glasses" refers to a method or device that allows patients to input vague symptoms using a smartphone or smart glasses.

[0238] "Means for inputting prompt sentences to a generative AI model" refers to a method or device for providing input sentences (prompt sentences) to a generative AI for analysis.

[0239] This system allows patients to input vague symptoms, converts them into specific medical terms, and guides them to the most appropriate doctor. It also collects post-diagnosis feedback to improve diagnostic accuracy and automatically generates medical records based on medical data. This system achieves these functions using a generative AI model.

[0240] First, the patient inputs their symptoms using a smartphone or smart glasses. The user enters vague symptoms into an input page and submits them. The device then sends the input data to the server. The server passes the received data to a data analysis module, where the generative AI analyzes the symptom data and converts it into specific medical terms. For example, if a patient inputs "I have a stomachache and feel sick," the generative AI will analyze this as "stomachache" and "nausea."

[0241] Next, the server selects the most suitable doctor based on the analysis results. The doctor selection module uses this analysis result to generate a list of the most suitable doctors. The information provision module then provides the user with information on the most suitable doctors. The user then selects the doctor they wish to see from the provided list and makes an appointment.

[0242] To input the progress of symptoms after diagnosis as feedback, the user inputs progress information into a feedback collection module. The terminal transmits the feedback data to a server, and the server passes the received feedback data to a database update module. The database update module updates the database based on this collected data to improve diagnostic accuracy.

[0243] Finally, a medical record is automatically generated based on the data at the time of diagnosis. The server sends the data at the time of diagnosis to the automatic medical record generation module. The generation AI automatically generates a medical record based on the sent data, registers it in the medical system, and makes it accessible to doctors.

[0244] This system is realized using the following specific hardware and software: Hardware includes a smartphone, smart glasses, a server, a user terminal, etc. Software includes a generative AI model (e.g., OpenAI API), a web browser, a data analysis module, a doctor selection module, an information provision module, a feedback collection module, a database update module, and an automatic medical record generation module.

[0245] For example, some examples of prompts to input to a generative AI model include:

[0246] "Please translate the following symptoms into specific medical terms: I have a stomach ache and feel sick."

[0247] This will create a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy.

[0248] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0249] Step 1:

[0250] The user inputs vague symptoms using a smartphone or smart glasses. The input vague symptoms might be, for example, "My stomach hurts and I feel sick." The device then sends the input data to the server.

[0251] Step 2:

[0252] The server passes the received data to the data analysis module, which sends a prompt to the generative AI model based on the vague symptoms entered. The prompt is, "Please translate the following symptoms into concrete medical terms: I have a stomachache and feel sick."

[0253] Step 3:

[0254] The generative AI model analyzes symptom data based on the prompt sentence. Specifically, it converts "I have a stomachache and feel sick" into specific medical terms such as "stomachache" and "nausea." The server receives the analysis results from the generative AI model.

[0255] Step 4:

[0256] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The doctor selection module lists doctors suited to the specialty based on the analysis results, such as "stomach pain" or "nausea." This allows the most suitable doctor to be selected.

[0257] Step 5:

[0258] The server uses the information provision module to provide the user with information about the selected doctors. Based on this information, the user can select the doctor they wish to see and make an appointment online.

[0259] Step 6:

[0260] After the diagnosis, the user inputs feedback about the results of the diagnosis and treatment into the feedback collection module, and the terminal transmits the feedback data to the server.

[0261] Step 7:

[0262] The server passes the received feedback data to a database update module, which analyzes the feedback data and updates the database to improve diagnostic accuracy.

[0263] Step 8:

[0264] When automatically generating a medical record based on diagnostic data, the server sends the data to the automatic medical record generation module. The generation AI automatically generates a medical record based on the diagnostic data sent. The generated medical record is registered in the medical system and made accessible to doctors.

[0265] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0266] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses generative AI to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[0267] System Configuration

[0268] The system consists of the following main components:

[0269] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[0270] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[0271] 3. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[0272] 4. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[0273] 5. Information provision module: A module that provides patients with information about selected doctors.

[0274] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[0275] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[0276] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[0277] Program processing

[0278] Displaying the symptom entry page

[0279] The server transmits a web page to the user's terminal for the patient to input symptoms.

[0280] The terminal displays the received web page in the browser and makes it ready for input.

[0281] Symptom data analysis

[0282] The user enters symptoms such as "stomach ache" or "feeling sick" into the input form.

[0283] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expression or voice and transmits the emotion data to the server.

[0284] The server passes the input symptom data and emotion data to the data analysis module.

[0285] The generative AI analyzes symptom data and converts it into specific medical terms (e.g., "stomach pain" or "nausea"), and also analyzes emotional data to use as auxiliary information for diagnosis.

[0286] The server sends the analysis results to the physician selection module.

[0287] Selection and guidance of the most suitable doctor

[0288] The doctor selection module lists multiple doctors who are best suited to the patient's condition based on specific medical terms and emotional data.

[0289] The server passes the list of optimal doctors to the information providing module and displays it to the user (patient).

[0290] Collecting diagnostic feedback

[0291] After the diagnosis, the user uses the feedback collection module to input the diagnosis results and the subsequent progress of symptoms.

[0292] The terminal transmits the input feedback data to the server.

[0293] The server passes the received feedback data to the database update module.

[0294] The database update module updates the database to improve diagnostic accuracy based on the feedback data.

[0295] Automatic generation of medical records

[0296] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0297] The generation AI automatically generates medical records based on the data sent.

[0298] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[0299] Specific examples

[0300] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[0301] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[0302] The terminal transmits the input data and emotion data to the server.

[0303] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[0304] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[0305] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[0306] The user is examined and provides feedback after the diagnosis.

[0307] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[0308] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0309] The above is a specific embodiment for carrying out the present invention. The present invention is a system that performs analysis based on symptom and emotion data, recommends the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[0310] The processing flow will be explained below.

[0311] Step 1:

[0312] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[0313] Step 2:

[0314] The server sends the HTML file of the symptom input page to the user's terminal.

[0315] Step 3:

[0316] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[0317] Step 4:

[0318] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form.

[0319] Step 5:

[0320] The emotion engine operates to collect and analyze facial expression or voice data while the user is inputting symptoms to generate emotion data.

[0321] Step 6:

[0322] The terminal transmits the input symptom data and emotion data to the server.

[0323] Step 7:

[0324] The server passes the received symptom data and emotion data to a data analysis module.

[0325] Step 8:

[0326] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea." It also analyzes emotional data and uses it as diagnostic aids.

[0327] Step 9:

[0328] The server transmits data to the doctor selection module based on the analysis results and emotion data.

[0329] Step 10:

[0330] The doctor selection module lists multiple doctors who are best suited to the patient's symptoms based on specific medical terms and emotional data, and selects the doctor who can provide the appropriate treatment for the patient, taking into account the emotional data.

[0331] Step 11:

[0332] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[0333] Step 12:

[0334] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[0335] Step 13:

[0336] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[0337] Step 14:

[0338] The terminal transmits information about the doctor selected by the user to the server.

[0339] Step 15:

[0340] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[0341] Step 16:

[0342] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[0343] Step 17:

[0344] The terminal transmits the input feedback data to the server.

[0345] Step 18:

[0346] The server passes the received feedback data to the database update module.

[0347] Step 19:

[0348] The database update module updates the database to improve diagnostic accuracy based on the feedback data and emotion data.

[0349] Step 20:

[0350] The server transmits the emotion data together with the diagnostic data and feedback data to the automatic medical record generation module.

[0351] Step 21:

[0352] The generation AI automatically generates medical records based on the data sent.

[0353] Step 22:

[0354] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[0355] Example 2

[0356] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0357] Conventional medical systems have had problems leading to accurate diagnoses because patients are unable to clearly describe their symptoms or emotional information is not taken into account. Furthermore, the selection of doctors, improving diagnostic accuracy, and recording medical records are all largely manual and inefficient. This places a heavy burden on both doctors and patients.

[0358] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the patient to input vague symptoms, an emotion engine means for recognizing emotions at the time of symptom input, a generation AI means for analyzing symptoms and converting the results into specific medical terms, a means for selecting an optimal doctor based on the analysis results and emotion data, a means for providing the patient with information on the selected doctor, a means for inputting the progress of symptoms after the diagnosis as feedback, a database update means for improving diagnostic accuracy based on the feedback data, and a generation AI means for automatically generating a medical record based on data at the time of diagnosis. This enables accurate diagnosis based on the patient's vague symptoms and emotion data, selection of an optimal doctor, improvement of diagnostic accuracy, and automatic generation of a medical record.

[0359] A "patient" is a person who receives diagnosis or treatment at a medical institution.

[0360] "Vague symptoms" are physical or mental abnormalities that patients describe without using specific medical or technical terms.

[0361] An "emotion engine" is software or hardware that analyzes a patient's facial expressions and voice and recognizes their emotional state.

[0362] "Generative AI" is a type of artificial intelligence that uses machine learning algorithms to analyze input data and output the results.

[0363] "Specific medical terms" are medically standardized terminology used for diagnosis and treatment.

[0364] A "doctor selection tool" is software or an algorithm that has the function of selecting an appropriate doctor based on the patient's symptoms and emotional data.

[0365] "Information providing means" refers to an interface or system for providing information about selected doctors to patients.

[0366] A "feedback collection means" is an interface or system for collecting information from a patient about the progress of their symptoms after diagnosis.

[0367] The "database update means" is software or algorithm that has the function of updating the database based on collected feedback data and improving diagnostic accuracy.

[0368] The "automatic medical record generation means" is a system that uses generation AI to automatically create medical records based on diagnostic data and feedback data.

[0369] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses a generative AI model to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[0370] System Configuration

[0371] The system consists of the following main components:

[0372] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[0373] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[0374] 3. Data analysis module: A module that analyzes input symptom data using a generative AI model and converts it into specific medical terms.

[0375] 4. Doctor selection module: A module that selects the most suitable doctor based on analysis results and emotional data.

[0376] 5. Information provision module: A module that provides patients with information about selected doctors.

[0377] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[0378] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[0379] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[0380] Program processing

[0381] Displaying the symptom entry page

[0382] The server sends a web page to the user's device, where the patient can enter their symptoms. This web page is composed of HTML and JavaScript and includes an input form, information fields, and a script for collecting emotion data.

[0383] The device displays the received web page in the browser, allowing the user to input symptoms. At the same time, the emotion engine is initialized.

[0384] Symptom data input and sentiment analysis

[0385] Users enter symptoms such as "stomach ache" or "feeling sick" into an input form. They can also provide additional information using a voice input function.

[0386] The device collects input symptom data in real time and simultaneously captures the patient's facial expressions and voice using a camera and microphone, which are then analyzed by an emotion engine.

[0387] The terminal transmits the collected symptom data and emotion data to the server.

[0388] Symptom and emotion data analysis

[0389] The server passes the received symptom data and emotion data to a data analysis module.

[0390] The generative AI model converts symptom data into specific medical terms and analyzes emotional data to generate diagnostic aids.

[0391] The server sends the analysis results and emotion data to the doctor selection module.

[0392] Selection and guidance of the most suitable doctor

[0393] The doctor selection module lists multiple optimal doctors based on the analysis results and emotional data.

[0394] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[0395] The information providing module displays the list to the user and prompts the user to make a selection.

[0396] Collecting diagnostic feedback

[0397] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[0398] The terminal transmits the input feedback data to the server.

[0399] The server sends the received feedback data to the database update module.

[0400] The database update module updates the database based on the feedback data to improve diagnostic accuracy.

[0401] Automatic generation of medical records

[0402] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0403] The generative AI model automatically generates medical records based on the submitted data.

[0404] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[0405] Specific examples

[0406] For example, if the user inputs "my stomach hurts and I feel sick" as a symptom, the process proceeds as follows:

[0407] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[0408] The terminal transmits the input data and emotion data to the server.

[0409] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[0410] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[0411] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[0412] The user is examined and provides feedback after the diagnosis.

[0413] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[0414] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0415] Prompt Sentence Examples

[0416] 1. "Please convert the patient's symptom, 'I have a stomachache and feel sick,' into medical terms. Furthermore, please analyze the patient's emotional data and use it as diagnostic support information."

[0417] 2. "Automatically generate a medical record based on the diagnosis and feedback."

[0418] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0419] Step 1: Display the symptom entry page

[0420] The server sends a symptom input page composed of HTML and JavaScript to devices that access a specific URL. The input page includes a symptom input form and a script for collecting emotional data.

[0421] The device renders the received HTML and JavaScript in the browser, allowing the patient to enter their symptoms. When the input page is displayed, the emotion engine is also initialized.

[0422] Input: URL visited by patient

[0423] Output: A browser showing the symptom entry page

[0424] Step 2: Symptom data input and sentiment analysis

[0425] The user enters symptoms such as "stomach ache" or "feeling sick" into the form on the symptom input page, and provides additional information using the voice input function as needed.

[0426] The device collects input symptom data in real time and uses a camera and microphone to capture the patient's facial expressions and voice data, which are then analyzed by an emotion engine.

[0427] The terminal combines the collected symptom data and emotion data into a single data packet and transmits it to the server.

[0428] Input: Symptom data entered by the patient, captured facial and voice data

[0429] Output: Symptom data and emotion data sent to the server

[0430] Step 3: Analyze symptom and emotion data

[0431] The server passes the received symptom data and emotion data to a data analysis module.

[0432] The generative AI model converts symptom data into specific medical terms such as "stomach pain" or "nausea," and also analyzes emotion data to generate diagnostic support information.

[0433] The server sends the generated medical terms and the results of the sentiment analysis to the doctor selection module.

[0434] Input: Symptom data and emotion data received by the server

[0435] Output: Analysis results with specific medical terms and supporting information

[0436] Step 4: Selecting and recommending the best doctor

[0437] The doctor selection module uses the analysis results and emotional data to create a list of multiple doctors best suited to the patient's symptoms.

[0438] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[0439] The information providing module displays a list of doctors on the user's browser and prompts the user to select the doctor they wish to see.

[0440] Input: Analysis results, emotional data, doctor information

[0441] Output: A list of doctors displayed to the user

[0442] Step 5: Collect diagnostic feedback

[0443] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[0444] The terminal transmits the input feedback data to the server.

[0445] The server passes the received feedback data to a database update module to update the database.

[0446] Input: User-entered feedback data

[0447] Output: Feedback data updated in the database

[0448] Step 6: Automatic generation of medical records

[0449] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0450] The generative AI model automatically generates detailed medical records based on the submitted data.

[0451] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[0452] Input: Diagnostic data, feedback data

[0453] Output: Medical records registered in the medical system

[0454] (Application example 2)

[0455] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0456] In conventional medical systems, it is difficult for patients to clearly communicate their symptoms and there is a lack of means to recognize their emotional state, making it difficult to make an appropriate diagnosis. Furthermore, many tasks, such as selecting the appropriate doctor, collecting feedback after diagnosis, and automatically generating medical records, are performed manually, placing a heavy burden on medical professionals. This leads to issues such as reduced diagnostic accuracy and worsening work efficiency.

[0457] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0458] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting the most appropriate doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the data at the time of the diagnosis; a means including an emotion engine for analyzing the patient's facial expressions or voice and recognizing emotional data; a means for inputting symptoms via a smartphone application and analyzing them together with the emotional data; and a means for listing and providing the most appropriate doctors for the application. This allows for a more accurate understanding of a patient's vague symptoms and emotional state, enabling the selection of an appropriate doctor, improving diagnostic accuracy, and enabling the automatic generation of medical records and the collection of feedback to be performed efficiently.

[0459] A "patient" is a person who seeks medical examination or treatment from a medical institution.

[0460] "Symptoms" refer to signs or conditions of a disease or abnormality that a patient is aware of.

[0461] "Input" is the act of providing information or data to a system.

[0462] "Generative AI" uses artificial intelligence techniques to analyze data and automatically generate specific results.

[0463] "Analysis" is the act of breaking down data or information and analyzing its contents in detail.

[0464] "Medical terminology" refers to specialized words and expressions related to medicine and health.

[0465] "Selection" is the act of choosing the best option from among many candidates.

[0466] A "physician" is a medical professional who has medical expertise and qualifications and who provides medical examinations and treatment.

[0467] "Information" refers to content such as knowledge and data.

[0468] "Providing" is the act of giving something that is needed to someone else.

[0469] "Diagnosis" is the medical procedure for identifying a patient's illness or abnormality.

[0470] "Feedback" is the act of giving a reaction or opinion to a certain action or result.

[0471] A "database" is a system that systematically collects and centrally manages a large amount of data.

[0472] "Update" is the act of changing existing information or data into new information or data.

[0473] A "medical record" is a document that compiles records and data related to a patient's medical treatment.

[0474] "Emotion engine" refers to technology that recognizes a patient's emotional state from their facial expressions and voice.

[0475] A "smartphone application" is software that runs on a smartphone.

[0476] "Listing" is the act of presenting suitable options from a number of options in list form.

[0477] A "system" is a system in which interrelated parts and elements are combined to perform a specific function.

[0478] This invention relates to a system that improves diagnostic accuracy by allowing patients to input vague symptoms using a smartphone application and even recognizing their emotions at the time of input. This system has the function of analyzing symptoms using a generative AI model and automatically generating medical records. It also allows for continuous improvement of diagnostic accuracy through feedback.

[0479] System Configuration

[0480] The system consists of the following main components:

[0481] 1. Symptom input method

[0482] This is an interface for patients to input their vague symptoms. This interface uses a smartphone application.

[0483] 2. Emotion Engine

[0484] The system analyzes the patient's facial expressions and voice when entering symptoms and recognizes emotional data, using Google Cloud Vision and IBM Watson's emotion analysis API.

[0485] 3. Data Analysis Module

[0486] It uses a generative AI model, such as OpenAI's GPT-4, that analyzes input symptom and emotion data and converts the results into specific medical terms.

[0487] 4. Doctor Selection Module

[0488] This module lists the most suitable doctors based on the analysis results. It is built using Python and utilizes libraries such as SciPy and TensorFlow.

[0489] 5. Information Module

[0490] This module provides patients with information about selected doctors. The information is presented through a smartphone application interface.

[0491] 6. Feedback Collection Module

[0492] This module collects feedback from patients about the progress of their symptoms after diagnosis. The collected feedback data is sent to the server.

[0493] 7. Database Update Module

[0494] This module periodically updates the database to improve diagnostic accuracy based on feedback data.

[0495] 8. Automatic medical record generation module

[0496] It uses a generative AI model that automatically generates medical records based on diagnostic data and feedback data, and the generated medical records are registered in the medical system and made accessible to doctors.

[0497] Program processing

[0498] Displaying the symptom entry page

[0499] The server generates a web page or smartphone application interface for patients to enter their symptoms and sends it to the user's device.

[0500] The terminal displays the received interface and makes it possible for the patient to input information.

[0501] Symptom data analysis

[0502] Users use a smartphone application to input symptoms such as "stomach ache" or "nausea."

[0503] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expressions or voice, and also transmits the emotion data to the server.

[0504] The server passes this data to a data analysis module, where a generative AI model analyzes it and converts it into specific medical terms.

[0505] Selection and guidance of the most suitable doctor

[0506] The doctor selection module lists the most suitable doctors based on medical terminology and emotional data received from the generative AI.

[0507] The server passes this list to the information providing module and displays it to the patient.

[0508] Collecting diagnostic feedback

[0509] Users input their post-diagnosis progress and impressions through a feedback collection module.

[0510] The terminal transmits this feedback data to the server.

[0511] The server passes the received feedback data to a database update module to update the database.

[0512] Automatic generation of medical records

[0513] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0514] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[0515] Specific examples

[0516] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[0517] The user enters symptoms into a smartphone application, and the emotion engine simultaneously analyzes emotional data from facial expressions and voice.

[0518] The terminal transmits the input symptom data and emotion data to the server.

[0519] The server passes the data to a data analysis module, where a generative AI model converts the data into specific medical terms.

[0520] The server sends the analysis results to the doctor selection module, which generates a list of the most suitable doctors.

[0521] The information provision module provides the list to the patient, who then schedules an appointment.

[0522] After the patient is seen, feedback is collected and sent to the server.

[0523] The database update module updates the database to improve diagnostic accuracy.

[0524] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0525] Prompt Sentence Examples

[0526] Patient's stated symptoms: Stomach pain, feeling sick

[0527] Emotional data: sad facial expression, nervous voice

[0528] Translate the symptoms into specific medical terms and list the doctors who are suitable for the patient.

[0529] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0530] Step 1:

[0531] Display of symptom entry screen

[0532] The server generates a web page or smartphone application interface for patients to enter their symptoms.

[0533] The server sends this interface to the user's terminal, which displays the received interface.

[0534] As a result, the patient is ready to enter their symptoms.

[0535] Step 2:

[0536] Symptom entry and emotional data collection

[0537] Users input their symptoms (e.g., "I have a stomachache" or "I feel sick") using the smartphone application interface.

[0538] At the same time, the emotion engine analyzes emotion data using video and audio data input from the device's camera and microphone.

[0539] The terminal transmits the collected symptom data and emotion data to a server.

[0540] Input data: Symptoms (text), emotion data (voice, facial expression)

[0541] Output data: Symptom data, emotion data

[0542] Step 3:

[0543] Data analysis

[0544] The server passes the received symptom data and emotion data to a data analysis module.

[0545] The data analysis module uses a generative AI model (e.g., GPT-4) to analyze this data and translate vague symptoms into concrete medical terms.

[0546] Input data: symptom data, emotion data

[0547] Output data: Data converted into medical terms

[0548] Step 4:

[0549] Doctor Selection

[0550] The server passes the specific medical terms obtained from the data analysis module to the physician selection module.

[0551] The doctor selection module uses libraries such as Python, SciPy, and TensorFlow to list the most suitable doctors based on the analysis results.

[0552] Input data: Data converted into medical terms

[0553] Output data: List of best doctors

[0554] Step 5:

[0555] Providing optimal doctor information

[0556] The server passes the list of optimal doctors obtained from the doctor selection module to the information providing module.

[0557] The information provision module provides this list to the patient through the smartphone application interface.

[0558] Input data: List of best doctors

[0559] Output data: Optimal doctor information displayed to the patient

[0560] Step 6:

[0561] Collecting diagnostic feedback

[0562] Users enter information about the progression of symptoms after diagnosis and their evaluation of the diagnostic results through the feedback collection module of the smartphone application.

[0563] The terminal transmits the feedback data to the server.

[0564] Input data: Feedback data

[0565] Output data: Feedback data sent to the server

[0566] Step 7:

[0567] Database Update

[0568] The server passes the received feedback data to the database update module.

[0569] The database update module updates the database based on this data to improve diagnostic accuracy.

[0570] Input data: Feedback data

[0571] Output data: Updated database

[0572] Step 8:

[0573] Automatic generation of medical records

[0574] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0575] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[0576] Input data: diagnostic data, feedback data

[0577] Output data: Automatically generated medical records

[0578] 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.

[0579] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0580] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0581] [Second embodiment]

[0582] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0583] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0584] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0585] 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.

[0586] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0587] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0588] 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.

[0589] 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.

[0590] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0591] 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.

[0592] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0593] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0594] This invention is a system that allows patients to input vague symptoms, converts them into specific medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses generative AI to analyze and automatically generate medical records, improving the work efficiency of medical professionals.

[0595] System Configuration

[0596] The system consists of the following main components:

[0597] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[0598] 2. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[0599] 3. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[0600] 4. Information provision module: A module that provides patients with information about selected doctors.

[0601] 5. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[0602] 6. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[0603] 7. Automatic medical record generation module: A generative AI module that automatically generates medical records based on diagnostic data.

[0604] Program processing

[0605] Displaying the symptom entry page

[0606] The server transmits a web page to the user's terminal for the patient to input symptoms.

[0607] The terminal displays the received web page in the browser, allowing the patient to enter their symptoms.

[0608] Symptom data analysis

[0609] The user enters the symptoms into the input page and presses the send button.

[0610] The terminal transmits the input data to the server.

[0611] The server passes the received data to the data analysis module.

[0612] The generative AI analyzes symptom data and converts it into specific medical terms such as "stomachache," "pain in the lower right abdomen," and "nausea."

[0613] The server passes the data to the doctor selection module based on the analysis results.

[0614] Selection and guidance of the most suitable doctor

[0615] The server generates a list of the most suitable doctors based on the analysis results and passes the data to the information providing module.

[0616] The information providing module provides the user with information on the most suitable doctor.

[0617] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[0618] Collecting diagnostic feedback

[0619] The user enters post-diagnosis feedback into a feedback collection module.

[0620] The terminal transmits the feedback data to the server.

[0621] The server passes the received feedback data to the database update module.

[0622] The database update module updates the database based on the collected data to improve diagnostic accuracy.

[0623] Automatic generation of medical records

[0624] The server transmits the diagnostic data to the automatic medical record generation module.

[0625] The generation AI automatically generates medical records based on the data sent.

[0626] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[0627] Specific examples

[0628] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[0629] The user enters the symptoms into the input page and submits it.

[0630] The terminal sends the transmitted data to the server.

[0631] The server passes the data to the data analysis module.

[0632] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[0633] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[0634] The information provision module provides the user with information on the most suitable doctor.

[0635] The user is examined and provides feedback after the diagnosis.

[0636] The feedback collection module sends the data to a server.

[0637] A database update module updates the database based on the feedback data.

[0638] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0639] The above is a specific embodiment for carrying out the present invention. The present invention is a system that specifically analyzes vague symptoms, guides patients to the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[0640] The processing flow will be explained below.

[0641] Step 1:

[0642] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[0643] Step 2:

[0644] The server sends the HTML file of the symptom input page to the user's terminal.

[0645] Step 3:

[0646] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[0647] Step 4:

[0648] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form and presses the send button.

[0649] Step 5:

[0650] The terminal transmits the symptom data entered by the user to the server.

[0651] Step 6:

[0652] The server passes the received symptom data to the data analysis module.

[0653] Step 7:

[0654] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea."

[0655] Step 8:

[0656] Based on the analysis results from the generation AI, the server sends information to the doctor selection module to select the most suitable doctor.

[0657] Step 9:

[0658] The doctor selection module lists multiple doctors suitable for the patient's condition based on specific medical terms.

[0659] Step 10:

[0660] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[0661] Step 11:

[0662] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[0663] Step 12:

[0664] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[0665] Step 13:

[0666] The terminal transmits information about the doctor selected by the user to the server.

[0667] Step 14:

[0668] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[0669] Step 15:

[0670] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[0671] Step 16:

[0672] The terminal transmits the input feedback data to the server.

[0673] Step 17:

[0674] The server passes the received feedback data to the database update module.

[0675] Step 18:

[0676] The database update module updates the database based on the feedback data to improve the accuracy of the diagnosis.

[0677] Step 19:

[0678] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0679] Step 20:

[0680] The generation AI automatically generates medical records based on the data sent.

[0681] Step 21:

[0682] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[0683] Example 1

[0684] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0685] In conventional medical systems, the symptoms entered by patients were often vague, resulting in an inefficient diagnosis process. It was also difficult for patients to accurately communicate their symptoms to doctors, which could delay the process of finding the most appropriate doctor. Furthermore, there was also the problem that feedback after diagnosis was not collected, preventing improvements in diagnostic accuracy. This increased the burden on medical professionals and reduced patient satisfaction.

[0686] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0687] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of the symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the diagnostic data; a means for transferring the received data to an analysis module and converting it into specific medical terms using a natural language processing algorithm; a means for transmitting data from a user's terminal and communicating with the analysis module to exchange data; a means for generating a list of doctors based on the analysis results and transferring the data to an information provision module; and a means for automatically generating a final medical record and registering it in the medical system. This allows for concretizing a patient's vague symptoms, quickly guiding the patient to the optimal doctor, and improving diagnostic accuracy.

[0688] "Patient" means an individual who uses the System to receive medical services.

[0689] "Symptoms" refer to the physical abnormalities or discomforts that a patient experiences.

[0690] The "symptom input means" is an interface that allows patients to input their symptoms into the system.

[0691] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform predetermined transformations.

[0692] "Generative AI means" refers to means that use artificial intelligence technology to analyze symptom data and convert it into specific medical terms.

[0693] "Analysis results" are data containing specific medical terms converted by the generating AI means.

[0694] The "doctor selection means" is a means for selecting the most suitable doctor based on the analysis results.

[0695] The "information provision means" is a means for providing information about the selected doctor to the patient.

[0696] The "feedback input means" is a means for the patient to input the progress of symptoms after diagnosis.

[0697] "Feedback data" refers to information entered by the patient regarding the progression of symptoms after diagnosis.

[0698] The "database updating means" is a means for updating the database based on feedback data and improving diagnostic accuracy.

[0699] The "automatic medical record generation means" is a means for automatically generating a medical record based on data at the time of diagnosis.

[0700] The "analysis module" is a module for processing received symptom data and converting it into specific medical terms.

[0701] A "natural language processing algorithm" is an algorithm for understanding and processing human language.

[0702] A "user terminal" is a device used by a patient to enter symptoms and provide feedback.

[0703] The "information provision module" is a module for providing patients with information on the most suitable doctor.

[0704] A "database" is a structure for centrally managing and storing data used throughout the system.

[0705] This invention is a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses a generative AI model to perform analysis and automatically generate medical records, improving the work efficiency of medical professionals. The system includes the following main components:

[0706] System Configuration

[0707] 1. Symptom input tool: A web browser-based interface for patients to input their symptoms. Patients can input physical problems using everyday language.

[0708] 2. Generative AI: A generative AI that analyzes inputted vague symptoms and converts them into specific medical terms. Specifically, it uses natural language processing algorithms such as the BERT model and GPT-3.

[0709] 3. Doctor Selection Means: This is a module that selects the most suitable doctor based on the results analyzed by the Generative AI Means. This module searches for an appropriate doctor from the database.

[0710] 4. Information provision method: An interface for providing patients with information about selected doctors. This is done via a web browser or mobile application.

[0711] 5. Feedback input means: An interface for inputting feedback on the progress of symptoms after diagnosis. Patients input changes in their physical condition and symptoms after diagnosis.

[0712] 6. Database update means: This module updates the database to improve diagnostic accuracy based on collected feedback data. It uses machine learning algorithms to analyze the data and update the database.

[0713] 7. Automatic medical record generation method: This is an AI method for automatically generating medical records based on diagnostic data. The generated medical records are automatically registered in the medical system and made accessible to doctors.

[0714] Specific examples

[0715] For example, if the user inputs "I have a stomachache and feel sick," the system proceeds as follows:

[0716] The user enters the symptoms into the input page and submits it.

[0717] The terminal sends the transmitted data to the server.

[0718] The server passes the data to the data analysis module.

[0719] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[0720] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[0721] The information provision module provides the user with information on the most suitable doctor.

[0722] The user is examined and provides feedback after the diagnosis.

[0723] The feedback collection module sends the data to a server.

[0724] A database update module updates the database based on the feedback data.

[0725] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0726] An example of a specific prompt sentence is, "I have a stomachache and feel sick." Based on this input, the generative AI converts it into specific medical terms such as "stomachache" and "nausea."

[0727] The above is a specific embodiment for carrying out the present invention, which clarifies the patient's vague symptoms, enables prompt guidance to the most appropriate doctor, improves diagnostic accuracy, and reduces the workload of medical professionals.

[0728] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0729] Step 1:

[0730] Displaying the symptom entry page

[0731] The server generates a web page for the patient to enter their symptoms. The page contains a text field where the patient can enter their symptoms and a submit button. The generated HTML and CSS files are prepared.

[0732] The server transmits the generated web page to the terminal.

[0733] The device then displays the received web page in the user's browser, allowing the user to enter their symptoms. The input is free-form text, using everyday language to describe physical problems.

[0734] Step 2:

[0735] Enter and submit symptom data

[0736] The user enters details of the symptom into the input fields and clicks the submit button.

[0737] The device sends the entered data to the server via an Ajax request, which is packaged in JSON format.

[0738] Step 3:

[0739] Symptom data analysis

[0740] The server passes the received symptom data to the analysis module, where the input data is the patient's free-form text.

[0741] The generative AI analyzes the received text data using a natural language processing algorithm (for example, the BERT model or GPT-3). Through this analysis, it converts vague expressions such as "my stomach hurts" or "I feel sick" into specific medical terms such as "stomachache" or "nausea." The processing results are output as a list of specific medical terms.

[0742] The server receives the analysis results and passes them on to the next processing step.

[0743] Step 4:

[0744] Selection of the best doctor

[0745] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The input data is a list of analyzed specific medical terms.

[0746] The doctor selection module searches the database based on this list, generates a list of multiple doctors who are most suitable for the patient's symptoms, and outputs the list of appropriate doctors as the search results.

[0747] The server receives the output data from the physician selection module and passes it on to the next processing step.

[0748] Step 5:

[0749] Providing doctor information

[0750] The server passes the generated list of doctors to the information providing module, and the input data is the list of doctors.

[0751] The information provision module generates an interface to provide to the user, creating a web page containing information such as the selected doctor's name, specialty, and available dates and times.

[0752] The server sends this information to the terminal and displays it in the user's browser.

[0753] Step 6:

[0754] Making an appointment

[0755] The user selects the doctor of their choice from the provided list and makes an appointment.

[0756] The device sends the selected doctor and appointment information to the server, which also packages this data in JSON format.

[0757] The server stores the received reservation information in a database and returns a reservation confirmation page to the user.

[0758] Step 7:

[0759] Collecting diagnostic feedback

[0760] After the consultation, the user enters the progress of symptoms and feedback into the feedback collection module.

[0761] The device sends the input feedback data to the server, including any changes in symptoms after diagnosis and any new abnormalities noticed.

[0762] Step 8:

[0763] Sending feedback data

[0764] The server passes the received feedback data to the database update module, and the input data is the specific feedback information.

[0765] The database update module analyzes the feedback data and updates the database using algorithms to improve diagnostic accuracy.

[0766] Step 9:

[0767] Automatic generation of medical records

[0768] The server sends the diagnosis data to the automatic medical record generation module. The input data is the diagnosis results and prescription information.

[0769] The AI ​​automatically generates a medical record based on the received data, which includes the patient's symptoms, diagnosis, prescriptions, and more.

[0770] The automatic medical record generation module registers the generated medical records in the medical system, making them accessible to doctors.

[0771] The above are the specific processing steps and functions of the system. This process clarifies the patient's vague symptoms, enabling prompt guidance to the most appropriate doctor and improving diagnostic accuracy.

[0772] (Application example 1)

[0773] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0774] In today's medical field, it remains difficult for patients to accurately communicate vague symptoms they experience to medical professionals and receive optimal treatment. Much effort is also spent on selecting doctors, creating medical records, and collecting feedback to improve diagnostic accuracy. Online medical services, in particular, require systems that can convert vague symptoms entered by patients into concrete medical terms and provide optimal treatment.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0776] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on data at the time of the diagnosis; a means for the symptom input means to use a smartphone or smart glasses; and a means for inputting a prompt sentence to the generating AI model to convert the symptoms into specific medical terms. By converting vague symptoms into specific medical terms and inputting them, the server can guide the patient to the optimal doctor, improving diagnostic accuracy and automatically generating medical records.

[0777] "Means for patients to input vague symptoms" refers to an interface that allows patients to input vague symptoms via text or voice.

[0778] "Generative AI means for analyzing symptoms and converting the results into specific medical terms" refers to a device or program that uses artificial intelligence technology to analyze inputted vague symptoms and convert them into specific medical terms.

[0779] "Means for selecting the best doctor" refers to a method or device for selecting the doctor most suitable for a patient based on analyzed symptom data.

[0780] "Means for providing information about the selected physician to the patient" refers to a method or interface for transmitting information about the selected physician to the patient.

[0781] "Means for inputting feedback on the progression of symptoms after diagnosis" refers to an interface for inputting the symptoms and condition of a patient after diagnosis.

[0782] The term "database updating means for improving diagnostic accuracy based on feedback data" refers to a method or device for updating a database based on collected feedback data to improve diagnostic accuracy.

[0783] "Generative AI means for automatically generating medical records based on data at the time of diagnosis" refers to artificial intelligence technology for automatically creating medical records using data collected at the time of diagnosis.

[0784] "Means in which symptom input means uses a smartphone or smart glasses" refers to a method or device that allows patients to input vague symptoms using a smartphone or smart glasses.

[0785] "Means for inputting prompt sentences to a generative AI model" refers to a method or device for providing input sentences (prompt sentences) to a generative AI for analysis.

[0786] This system allows patients to input vague symptoms, converts them into specific medical terms, and guides them to the most appropriate doctor. It also collects post-diagnosis feedback to improve diagnostic accuracy and automatically generates medical records based on medical data. This system achieves these functions using a generative AI model.

[0787] First, the patient inputs their symptoms using a smartphone or smart glasses. The user enters vague symptoms into an input page and submits them. The device then sends the input data to the server. The server passes the received data to a data analysis module, where the generative AI analyzes the symptom data and converts it into specific medical terms. For example, if a patient inputs "I have a stomachache and feel sick," the generative AI will analyze this as "stomachache" and "nausea."

[0788] Next, the server selects the most suitable doctor based on the analysis results. The doctor selection module uses this analysis result to generate a list of the most suitable doctors. The information provision module then provides the user with information on the most suitable doctors. The user then selects the doctor they wish to see from the provided list and makes an appointment.

[0789] To input the progress of symptoms after diagnosis as feedback, the user inputs progress information into a feedback collection module. The terminal transmits the feedback data to a server, and the server passes the received feedback data to a database update module. The database update module updates the database based on this collected data to improve diagnostic accuracy.

[0790] Finally, a medical record is automatically generated based on the data at the time of diagnosis. The server sends the data at the time of diagnosis to the automatic medical record generation module. The generation AI automatically generates a medical record based on the sent data, registers it in the medical system, and makes it accessible to doctors.

[0791] This system is realized using the following specific hardware and software: Hardware includes a smartphone, smart glasses, a server, a user terminal, etc. Software includes a generative AI model (e.g., OpenAI API), a web browser, a data analysis module, a doctor selection module, an information provision module, a feedback collection module, a database update module, and an automatic medical record generation module.

[0792] For example, some examples of prompts to input to a generative AI model include:

[0793] "Please translate the following symptoms into specific medical terms: I have a stomach ache and feel sick."

[0794] This will create a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy.

[0795] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0796] Step 1:

[0797] The user inputs vague symptoms using a smartphone or smart glasses. The input vague symptoms might be, for example, "My stomach hurts and I feel sick." The device then sends the input data to the server.

[0798] Step 2:

[0799] The server passes the received data to the data analysis module, which sends a prompt to the generative AI model based on the vague symptoms entered. The prompt is, "Please translate the following symptoms into concrete medical terms: I have a stomachache and feel sick."

[0800] Step 3:

[0801] The generative AI model analyzes symptom data based on the prompt sentence. Specifically, it converts "I have a stomachache and feel sick" into specific medical terms such as "stomachache" and "nausea." The server receives the analysis results from the generative AI model.

[0802] Step 4:

[0803] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The doctor selection module lists doctors suited to the specialty based on the analysis results, such as "stomach pain" or "nausea." This allows the most suitable doctor to be selected.

[0804] Step 5:

[0805] The server uses the information provision module to provide the user with information about the selected doctors. Based on this information, the user can select the doctor they wish to see and make an appointment online.

[0806] Step 6:

[0807] After the diagnosis, the user inputs feedback about the results of the diagnosis and treatment into the feedback collection module, and the terminal transmits the feedback data to the server.

[0808] Step 7:

[0809] The server passes the received feedback data to a database update module, which analyzes the feedback data and updates the database to improve diagnostic accuracy.

[0810] Step 8:

[0811] When automatically generating a medical record based on diagnostic data, the server sends the data to the automatic medical record generation module. The generation AI automatically generates a medical record based on the diagnostic data sent. The generated medical record is registered in the medical system and made accessible to doctors.

[0812] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0813] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses generative AI to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[0814] System Configuration

[0815] The system consists of the following main components:

[0816] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[0817] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[0818] 3. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[0819] 4. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[0820] 5. Information provision module: A module that provides patients with information about selected doctors.

[0821] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[0822] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[0823] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[0824] Program processing

[0825] Displaying the symptom entry page

[0826] The server transmits a web page to the user's terminal for the patient to input symptoms.

[0827] The terminal displays the received web page in the browser and makes it ready for input.

[0828] Symptom data analysis

[0829] The user enters symptoms such as "stomach ache" or "feeling sick" into the input form.

[0830] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expression or voice and transmits the emotion data to the server.

[0831] The server passes the input symptom data and emotion data to the data analysis module.

[0832] The generative AI analyzes symptom data and converts it into specific medical terms (e.g., "stomach pain" or "nausea"), and also analyzes emotional data to use as auxiliary information for diagnosis.

[0833] The server sends the analysis results to the physician selection module.

[0834] Selection and guidance of the most suitable doctor

[0835] The doctor selection module lists multiple doctors who are best suited to the patient's condition based on specific medical terms and emotional data.

[0836] The server passes the list of optimal doctors to the information providing module and displays it to the user (patient).

[0837] Collecting diagnostic feedback

[0838] After the diagnosis, the user uses the feedback collection module to input the diagnosis results and the subsequent progress of symptoms.

[0839] The terminal transmits the input feedback data to the server.

[0840] The server passes the received feedback data to the database update module.

[0841] The database update module updates the database to improve diagnostic accuracy based on the feedback data.

[0842] Automatic generation of medical records

[0843] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0844] The generation AI automatically generates medical records based on the data sent.

[0845] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[0846] Specific examples

[0847] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[0848] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[0849] The terminal transmits the input data and emotion data to the server.

[0850] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[0851] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[0852] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[0853] The user is examined and provides feedback after the diagnosis.

[0854] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[0855] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0856] The above is a specific embodiment for carrying out the present invention. The present invention is a system that performs analysis based on symptom and emotion data, recommends the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[0857] The processing flow will be explained below.

[0858] Step 1:

[0859] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[0860] Step 2:

[0861] The server sends the HTML file of the symptom input page to the user's terminal.

[0862] Step 3:

[0863] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[0864] Step 4:

[0865] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form.

[0866] Step 5:

[0867] The emotion engine operates to collect and analyze facial expression or voice data while the user is inputting symptoms to generate emotion data.

[0868] Step 6:

[0869] The terminal transmits the input symptom data and emotion data to the server.

[0870] Step 7:

[0871] The server passes the received symptom data and emotion data to a data analysis module.

[0872] Step 8:

[0873] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea." It also analyzes emotional data and uses it as diagnostic aids.

[0874] Step 9:

[0875] The server transmits data to the doctor selection module based on the analysis results and emotion data.

[0876] Step 10:

[0877] The doctor selection module lists multiple doctors who are best suited to the patient's symptoms based on specific medical terms and emotional data, and selects the doctor who can provide the appropriate treatment for the patient, taking into account the emotional data.

[0878] Step 11:

[0879] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[0880] Step 12:

[0881] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[0882] Step 13:

[0883] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[0884] Step 14:

[0885] The terminal transmits information about the doctor selected by the user to the server.

[0886] Step 15:

[0887] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[0888] Step 16:

[0889] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[0890] Step 17:

[0891] The terminal transmits the input feedback data to the server.

[0892] Step 18:

[0893] The server passes the received feedback data to the database update module.

[0894] Step 19:

[0895] The database update module updates the database to improve diagnostic accuracy based on the feedback data and emotion data.

[0896] Step 20:

[0897] The server transmits the emotion data together with the diagnostic data and feedback data to the automatic medical record generation module.

[0898] Step 21:

[0899] The generation AI automatically generates medical records based on the data sent.

[0900] Step 22:

[0901] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[0902] Example 2

[0903] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0904] Conventional medical systems have had problems leading to accurate diagnoses because patients are unable to clearly describe their symptoms or emotional information is not taken into account. Furthermore, the selection of doctors, improving diagnostic accuracy, and recording medical records are all largely manual and inefficient. This places a heavy burden on both doctors and patients.

[0905] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the patient to input vague symptoms, an emotion engine means for recognizing emotions at the time of symptom input, a generation AI means for analyzing symptoms and converting the results into specific medical terms, a means for selecting an optimal doctor based on the analysis results and emotion data, a means for providing the patient with information on the selected doctor, a means for inputting the progress of symptoms after the diagnosis as feedback, a database update means for improving diagnostic accuracy based on the feedback data, and a generation AI means for automatically generating a medical record based on data at the time of diagnosis. This enables accurate diagnosis based on the patient's vague symptoms and emotion data, selection of an optimal doctor, improvement of diagnostic accuracy, and automatic generation of a medical record.

[0906] A "patient" is a person who receives diagnosis or treatment at a medical institution.

[0907] "Vague symptoms" are physical or mental abnormalities that patients describe without using specific medical or technical terms.

[0908] An "emotion engine" is software or hardware that analyzes a patient's facial expressions and voice and recognizes their emotional state.

[0909] "Generative AI" is a type of artificial intelligence that uses machine learning algorithms to analyze input data and output the results.

[0910] "Specific medical terms" are medically standardized terminology used for diagnosis and treatment.

[0911] A "doctor selection tool" is software or an algorithm that has the function of selecting an appropriate doctor based on the patient's symptoms and emotional data.

[0912] "Information providing means" refers to an interface or system for providing information about selected doctors to patients.

[0913] A "feedback collection means" is an interface or system for collecting information from a patient about the progress of their symptoms after diagnosis.

[0914] The "database update means" is software or algorithm that has the function of updating the database based on collected feedback data and improving diagnostic accuracy.

[0915] The "automatic medical record generation means" is a system that uses generation AI to automatically create medical records based on diagnostic data and feedback data.

[0916] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses a generative AI model to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[0917] System Configuration

[0918] The system consists of the following main components:

[0919] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[0920] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[0921] 3. Data analysis module: A module that analyzes input symptom data using a generative AI model and converts it into specific medical terms.

[0922] 4. Doctor selection module: A module that selects the most suitable doctor based on analysis results and emotional data.

[0923] 5. Information provision module: A module that provides patients with information about selected doctors.

[0924] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[0925] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[0926] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[0927] Program processing

[0928] Displaying the symptom entry page

[0929] The server sends a web page to the user's device, where the patient can enter their symptoms. This web page is composed of HTML and JavaScript and includes an input form, information fields, and a script for collecting emotion data.

[0930] The device displays the received web page in the browser, allowing the user to input symptoms. At the same time, the emotion engine is initialized.

[0931] Symptom data input and sentiment analysis

[0932] Users enter symptoms such as "stomach ache" or "feeling sick" into an input form. They can also provide additional information using a voice input function.

[0933] The device collects input symptom data in real time and simultaneously captures the patient's facial expressions and voice using a camera and microphone, which are then analyzed by an emotion engine.

[0934] The terminal transmits the collected symptom data and emotion data to the server.

[0935] Symptom and emotion data analysis

[0936] The server passes the received symptom data and emotion data to a data analysis module.

[0937] The generative AI model converts symptom data into specific medical terms and analyzes emotional data to generate diagnostic aids.

[0938] The server sends the analysis results and emotion data to the doctor selection module.

[0939] Selection and guidance of the most suitable doctor

[0940] The doctor selection module lists multiple optimal doctors based on the analysis results and emotional data.

[0941] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[0942] The information providing module displays the list to the user and prompts the user to make a selection.

[0943] Collecting diagnostic feedback

[0944] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[0945] The terminal transmits the input feedback data to the server.

[0946] The server sends the received feedback data to the database update module.

[0947] The database update module updates the database based on the feedback data to improve diagnostic accuracy.

[0948] Automatic generation of medical records

[0949] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0950] The generative AI model automatically generates medical records based on the submitted data.

[0951] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[0952] Specific examples

[0953] For example, if the user inputs "my stomach hurts and I feel sick" as a symptom, the process proceeds as follows:

[0954] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[0955] The terminal transmits the input data and emotion data to the server.

[0956] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[0957] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[0958] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[0959] The user is examined and provides feedback after the diagnosis.

[0960] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[0961] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[0962] Prompt Sentence Examples

[0963] 1. "Please convert the patient's symptom, 'I have a stomachache and feel sick,' into medical terms. Furthermore, please analyze the patient's emotional data and use it as diagnostic support information."

[0964] 2. "Automatically generate a medical record based on the diagnosis and feedback."

[0965] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0966] Step 1: Display the symptom entry page

[0967] The server sends a symptom input page composed of HTML and JavaScript to devices that access a specific URL. The input page includes a symptom input form and a script for collecting emotional data.

[0968] The device renders the received HTML and JavaScript in the browser, allowing the patient to enter their symptoms. When the input page is displayed, the emotion engine is also initialized.

[0969] Input: URL visited by patient

[0970] Output: A browser showing the symptom entry page

[0971] Step 2: Symptom data input and sentiment analysis

[0972] The user enters symptoms such as "stomach ache" or "feeling sick" into the form on the symptom input page, and provides additional information using the voice input function as needed.

[0973] The device collects input symptom data in real time and uses a camera and microphone to capture the patient's facial expressions and voice data, which are then analyzed by an emotion engine.

[0974] The terminal combines the collected symptom data and emotion data into a single data packet and transmits it to the server.

[0975] Input: Symptom data entered by the patient, captured facial and voice data

[0976] Output: Symptom data and emotion data sent to the server

[0977] Step 3: Analyze symptom and emotion data

[0978] The server passes the received symptom data and emotion data to a data analysis module.

[0979] The generative AI model converts symptom data into specific medical terms such as "stomach pain" or "nausea," and also analyzes emotion data to generate diagnostic support information.

[0980] The server sends the generated medical terms and the results of the sentiment analysis to the doctor selection module.

[0981] Input: Symptom data and emotion data received by the server

[0982] Output: Analysis results with specific medical terms and supporting information

[0983] Step 4: Selecting and recommending the best doctor

[0984] The doctor selection module uses the analysis results and emotional data to create a list of multiple doctors best suited to the patient's symptoms.

[0985] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[0986] The information providing module displays a list of doctors on the user's browser and prompts the user to select the doctor they wish to see.

[0987] Input: Analysis results, emotional data, doctor information

[0988] Output: A list of doctors displayed to the user

[0989] Step 5: Collect diagnostic feedback

[0990] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[0991] The terminal transmits the input feedback data to the server.

[0992] The server passes the received feedback data to a database update module to update the database.

[0993] Input: User-entered feedback data

[0994] Output: Feedback data updated in the database

[0995] Step 6: Automatic generation of medical records

[0996] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[0997] The generative AI model automatically generates detailed medical records based on the submitted data.

[0998] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[0999] Input: Diagnostic data, feedback data

[1000] Output: Medical records registered in the medical system

[1001] (Application example 2)

[1002] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1003] In conventional medical systems, it is difficult for patients to clearly communicate their symptoms and there is a lack of means to recognize their emotional state, making it difficult to make an appropriate diagnosis. Furthermore, many tasks, such as selecting the appropriate doctor, collecting feedback after diagnosis, and automatically generating medical records, are performed manually, placing a heavy burden on medical professionals. This leads to issues such as reduced diagnostic accuracy and worsening work efficiency.

[1004] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1005] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting the most appropriate doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the data at the time of the diagnosis; a means including an emotion engine for analyzing the patient's facial expressions or voice and recognizing emotional data; a means for inputting symptoms via a smartphone application and analyzing them together with the emotional data; and a means for listing and providing the most appropriate doctors for the application. This allows for a more accurate understanding of a patient's vague symptoms and emotional state, enabling the selection of an appropriate doctor, improving diagnostic accuracy, and enabling the automatic generation of medical records and the collection of feedback to be performed efficiently.

[1006] A "patient" is a person who seeks medical examination or treatment from a medical institution.

[1007] "Symptoms" refer to signs or conditions of a disease or abnormality that a patient is aware of.

[1008] "Input" is the act of providing information or data to a system.

[1009] "Generative AI" uses artificial intelligence techniques to analyze data and automatically generate specific results.

[1010] "Analysis" is the act of breaking down data or information and analyzing its contents in detail.

[1011] "Medical terminology" refers to specialized words and expressions related to medicine and health.

[1012] "Selection" is the act of choosing the best option from among many candidates.

[1013] A "physician" is a medical professional who has medical expertise and qualifications and who provides medical examinations and treatment.

[1014] "Information" refers to content such as knowledge and data.

[1015] "Providing" is the act of giving something that is needed to someone else.

[1016] "Diagnosis" is the medical procedure for identifying a patient's illness or abnormality.

[1017] "Feedback" is the act of giving a reaction or opinion to a certain action or result.

[1018] A "database" is a system that systematically collects and centrally manages a large amount of data.

[1019] "Update" is the act of changing existing information or data into new information or data.

[1020] A "medical record" is a document that compiles records and data related to a patient's medical treatment.

[1021] "Emotion engine" refers to technology that recognizes a patient's emotional state from their facial expressions and voice.

[1022] A "smartphone application" is software that runs on a smartphone.

[1023] "Listing" is the act of presenting suitable options from a number of options in list form.

[1024] A "system" is a system in which interrelated parts and elements are combined to perform a specific function.

[1025] This invention relates to a system that improves diagnostic accuracy by allowing patients to input vague symptoms using a smartphone application and even recognizing their emotions at the time of input. This system has the function of analyzing symptoms using a generative AI model and automatically generating medical records. It also allows for continuous improvement of diagnostic accuracy through feedback.

[1026] System Configuration

[1027] The system consists of the following main components:

[1028] 1. Symptom input method

[1029] This is an interface for patients to input their vague symptoms. This interface uses a smartphone application.

[1030] 2. Emotion Engine

[1031] The system analyzes the patient's facial expressions and voice when entering symptoms and recognizes emotional data, using Google Cloud Vision and IBM Watson's emotion analysis API.

[1032] 3. Data Analysis Module

[1033] It uses a generative AI model, such as OpenAI's GPT-4, that analyzes input symptom and emotion data and converts the results into specific medical terms.

[1034] 4. Doctor Selection Module

[1035] This module lists the most suitable doctors based on the analysis results. It is built using Python and utilizes libraries such as SciPy and TensorFlow.

[1036] 5. Information Module

[1037] This module provides patients with information about selected doctors. The information is presented through a smartphone application interface.

[1038] 6. Feedback Collection Module

[1039] This module collects feedback from patients about the progress of their symptoms after diagnosis. The collected feedback data is sent to the server.

[1040] 7. Database Update Module

[1041] This module periodically updates the database to improve diagnostic accuracy based on feedback data.

[1042] 8. Automatic medical record generation module

[1043] It uses a generative AI model that automatically generates medical records based on diagnostic data and feedback data, and the generated medical records are registered in the medical system and made accessible to doctors.

[1044] Program processing

[1045] Displaying the symptom entry page

[1046] The server generates a web page or smartphone application interface for patients to enter their symptoms and sends it to the user's device.

[1047] The terminal displays the received interface and makes it possible for the patient to input information.

[1048] Symptom data analysis

[1049] Users use a smartphone application to input symptoms such as "stomach ache" or "nausea."

[1050] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expressions or voice, and also transmits the emotion data to the server.

[1051] The server passes this data to a data analysis module, where a generative AI model analyzes it and converts it into specific medical terms.

[1052] Selection and guidance of the most suitable doctor

[1053] The doctor selection module lists the most suitable doctors based on medical terminology and emotional data received from the generative AI.

[1054] The server passes this list to the information providing module and displays it to the patient.

[1055] Collecting diagnostic feedback

[1056] Users input their post-diagnosis progress and impressions through a feedback collection module.

[1057] The terminal transmits this feedback data to the server.

[1058] The server passes the received feedback data to a database update module to update the database.

[1059] Automatic generation of medical records

[1060] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1061] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[1062] Specific examples

[1063] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[1064] The user enters symptoms into a smartphone application, and the emotion engine simultaneously analyzes emotional data from facial expressions and voice.

[1065] The terminal transmits the input symptom data and emotion data to the server.

[1066] The server passes the data to a data analysis module, where a generative AI model converts the data into specific medical terms.

[1067] The server sends the analysis results to the doctor selection module, which generates a list of the most suitable doctors.

[1068] The information provision module provides the list to the patient, who then schedules an appointment.

[1069] After the patient is seen, feedback is collected and sent to the server.

[1070] The database update module updates the database to improve diagnostic accuracy.

[1071] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1072] Prompt Sentence Examples

[1073] Patient's stated symptoms: Stomach pain, feeling sick

[1074] Emotional data: sad facial expression, nervous voice

[1075] Translate the symptoms into specific medical terms and list the doctors who are suitable for the patient.

[1076] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1077] Step 1:

[1078] Display of symptom entry screen

[1079] The server generates a web page or smartphone application interface for patients to enter their symptoms.

[1080] The server sends this interface to the user's terminal, which displays the received interface.

[1081] As a result, the patient is ready to enter their symptoms.

[1082] Step 2:

[1083] Symptom entry and emotional data collection

[1084] Users input their symptoms (e.g., "I have a stomachache" or "I feel sick") using the smartphone application interface.

[1085] At the same time, the emotion engine analyzes emotion data using video and audio data input from the device's camera and microphone.

[1086] The terminal transmits the collected symptom data and emotion data to a server.

[1087] Input data: Symptoms (text), emotion data (voice, facial expression)

[1088] Output data: Symptom data, emotion data

[1089] Step 3:

[1090] Data analysis

[1091] The server passes the received symptom data and emotion data to a data analysis module.

[1092] The data analysis module uses a generative AI model (e.g., GPT-4) to analyze this data and translate vague symptoms into concrete medical terms.

[1093] Input data: symptom data, emotion data

[1094] Output data: Data converted into medical terms

[1095] Step 4:

[1096] Doctor Selection

[1097] The server passes the specific medical terms obtained from the data analysis module to the physician selection module.

[1098] The doctor selection module uses libraries such as Python, SciPy, and TensorFlow to list the most suitable doctors based on the analysis results.

[1099] Input data: Data converted into medical terms

[1100] Output data: List of best doctors

[1101] Step 5:

[1102] Providing optimal doctor information

[1103] The server passes the list of optimal doctors obtained from the doctor selection module to the information providing module.

[1104] The information provision module provides this list to the patient through the smartphone application interface.

[1105] Input data: List of best doctors

[1106] Output data: Optimal doctor information displayed to the patient

[1107] Step 6:

[1108] Collecting diagnostic feedback

[1109] Users enter information about the progression of symptoms after diagnosis and their evaluation of the diagnostic results through the feedback collection module of the smartphone application.

[1110] The terminal transmits the feedback data to the server.

[1111] Input data: Feedback data

[1112] Output data: Feedback data sent to the server

[1113] Step 7:

[1114] Database Update

[1115] The server passes the received feedback data to the database update module.

[1116] The database update module updates the database based on this data to improve diagnostic accuracy.

[1117] Input data: Feedback data

[1118] Output data: Updated database

[1119] Step 8:

[1120] Automatic generation of medical records

[1121] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1122] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[1123] Input data: diagnostic data, feedback data

[1124] Output data: Automatically generated medical records

[1125] 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.

[1126] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1127] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1128] [Third embodiment]

[1129] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1130] 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.

[1131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1132] 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.

[1133] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1135] 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.

[1136] 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.

[1137] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1138] 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.

[1139] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1140] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1141] This invention is a system that allows patients to input vague symptoms, converts them into specific medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses generative AI to analyze and automatically generate medical records, improving the work efficiency of medical professionals.

[1142] System Configuration

[1143] The system consists of the following main components:

[1144] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[1145] 2. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[1146] 3. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[1147] 4. Information provision module: A module that provides patients with information about selected doctors.

[1148] 5. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[1149] 6. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[1150] 7. Automatic medical record generation module: A generative AI module that automatically generates medical records based on diagnostic data.

[1151] Program processing

[1152] Displaying the symptom entry page

[1153] The server transmits a web page to the user's terminal for the patient to input symptoms.

[1154] The terminal displays the received web page in the browser, allowing the patient to enter their symptoms.

[1155] Symptom data analysis

[1156] The user enters the symptoms into the input page and presses the send button.

[1157] The terminal transmits the input data to the server.

[1158] The server passes the received data to the data analysis module.

[1159] The generative AI analyzes symptom data and converts it into specific medical terms such as "stomachache," "pain in the lower right abdomen," and "nausea."

[1160] The server passes the data to the doctor selection module based on the analysis results.

[1161] Selection and guidance of the most suitable doctor

[1162] The server generates a list of the most suitable doctors based on the analysis results and passes the data to the information providing module.

[1163] The information providing module provides the user with information on the most suitable doctor.

[1164] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[1165] Collecting diagnostic feedback

[1166] The user enters post-diagnosis feedback into a feedback collection module.

[1167] The terminal transmits the feedback data to the server.

[1168] The server passes the received feedback data to the database update module.

[1169] The database update module updates the database based on the collected data to improve diagnostic accuracy.

[1170] Automatic generation of medical records

[1171] The server transmits the diagnostic data to the automatic medical record generation module.

[1172] The generation AI automatically generates medical records based on the data sent.

[1173] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[1174] Specific examples

[1175] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[1176] The user enters the symptoms into the input page and submits it.

[1177] The terminal sends the transmitted data to the server.

[1178] The server passes the data to the data analysis module.

[1179] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[1180] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[1181] The information provision module provides the user with information on the most suitable doctor.

[1182] The user is examined and provides feedback after the diagnosis.

[1183] The feedback collection module sends the data to a server.

[1184] A database update module updates the database based on the feedback data.

[1185] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1186] The above is a specific embodiment for carrying out the present invention. The present invention is a system that specifically analyzes vague symptoms, guides patients to the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[1187] The processing flow will be explained below.

[1188] Step 1:

[1189] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[1190] Step 2:

[1191] The server sends the HTML file of the symptom input page to the user's terminal.

[1192] Step 3:

[1193] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[1194] Step 4:

[1195] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form and presses the send button.

[1196] Step 5:

[1197] The terminal transmits the symptom data entered by the user to the server.

[1198] Step 6:

[1199] The server passes the received symptom data to the data analysis module.

[1200] Step 7:

[1201] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea."

[1202] Step 8:

[1203] Based on the analysis results from the generation AI, the server sends information to the doctor selection module to select the most suitable doctor.

[1204] Step 9:

[1205] The doctor selection module lists multiple doctors suitable for the patient's condition based on specific medical terms.

[1206] Step 10:

[1207] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[1208] Step 11:

[1209] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[1210] Step 12:

[1211] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[1212] Step 13:

[1213] The terminal transmits information about the doctor selected by the user to the server.

[1214] Step 14:

[1215] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[1216] Step 15:

[1217] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[1218] Step 16:

[1219] The terminal transmits the input feedback data to the server.

[1220] Step 17:

[1221] The server passes the received feedback data to the database update module.

[1222] Step 18:

[1223] The database update module updates the database based on the feedback data to improve the accuracy of the diagnosis.

[1224] Step 19:

[1225] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1226] Step 20:

[1227] The generation AI automatically generates medical records based on the data sent.

[1228] Step 21:

[1229] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[1230] Example 1

[1231] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1232] In conventional medical systems, the symptoms entered by patients were often vague, resulting in an inefficient diagnosis process. It was also difficult for patients to accurately communicate their symptoms to doctors, which could delay the process of finding the most appropriate doctor. Furthermore, there was also the problem that feedback after diagnosis was not collected, preventing improvements in diagnostic accuracy. This increased the burden on medical professionals and reduced patient satisfaction.

[1233] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1234] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of the symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the diagnostic data; a means for transferring the received data to an analysis module and converting it into specific medical terms using a natural language processing algorithm; a means for transmitting data from a user's terminal and communicating with the analysis module to exchange data; a means for generating a list of doctors based on the analysis results and transferring the data to an information provision module; and a means for automatically generating a final medical record and registering it in the medical system. This allows for concretizing a patient's vague symptoms, quickly guiding the patient to the optimal doctor, and improving diagnostic accuracy.

[1235] "Patient" means an individual who uses the System to receive medical services.

[1236] "Symptoms" refer to the physical abnormalities or discomforts that a patient experiences.

[1237] The "symptom input means" is an interface that allows patients to input their symptoms into the system.

[1238] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform predetermined transformations.

[1239] "Generative AI means" refers to means that use artificial intelligence technology to analyze symptom data and convert it into specific medical terms.

[1240] "Analysis results" are data containing specific medical terms converted by the generating AI means.

[1241] The "doctor selection means" is a means for selecting the most suitable doctor based on the analysis results.

[1242] The "information provision means" is a means for providing information about the selected doctor to the patient.

[1243] The "feedback input means" is a means for the patient to input the progress of symptoms after diagnosis.

[1244] "Feedback data" refers to information entered by the patient regarding the progression of symptoms after diagnosis.

[1245] The "database updating means" is a means for updating the database based on feedback data and improving diagnostic accuracy.

[1246] The "automatic medical record generation means" is a means for automatically generating a medical record based on data at the time of diagnosis.

[1247] The "analysis module" is a module for processing received symptom data and converting it into specific medical terms.

[1248] A "natural language processing algorithm" is an algorithm for understanding and processing human language.

[1249] A "user terminal" is a device used by a patient to enter symptoms and provide feedback.

[1250] The "information provision module" is a module for providing patients with information on the most suitable doctor.

[1251] A "database" is a structure for centrally managing and storing data used throughout the system.

[1252] This invention is a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses a generative AI model to perform analysis and automatically generate medical records, improving the work efficiency of medical professionals. The system includes the following main components:

[1253] System Configuration

[1254] 1. Symptom input tool: A web browser-based interface for patients to input their symptoms. Patients can input physical problems using everyday language.

[1255] 2. Generative AI: A generative AI that analyzes inputted vague symptoms and converts them into specific medical terms. Specifically, it uses natural language processing algorithms such as the BERT model and GPT-3.

[1256] 3. Doctor Selection Means: This is a module that selects the most suitable doctor based on the results analyzed by the Generative AI Means. This module searches for an appropriate doctor from the database.

[1257] 4. Information provision method: An interface for providing patients with information about selected doctors. This is done via a web browser or mobile application.

[1258] 5. Feedback input means: An interface for inputting feedback on the progress of symptoms after diagnosis. Patients input changes in their physical condition and symptoms after diagnosis.

[1259] 6. Database update means: This module updates the database to improve diagnostic accuracy based on collected feedback data. It uses machine learning algorithms to analyze the data and update the database.

[1260] 7. Automatic medical record generation method: This is an AI method for automatically generating medical records based on diagnostic data. The generated medical records are automatically registered in the medical system and made accessible to doctors.

[1261] Specific examples

[1262] For example, if the user inputs "I have a stomachache and feel sick," the system proceeds as follows:

[1263] The user enters the symptoms into the input page and submits it.

[1264] The terminal sends the transmitted data to the server.

[1265] The server passes the data to the data analysis module.

[1266] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[1267] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[1268] The information provision module provides the user with information on the most suitable doctor.

[1269] The user is examined and provides feedback after the diagnosis.

[1270] The feedback collection module sends the data to a server.

[1271] A database update module updates the database based on the feedback data.

[1272] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1273] An example of a specific prompt sentence is, "I have a stomachache and feel sick." Based on this input, the generative AI converts it into specific medical terms such as "stomachache" and "nausea."

[1274] The above is a specific embodiment for carrying out the present invention, which clarifies the patient's vague symptoms, enables prompt guidance to the most appropriate doctor, improves diagnostic accuracy, and reduces the workload of medical professionals.

[1275] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1276] Step 1:

[1277] Displaying the symptom entry page

[1278] The server generates a web page for the patient to enter their symptoms. The page contains a text field where the patient can enter their symptoms and a submit button. The generated HTML and CSS files are prepared.

[1279] The server transmits the generated web page to the terminal.

[1280] The device then displays the received web page in the user's browser, allowing the user to enter their symptoms. The input is free-form text, using everyday language to describe physical problems.

[1281] Step 2:

[1282] Enter and submit symptom data

[1283] The user enters details of the symptom into the input fields and clicks the submit button.

[1284] The device sends the entered data to the server via an Ajax request, which is packaged in JSON format.

[1285] Step 3:

[1286] Symptom data analysis

[1287] The server passes the received symptom data to the analysis module, where the input data is the patient's free-form text.

[1288] The generative AI analyzes the received text data using a natural language processing algorithm (for example, the BERT model or GPT-3). Through this analysis, it converts vague expressions such as "my stomach hurts" or "I feel sick" into specific medical terms such as "stomachache" or "nausea." The processing results are output as a list of specific medical terms.

[1289] The server receives the analysis results and passes them on to the next processing step.

[1290] Step 4:

[1291] Selection of the best doctor

[1292] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The input data is a list of analyzed specific medical terms.

[1293] The doctor selection module searches the database based on this list, generates a list of multiple doctors who are most suitable for the patient's symptoms, and outputs the list of appropriate doctors as the search results.

[1294] The server receives the output data from the physician selection module and passes it on to the next processing step.

[1295] Step 5:

[1296] Providing doctor information

[1297] The server passes the generated list of doctors to the information providing module, and the input data is the list of doctors.

[1298] The information provision module generates an interface to provide to the user, creating a web page containing information such as the selected doctor's name, specialty, and available dates and times.

[1299] The server sends this information to the terminal and displays it in the user's browser.

[1300] Step 6:

[1301] Making an appointment

[1302] The user selects the doctor of their choice from the provided list and makes an appointment.

[1303] The device sends the selected doctor and appointment information to the server, which also packages this data in JSON format.

[1304] The server stores the received reservation information in a database and returns a reservation confirmation page to the user.

[1305] Step 7:

[1306] Collecting diagnostic feedback

[1307] After the consultation, the user enters the progress of symptoms and feedback into the feedback collection module.

[1308] The device sends the input feedback data to the server, including any changes in symptoms after diagnosis and any new abnormalities noticed.

[1309] Step 8:

[1310] Sending feedback data

[1311] The server passes the received feedback data to the database update module, and the input data is the specific feedback information.

[1312] The database update module analyzes the feedback data and updates the database using algorithms to improve diagnostic accuracy.

[1313] Step 9:

[1314] Automatic generation of medical records

[1315] The server sends the diagnosis data to the automatic medical record generation module. The input data is the diagnosis results and prescription information.

[1316] The AI ​​automatically generates a medical record based on the received data, which includes the patient's symptoms, diagnosis, prescriptions, and more.

[1317] The automatic medical record generation module registers the generated medical records in the medical system, making them accessible to doctors.

[1318] The above are the specific processing steps and functions of the system. This process clarifies the patient's vague symptoms, enabling prompt guidance to the most appropriate doctor and improving diagnostic accuracy.

[1319] (Application example 1)

[1320] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1321] In today's medical field, it remains difficult for patients to accurately communicate vague symptoms they experience to medical professionals and receive optimal treatment. Much effort is also spent on selecting doctors, creating medical records, and collecting feedback to improve diagnostic accuracy. Online medical services, in particular, require systems that can convert vague symptoms entered by patients into concrete medical terms and provide optimal treatment.

[1322] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1323] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on data at the time of the diagnosis; a means for the symptom input means to use a smartphone or smart glasses; and a means for inputting a prompt sentence to the generating AI model to convert the symptoms into specific medical terms. By converting vague symptoms into specific medical terms and inputting them, the server can guide the patient to the optimal doctor, improving diagnostic accuracy and automatically generating medical records.

[1324] "Means for patients to input vague symptoms" refers to an interface that allows patients to input vague symptoms via text or voice.

[1325] "Generative AI means for analyzing symptoms and converting the results into specific medical terms" refers to a device or program that uses artificial intelligence technology to analyze inputted vague symptoms and convert them into specific medical terms.

[1326] "Means for selecting the best doctor" refers to a method or device for selecting the doctor most suitable for a patient based on analyzed symptom data.

[1327] "Means for providing information about the selected physician to the patient" refers to a method or interface for transmitting information about the selected physician to the patient.

[1328] "Means for inputting feedback on the progression of symptoms after diagnosis" refers to an interface for inputting the symptoms and condition of a patient after diagnosis.

[1329] The term "database updating means for improving diagnostic accuracy based on feedback data" refers to a method or device for updating a database based on collected feedback data to improve diagnostic accuracy.

[1330] "Generative AI means for automatically generating medical records based on data at the time of diagnosis" refers to artificial intelligence technology for automatically creating medical records using data collected at the time of diagnosis.

[1331] "Means in which symptom input means uses a smartphone or smart glasses" refers to a method or device that allows patients to input vague symptoms using a smartphone or smart glasses.

[1332] "Means for inputting prompt sentences to a generative AI model" refers to a method or device for providing input sentences (prompt sentences) to a generative AI for analysis.

[1333] This system allows patients to input vague symptoms, converts them into specific medical terms, and guides them to the most appropriate doctor. It also collects post-diagnosis feedback to improve diagnostic accuracy and automatically generates medical records based on medical data. This system achieves these functions using a generative AI model.

[1334] First, the patient inputs their symptoms using a smartphone or smart glasses. The user enters vague symptoms into an input page and submits them. The device then sends the input data to the server. The server passes the received data to a data analysis module, where the generative AI analyzes the symptom data and converts it into specific medical terms. For example, if a patient inputs "I have a stomachache and feel sick," the generative AI will analyze this as "stomachache" and "nausea."

[1335] Next, the server selects the most suitable doctor based on the analysis results. The doctor selection module uses this analysis result to generate a list of the most suitable doctors. The information provision module then provides the user with information on the most suitable doctors. The user then selects the doctor they wish to see from the provided list and makes an appointment.

[1336] To input the progress of symptoms after diagnosis as feedback, the user inputs progress information into a feedback collection module. The terminal transmits the feedback data to a server, and the server passes the received feedback data to a database update module. The database update module updates the database based on this collected data to improve diagnostic accuracy.

[1337] Finally, a medical record is automatically generated based on the data at the time of diagnosis. The server sends the data at the time of diagnosis to the automatic medical record generation module. The generation AI automatically generates a medical record based on the sent data, registers it in the medical system, and makes it accessible to doctors.

[1338] This system is realized using the following specific hardware and software: Hardware includes a smartphone, smart glasses, a server, a user terminal, etc. Software includes a generative AI model (e.g., OpenAI API), a web browser, a data analysis module, a doctor selection module, an information provision module, a feedback collection module, a database update module, and an automatic medical record generation module.

[1339] For example, some examples of prompts to input to a generative AI model include:

[1340] "Please translate the following symptoms into specific medical terms: I have a stomach ache and feel sick."

[1341] This will create a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy.

[1342] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1343] Step 1:

[1344] The user inputs vague symptoms using a smartphone or smart glasses. The input vague symptoms might be, for example, "My stomach hurts and I feel sick." The device then sends the input data to the server.

[1345] Step 2:

[1346] The server passes the received data to the data analysis module, which sends a prompt to the generative AI model based on the vague symptoms entered. The prompt is, "Please translate the following symptoms into concrete medical terms: I have a stomachache and feel sick."

[1347] Step 3:

[1348] The generative AI model analyzes symptom data based on the prompt sentence. Specifically, it converts "I have a stomachache and feel sick" into specific medical terms such as "stomachache" and "nausea." The server receives the analysis results from the generative AI model.

[1349] Step 4:

[1350] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The doctor selection module lists doctors suited to the specialty based on the analysis results, such as "stomach pain" or "nausea." This allows the most suitable doctor to be selected.

[1351] Step 5:

[1352] The server uses the information provision module to provide the user with information about the selected doctors. Based on this information, the user can select the doctor they wish to see and make an appointment online.

[1353] Step 6:

[1354] After the diagnosis, the user inputs feedback about the results of the diagnosis and treatment into the feedback collection module, and the terminal transmits the feedback data to the server.

[1355] Step 7:

[1356] The server passes the received feedback data to a database update module, which analyzes the feedback data and updates the database to improve diagnostic accuracy.

[1357] Step 8:

[1358] When automatically generating a medical record based on diagnostic data, the server sends the data to the automatic medical record generation module. The generation AI automatically generates a medical record based on the diagnostic data sent. The generated medical record is registered in the medical system and made accessible to doctors.

[1359] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1360] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses generative AI to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[1361] System Configuration

[1362] The system consists of the following main components:

[1363] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[1364] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[1365] 3. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[1366] 4. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[1367] 5. Information provision module: A module that provides patients with information about selected doctors.

[1368] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[1369] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[1370] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[1371] Program processing

[1372] Displaying the symptom entry page

[1373] The server transmits a web page to the user's terminal for the patient to input symptoms.

[1374] The terminal displays the received web page in the browser and makes it ready for input.

[1375] Symptom data analysis

[1376] The user enters symptoms such as "stomach ache" or "feeling sick" into the input form.

[1377] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expression or voice and transmits the emotion data to the server.

[1378] The server passes the input symptom data and emotion data to the data analysis module.

[1379] The generative AI analyzes symptom data and converts it into specific medical terms (e.g., "stomach pain" or "nausea"), and also analyzes emotional data to use as auxiliary information for diagnosis.

[1380] The server sends the analysis results to the physician selection module.

[1381] Selection and guidance of the most suitable doctor

[1382] The doctor selection module lists multiple doctors who are best suited to the patient's condition based on specific medical terms and emotional data.

[1383] The server passes the list of optimal doctors to the information providing module and displays it to the user (patient).

[1384] Collecting diagnostic feedback

[1385] After the diagnosis, the user uses the feedback collection module to input the diagnosis results and the subsequent progress of symptoms.

[1386] The terminal transmits the input feedback data to the server.

[1387] The server passes the received feedback data to the database update module.

[1388] The database update module updates the database to improve diagnostic accuracy based on the feedback data.

[1389] Automatic generation of medical records

[1390] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1391] The generation AI automatically generates medical records based on the data sent.

[1392] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[1393] Specific examples

[1394] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[1395] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[1396] The terminal transmits the input data and emotion data to the server.

[1397] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[1398] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[1399] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[1400] The user is examined and provides feedback after the diagnosis.

[1401] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[1402] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1403] The above is a specific embodiment for carrying out the present invention. The present invention is a system that performs analysis based on symptom and emotion data, recommends the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[1404] The processing flow will be explained below.

[1405] Step 1:

[1406] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[1407] Step 2:

[1408] The server sends the HTML file of the symptom input page to the user's terminal.

[1409] Step 3:

[1410] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[1411] Step 4:

[1412] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form.

[1413] Step 5:

[1414] The emotion engine operates to collect and analyze facial expression or voice data while the user is inputting symptoms to generate emotion data.

[1415] Step 6:

[1416] The terminal transmits the input symptom data and emotion data to the server.

[1417] Step 7:

[1418] The server passes the received symptom data and emotion data to a data analysis module.

[1419] Step 8:

[1420] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea." It also analyzes emotional data and uses it as diagnostic aids.

[1421] Step 9:

[1422] The server transmits data to the doctor selection module based on the analysis results and emotion data.

[1423] Step 10:

[1424] The doctor selection module lists multiple doctors who are best suited to the patient's symptoms based on specific medical terms and emotional data, and selects the doctor who can provide the appropriate treatment for the patient, taking into account the emotional data.

[1425] Step 11:

[1426] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[1427] Step 12:

[1428] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[1429] Step 13:

[1430] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[1431] Step 14:

[1432] The terminal transmits information about the doctor selected by the user to the server.

[1433] Step 15:

[1434] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[1435] Step 16:

[1436] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[1437] Step 17:

[1438] The terminal transmits the input feedback data to the server.

[1439] Step 18:

[1440] The server passes the received feedback data to the database update module.

[1441] Step 19:

[1442] The database update module updates the database to improve diagnostic accuracy based on the feedback data and emotion data.

[1443] Step 20:

[1444] The server transmits the emotion data together with the diagnostic data and feedback data to the automatic medical record generation module.

[1445] Step 21:

[1446] The generation AI automatically generates medical records based on the data sent.

[1447] Step 22:

[1448] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[1449] Example 2

[1450] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1451] Conventional medical systems have had problems leading to accurate diagnoses because patients are unable to clearly describe their symptoms or emotional information is not taken into account. Furthermore, the selection of doctors, improving diagnostic accuracy, and recording medical records are all largely manual and inefficient. This places a heavy burden on both doctors and patients.

[1452] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the patient to input vague symptoms, an emotion engine means for recognizing emotions at the time of symptom input, a generation AI means for analyzing symptoms and converting the results into specific medical terms, a means for selecting an optimal doctor based on the analysis results and emotion data, a means for providing the patient with information on the selected doctor, a means for inputting the progress of symptoms after the diagnosis as feedback, a database update means for improving diagnostic accuracy based on the feedback data, and a generation AI means for automatically generating a medical record based on data at the time of diagnosis. This enables accurate diagnosis based on the patient's vague symptoms and emotion data, selection of an optimal doctor, improvement of diagnostic accuracy, and automatic generation of a medical record.

[1453] A "patient" is a person who receives diagnosis or treatment at a medical institution.

[1454] "Vague symptoms" are physical or mental abnormalities that patients describe without using specific medical or technical terms.

[1455] An "emotion engine" is software or hardware that analyzes a patient's facial expressions and voice and recognizes their emotional state.

[1456] "Generative AI" is a type of artificial intelligence that uses machine learning algorithms to analyze input data and output the results.

[1457] "Specific medical terms" are medically standardized terminology used for diagnosis and treatment.

[1458] A "doctor selection tool" is software or an algorithm that has the function of selecting an appropriate doctor based on the patient's symptoms and emotional data.

[1459] "Information providing means" refers to an interface or system for providing information about selected doctors to patients.

[1460] A "feedback collection means" is an interface or system for collecting information from a patient about the progress of their symptoms after diagnosis.

[1461] The "database update means" is software or algorithm that has the function of updating the database based on collected feedback data and improving diagnostic accuracy.

[1462] The "automatic medical record generation means" is a system that uses generation AI to automatically create medical records based on diagnostic data and feedback data.

[1463] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses a generative AI model to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[1464] System Configuration

[1465] The system consists of the following main components:

[1466] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[1467] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[1468] 3. Data analysis module: A module that analyzes input symptom data using a generative AI model and converts it into specific medical terms.

[1469] 4. Doctor selection module: A module that selects the most suitable doctor based on analysis results and emotional data.

[1470] 5. Information provision module: A module that provides patients with information about selected doctors.

[1471] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[1472] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[1473] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[1474] Program processing

[1475] Displaying the symptom entry page

[1476] The server sends a web page to the user's device, where the patient can enter their symptoms. This web page is composed of HTML and JavaScript and includes an input form, information fields, and a script for collecting emotion data.

[1477] The device displays the received web page in the browser, allowing the user to input symptoms. At the same time, the emotion engine is initialized.

[1478] Symptom data input and sentiment analysis

[1479] Users enter symptoms such as "stomach ache" or "feeling sick" into an input form. They can also provide additional information using a voice input function.

[1480] The device collects input symptom data in real time and simultaneously captures the patient's facial expressions and voice using a camera and microphone, which are then analyzed by an emotion engine.

[1481] The terminal transmits the collected symptom data and emotion data to the server.

[1482] Symptom and emotion data analysis

[1483] The server passes the received symptom data and emotion data to a data analysis module.

[1484] The generative AI model converts symptom data into specific medical terms and analyzes emotional data to generate diagnostic aids.

[1485] The server sends the analysis results and emotion data to the doctor selection module.

[1486] Selection and guidance of the most suitable doctor

[1487] The doctor selection module lists multiple optimal doctors based on the analysis results and emotional data.

[1488] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[1489] The information providing module displays the list to the user and prompts the user to make a selection.

[1490] Collecting diagnostic feedback

[1491] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[1492] The terminal transmits the input feedback data to the server.

[1493] The server sends the received feedback data to the database update module.

[1494] The database update module updates the database based on the feedback data to improve diagnostic accuracy.

[1495] Automatic generation of medical records

[1496] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1497] The generative AI model automatically generates medical records based on the submitted data.

[1498] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[1499] Specific examples

[1500] For example, if the user inputs "my stomach hurts and I feel sick" as a symptom, the process proceeds as follows:

[1501] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[1502] The terminal transmits the input data and emotion data to the server.

[1503] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[1504] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[1505] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[1506] The user is examined and provides feedback after the diagnosis.

[1507] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[1508] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1509] Prompt Sentence Examples

[1510] 1. "Please convert the patient's symptom, 'I have a stomachache and feel sick,' into medical terms. Furthermore, please analyze the patient's emotional data and use it as diagnostic support information."

[1511] 2. "Automatically generate a medical record based on the diagnosis and feedback."

[1512] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1513] Step 1: Display the symptom entry page

[1514] The server sends a symptom input page composed of HTML and JavaScript to devices that access a specific URL. The input page includes a symptom input form and a script for collecting emotional data.

[1515] The device renders the received HTML and JavaScript in the browser, allowing the patient to enter their symptoms. When the input page is displayed, the emotion engine is also initialized.

[1516] Input: URL visited by patient

[1517] Output: A browser showing the symptom entry page

[1518] Step 2: Symptom data input and sentiment analysis

[1519] The user enters symptoms such as "stomach ache" or "feeling sick" into the form on the symptom input page, and provides additional information using the voice input function as needed.

[1520] The device collects input symptom data in real time and uses a camera and microphone to capture the patient's facial expressions and voice data, which are then analyzed by an emotion engine.

[1521] The terminal combines the collected symptom data and emotion data into a single data packet and transmits it to the server.

[1522] Input: Symptom data entered by the patient, captured facial and voice data

[1523] Output: Symptom data and emotion data sent to the server

[1524] Step 3: Analyze symptom and emotion data

[1525] The server passes the received symptom data and emotion data to a data analysis module.

[1526] The generative AI model converts symptom data into specific medical terms such as "stomach pain" or "nausea," and also analyzes emotion data to generate diagnostic support information.

[1527] The server sends the generated medical terms and the results of the sentiment analysis to the doctor selection module.

[1528] Input: Symptom data and emotion data received by the server

[1529] Output: Analysis results with specific medical terms and supporting information

[1530] Step 4: Selecting and recommending the best doctor

[1531] The doctor selection module uses the analysis results and emotional data to create a list of multiple doctors best suited to the patient's symptoms.

[1532] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[1533] The information providing module displays a list of doctors on the user's browser and prompts the user to select the doctor they wish to see.

[1534] Input: Analysis results, emotional data, doctor information

[1535] Output: A list of doctors displayed to the user

[1536] Step 5: Collect diagnostic feedback

[1537] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[1538] The terminal transmits the input feedback data to the server.

[1539] The server passes the received feedback data to a database update module to update the database.

[1540] Input: User-entered feedback data

[1541] Output: Feedback data updated in the database

[1542] Step 6: Automatic generation of medical records

[1543] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1544] The generative AI model automatically generates detailed medical records based on the submitted data.

[1545] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[1546] Input: Diagnostic data, feedback data

[1547] Output: Medical records registered in the medical system

[1548] (Application example 2)

[1549] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1550] In conventional medical systems, it is difficult for patients to clearly communicate their symptoms and there is a lack of means to recognize their emotional state, making it difficult to make an appropriate diagnosis. Furthermore, many tasks, such as selecting the appropriate doctor, collecting feedback after diagnosis, and automatically generating medical records, are performed manually, placing a heavy burden on medical professionals. This leads to issues such as reduced diagnostic accuracy and worsening work efficiency.

[1551] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1552] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting the most appropriate doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the data at the time of the diagnosis; a means including an emotion engine for analyzing the patient's facial expressions or voice and recognizing emotional data; a means for inputting symptoms via a smartphone application and analyzing them together with the emotional data; and a means for listing and providing the most appropriate doctors for the application. This allows for a more accurate understanding of a patient's vague symptoms and emotional state, enabling the selection of an appropriate doctor, improving diagnostic accuracy, and enabling the automatic generation of medical records and the collection of feedback to be performed efficiently.

[1553] A "patient" is a person who seeks medical examination or treatment from a medical institution.

[1554] "Symptoms" refer to signs or conditions of a disease or abnormality that a patient is aware of.

[1555] "Input" is the act of providing information or data to a system.

[1556] "Generative AI" uses artificial intelligence techniques to analyze data and automatically generate specific results.

[1557] "Analysis" is the act of breaking down data or information and analyzing its contents in detail.

[1558] "Medical terminology" refers to specialized words and expressions related to medicine and health.

[1559] "Selection" is the act of choosing the best option from among many candidates.

[1560] A "physician" is a medical professional who has medical expertise and qualifications and who provides medical examinations and treatment.

[1561] "Information" refers to content such as knowledge and data.

[1562] "Providing" is the act of giving something that is needed to someone else.

[1563] "Diagnosis" is the medical procedure for identifying a patient's illness or abnormality.

[1564] "Feedback" is the act of giving a reaction or opinion to a certain action or result.

[1565] A "database" is a system that systematically collects and centrally manages a large amount of data.

[1566] "Update" is the act of changing existing information or data into new information or data.

[1567] A "medical record" is a document that compiles records and data related to a patient's medical treatment.

[1568] "Emotion engine" refers to technology that recognizes a patient's emotional state from their facial expressions and voice.

[1569] A "smartphone application" is software that runs on a smartphone.

[1570] "Listing" is the act of presenting suitable options from a number of options in list form.

[1571] A "system" is a system in which interrelated parts and elements are combined to perform a specific function.

[1572] This invention relates to a system that improves diagnostic accuracy by allowing patients to input vague symptoms using a smartphone application and even recognizing their emotions at the time of input. This system has the function of analyzing symptoms using a generative AI model and automatically generating medical records. It also allows for continuous improvement of diagnostic accuracy through feedback.

[1573] System Configuration

[1574] The system consists of the following main components:

[1575] 1. Symptom input method

[1576] This is an interface for patients to input their vague symptoms. This interface uses a smartphone application.

[1577] 2. Emotion Engine

[1578] The system analyzes the patient's facial expressions and voice when entering symptoms and recognizes emotional data, using Google Cloud Vision and IBM Watson's emotion analysis API.

[1579] 3. Data Analysis Module

[1580] It uses a generative AI model, such as OpenAI's GPT-4, that analyzes input symptom and emotion data and converts the results into specific medical terms.

[1581] 4. Doctor Selection Module

[1582] This module lists the most suitable doctors based on the analysis results. It is built using Python and utilizes libraries such as SciPy and TensorFlow.

[1583] 5. Information Module

[1584] This module provides patients with information about selected doctors. The information is presented through a smartphone application interface.

[1585] 6. Feedback Collection Module

[1586] This module collects feedback from patients about the progress of their symptoms after diagnosis. The collected feedback data is sent to the server.

[1587] 7. Database Update Module

[1588] This module periodically updates the database to improve diagnostic accuracy based on feedback data.

[1589] 8. Automatic medical record generation module

[1590] It uses a generative AI model that automatically generates medical records based on diagnostic data and feedback data, and the generated medical records are registered in the medical system and made accessible to doctors.

[1591] Program processing

[1592] Displaying the symptom entry page

[1593] The server generates a web page or smartphone application interface for patients to enter their symptoms and sends it to the user's device.

[1594] The terminal displays the received interface and makes it possible for the patient to input information.

[1595] Symptom data analysis

[1596] Users use a smartphone application to input symptoms such as "stomach ache" or "nausea."

[1597] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expressions or voice, and also transmits the emotion data to the server.

[1598] The server passes this data to a data analysis module, where a generative AI model analyzes it and converts it into specific medical terms.

[1599] Selection and guidance of the most suitable doctor

[1600] The doctor selection module lists the most suitable doctors based on medical terminology and emotional data received from the generative AI.

[1601] The server passes this list to the information providing module and displays it to the patient.

[1602] Collecting diagnostic feedback

[1603] Users input their post-diagnosis progress and impressions through a feedback collection module.

[1604] The terminal transmits this feedback data to the server.

[1605] The server passes the received feedback data to a database update module to update the database.

[1606] Automatic generation of medical records

[1607] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1608] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[1609] Specific examples

[1610] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[1611] The user enters symptoms into a smartphone application, and the emotion engine simultaneously analyzes emotional data from facial expressions and voice.

[1612] The terminal transmits the input symptom data and emotion data to the server.

[1613] The server passes the data to a data analysis module, where a generative AI model converts the data into specific medical terms.

[1614] The server sends the analysis results to the doctor selection module, which generates a list of the most suitable doctors.

[1615] The information provision module provides the list to the patient, who then schedules an appointment.

[1616] After the patient is seen, feedback is collected and sent to the server.

[1617] The database update module updates the database to improve diagnostic accuracy.

[1618] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1619] Prompt Sentence Examples

[1620] Patient's stated symptoms: Stomach pain, feeling sick

[1621] Emotional data: sad facial expression, nervous voice

[1622] Translate the symptoms into specific medical terms and list the doctors who are suitable for the patient.

[1623] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1624] Step 1:

[1625] Display of symptom entry screen

[1626] The server generates a web page or smartphone application interface for patients to enter their symptoms.

[1627] The server sends this interface to the user's terminal, which displays the received interface.

[1628] As a result, the patient is ready to enter their symptoms.

[1629] Step 2:

[1630] Symptom entry and emotional data collection

[1631] Users input their symptoms (e.g., "I have a stomachache" or "I feel sick") using the smartphone application interface.

[1632] At the same time, the emotion engine analyzes emotion data using video and audio data input from the device's camera and microphone.

[1633] The terminal transmits the collected symptom data and emotion data to a server.

[1634] Input data: Symptoms (text), emotion data (voice, facial expression)

[1635] Output data: Symptom data, emotion data

[1636] Step 3:

[1637] Data analysis

[1638] The server passes the received symptom data and emotion data to a data analysis module.

[1639] The data analysis module uses a generative AI model (e.g., GPT-4) to analyze this data and translate vague symptoms into concrete medical terms.

[1640] Input data: symptom data, emotion data

[1641] Output data: Data converted into medical terms

[1642] Step 4:

[1643] Doctor Selection

[1644] The server passes the specific medical terms obtained from the data analysis module to the physician selection module.

[1645] The doctor selection module uses libraries such as Python, SciPy, and TensorFlow to list the most suitable doctors based on the analysis results.

[1646] Input data: Data converted into medical terms

[1647] Output data: List of best doctors

[1648] Step 5:

[1649] Providing optimal doctor information

[1650] The server passes the list of optimal doctors obtained from the doctor selection module to the information providing module.

[1651] The information provision module provides this list to the patient through the smartphone application interface.

[1652] Input data: List of best doctors

[1653] Output data: Optimal doctor information displayed to the patient

[1654] Step 6:

[1655] Collecting diagnostic feedback

[1656] Users enter information about the progression of symptoms after diagnosis and their evaluation of the diagnostic results through the feedback collection module of the smartphone application.

[1657] The terminal transmits the feedback data to the server.

[1658] Input data: Feedback data

[1659] Output data: Feedback data sent to the server

[1660] Step 7:

[1661] Database Update

[1662] The server passes the received feedback data to the database update module.

[1663] The database update module updates the database based on this data to improve diagnostic accuracy.

[1664] Input data: Feedback data

[1665] Output data: Updated database

[1666] Step 8:

[1667] Automatic generation of medical records

[1668] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1669] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[1670] Input data: diagnostic data, feedback data

[1671] Output data: Automatically generated medical records

[1672] 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.

[1673] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1674] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1675] [Fourth embodiment]

[1676] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1677] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1678] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1679] 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.

[1680] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1681] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1682] 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.

[1683] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1684] 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.

[1685] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1686] 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.

[1687] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1688] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1689] This invention is a system that allows patients to input vague symptoms, converts them into specific medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses generative AI to analyze and automatically generate medical records, improving the work efficiency of medical professionals.

[1690] System Configuration

[1691] The system consists of the following main components:

[1692] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[1693] 2. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[1694] 3. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[1695] 4. Information provision module: A module that provides patients with information about selected doctors.

[1696] 5. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[1697] 6. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[1698] 7. Automatic medical record generation module: A generative AI module that automatically generates medical records based on diagnostic data.

[1699] Program processing

[1700] Displaying the symptom entry page

[1701] The server transmits a web page to the user's terminal for the patient to input symptoms.

[1702] The terminal displays the received web page in the browser, allowing the patient to enter their symptoms.

[1703] Symptom data analysis

[1704] The user enters the symptoms into the input page and presses the send button.

[1705] The terminal transmits the input data to the server.

[1706] The server passes the received data to the data analysis module.

[1707] The generative AI analyzes symptom data and converts it into specific medical terms such as "stomachache," "pain in the lower right abdomen," and "nausea."

[1708] The server passes the data to the doctor selection module based on the analysis results.

[1709] Selection and guidance of the most suitable doctor

[1710] The server generates a list of the most suitable doctors based on the analysis results and passes the data to the information providing module.

[1711] The information providing module provides the user with information on the most suitable doctor.

[1712] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[1713] Collecting diagnostic feedback

[1714] The user enters post-diagnosis feedback into a feedback collection module.

[1715] The terminal transmits the feedback data to the server.

[1716] The server passes the received feedback data to the database update module.

[1717] The database update module updates the database based on the collected data to improve diagnostic accuracy.

[1718] Automatic generation of medical records

[1719] The server transmits the diagnostic data to the automatic medical record generation module.

[1720] The generation AI automatically generates medical records based on the data sent.

[1721] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[1722] Specific examples

[1723] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[1724] The user enters the symptoms into the input page and submits it.

[1725] The terminal sends the transmitted data to the server.

[1726] The server passes the data to the data analysis module.

[1727] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[1728] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[1729] The information provision module provides the user with information on the most suitable doctor.

[1730] The user is examined and provides feedback after the diagnosis.

[1731] The feedback collection module sends the data to a server.

[1732] A database update module updates the database based on the feedback data.

[1733] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1734] The above is a specific embodiment for carrying out the present invention. The present invention is a system that specifically analyzes vague symptoms, guides patients to the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[1735] The processing flow will be explained below.

[1736] Step 1:

[1737] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[1738] Step 2:

[1739] The server sends the HTML file of the symptom input page to the user's terminal.

[1740] Step 3:

[1741] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[1742] Step 4:

[1743] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form and presses the send button.

[1744] Step 5:

[1745] The terminal transmits the symptom data entered by the user to the server.

[1746] Step 6:

[1747] The server passes the received symptom data to the data analysis module.

[1748] Step 7:

[1749] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea."

[1750] Step 8:

[1751] Based on the analysis results from the generation AI, the server sends information to the doctor selection module to select the most suitable doctor.

[1752] Step 9:

[1753] The doctor selection module lists multiple doctors suitable for the patient's condition based on specific medical terms.

[1754] Step 10:

[1755] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[1756] Step 11:

[1757] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[1758] Step 12:

[1759] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[1760] Step 13:

[1761] The terminal transmits information about the doctor selected by the user to the server.

[1762] Step 14:

[1763] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[1764] Step 15:

[1765] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[1766] Step 16:

[1767] The terminal transmits the input feedback data to the server.

[1768] Step 17:

[1769] The server passes the received feedback data to the database update module.

[1770] Step 18:

[1771] The database update module updates the database based on the feedback data to improve the accuracy of the diagnosis.

[1772] Step 19:

[1773] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1774] Step 20:

[1775] The generation AI automatically generates medical records based on the data sent.

[1776] Step 21:

[1777] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[1778] Example 1

[1779] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1780] In conventional medical systems, the symptoms entered by patients were often vague, resulting in an inefficient diagnosis process. It was also difficult for patients to accurately communicate their symptoms to doctors, which could delay the process of finding the most appropriate doctor. Furthermore, there was also the problem that feedback after diagnosis was not collected, preventing improvements in diagnostic accuracy. This increased the burden on medical professionals and reduced patient satisfaction.

[1781] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1782] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of the symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the diagnostic data; a means for transferring the received data to an analysis module and converting it into specific medical terms using a natural language processing algorithm; a means for transmitting data from a user's terminal and communicating with the analysis module to exchange data; a means for generating a list of doctors based on the analysis results and transferring the data to an information provision module; and a means for automatically generating a final medical record and registering it in the medical system. This allows for concretizing a patient's vague symptoms, quickly guiding the patient to the optimal doctor, and improving diagnostic accuracy.

[1783] "Patient" means an individual who uses the System to receive medical services.

[1784] "Symptoms" refer to the physical abnormalities or discomforts that a patient experiences.

[1785] The "symptom input means" is an interface that allows patients to input their symptoms into the system.

[1786] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform predetermined transformations.

[1787] "Generative AI means" refers to means that use artificial intelligence technology to analyze symptom data and convert it into specific medical terms.

[1788] "Analysis results" are data containing specific medical terms converted by the generating AI means.

[1789] The "doctor selection means" is a means for selecting the most suitable doctor based on the analysis results.

[1790] The "information provision means" is a means for providing information about the selected doctor to the patient.

[1791] The "feedback input means" is a means for the patient to input the progress of symptoms after diagnosis.

[1792] "Feedback data" refers to information entered by the patient regarding the progression of symptoms after diagnosis.

[1793] The "database updating means" is a means for updating the database based on feedback data and improving diagnostic accuracy.

[1794] The "automatic medical record generation means" is a means for automatically generating a medical record based on data at the time of diagnosis.

[1795] The "analysis module" is a module for processing received symptom data and converting it into specific medical terms.

[1796] A "natural language processing algorithm" is an algorithm for understanding and processing human language.

[1797] A "user terminal" is a device used by a patient to enter symptoms and provide feedback.

[1798] The "information provision module" is a module for providing patients with information on the most suitable doctor.

[1799] A "database" is a structure for centrally managing and storing data used throughout the system.

[1800] This invention is a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy through post-diagnosis feedback. This system uses a generative AI model to perform analysis and automatically generate medical records, improving the work efficiency of medical professionals. The system includes the following main components:

[1801] System Configuration

[1802] 1. Symptom input tool: A web browser-based interface for patients to input their symptoms. Patients can input physical problems using everyday language.

[1803] 2. Generative AI: A generative AI that analyzes inputted vague symptoms and converts them into specific medical terms. Specifically, it uses natural language processing algorithms such as the BERT model and GPT-3.

[1804] 3. Doctor Selection Means: This is a module that selects the most suitable doctor based on the results analyzed by the Generative AI Means. This module searches for an appropriate doctor from the database.

[1805] 4. Information provision method: An interface for providing patients with information about selected doctors. This is done via a web browser or mobile application.

[1806] 5. Feedback input means: An interface for inputting feedback on the progress of symptoms after diagnosis. Patients input changes in their physical condition and symptoms after diagnosis.

[1807] 6. Database update means: This module updates the database to improve diagnostic accuracy based on collected feedback data. It uses machine learning algorithms to analyze the data and update the database.

[1808] 7. Automatic medical record generation method: This is an AI method for automatically generating medical records based on diagnostic data. The generated medical records are automatically registered in the medical system and made accessible to doctors.

[1809] Specific examples

[1810] For example, if the user inputs "I have a stomachache and feel sick," the system proceeds as follows:

[1811] The user enters the symptoms into the input page and submits it.

[1812] The terminal sends the transmitted data to the server.

[1813] The server passes the data to the data analysis module.

[1814] The generative AI analyzes "stomach ache" as "stomachache" and "feeling sick" as "nausea."

[1815] Based on the analysis results, the server generates a list of the most suitable doctors using the doctor selection module.

[1816] The information provision module provides the user with information on the most suitable doctor.

[1817] The user is examined and provides feedback after the diagnosis.

[1818] The feedback collection module sends the data to a server.

[1819] A database update module updates the database based on the feedback data.

[1820] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1821] An example of a specific prompt sentence is, "I have a stomachache and feel sick." Based on this input, the generative AI converts it into specific medical terms such as "stomachache" and "nausea."

[1822] The above is a specific embodiment for carrying out the present invention, which clarifies the patient's vague symptoms, enables prompt guidance to the most appropriate doctor, improves diagnostic accuracy, and reduces the workload of medical professionals.

[1823] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1824] Step 1:

[1825] Displaying the symptom entry page

[1826] The server generates a web page for the patient to enter their symptoms. The page contains a text field where the patient can enter their symptoms and a submit button. The generated HTML and CSS files are prepared.

[1827] The server transmits the generated web page to the terminal.

[1828] The device then displays the received web page in the user's browser, allowing the user to enter their symptoms. The input is free-form text, using everyday language to describe physical problems.

[1829] Step 2:

[1830] Enter and submit symptom data

[1831] The user enters details of the symptom into the input fields and clicks the submit button.

[1832] The device sends the entered data to the server via an Ajax request, which is packaged in JSON format.

[1833] Step 3:

[1834] Symptom data analysis

[1835] The server passes the received symptom data to the analysis module, where the input data is the patient's free-form text.

[1836] The generative AI analyzes the received text data using a natural language processing algorithm (for example, the BERT model or GPT-3). Through this analysis, it converts vague expressions such as "my stomach hurts" or "I feel sick" into specific medical terms such as "stomachache" or "nausea." The processing results are output as a list of specific medical terms.

[1837] The server receives the analysis results and passes them on to the next processing step.

[1838] Step 4:

[1839] Selection of the best doctor

[1840] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The input data is a list of analyzed specific medical terms.

[1841] The doctor selection module searches the database based on this list, generates a list of multiple doctors who are most suitable for the patient's symptoms, and outputs the list of appropriate doctors as the search results.

[1842] The server receives the output data from the physician selection module and passes it on to the next processing step.

[1843] Step 5:

[1844] Providing doctor information

[1845] The server passes the generated list of doctors to the information providing module, and the input data is the list of doctors.

[1846] The information provision module generates an interface to provide to the user, creating a web page containing information such as the selected doctor's name, specialty, and available dates and times.

[1847] The server sends this information to the terminal and displays it in the user's browser.

[1848] Step 6:

[1849] Making an appointment

[1850] The user selects the doctor of their choice from the provided list and makes an appointment.

[1851] The device sends the selected doctor and appointment information to the server, which also packages this data in JSON format.

[1852] The server stores the received reservation information in a database and returns a reservation confirmation page to the user.

[1853] Step 7:

[1854] Collecting diagnostic feedback

[1855] After the consultation, the user enters the progress of symptoms and feedback into the feedback collection module.

[1856] The device sends the input feedback data to the server, including any changes in symptoms after diagnosis and any new abnormalities noticed.

[1857] Step 8:

[1858] Sending feedback data

[1859] The server passes the received feedback data to the database update module, and the input data is the specific feedback information.

[1860] The database update module analyzes the feedback data and updates the database using algorithms to improve diagnostic accuracy.

[1861] Step 9:

[1862] Automatic generation of medical records

[1863] The server sends the diagnosis data to the automatic medical record generation module. The input data is the diagnosis results and prescription information.

[1864] The AI ​​automatically generates a medical record based on the received data, which includes the patient's symptoms, diagnosis, prescriptions, and more.

[1865] The automatic medical record generation module registers the generated medical records in the medical system, making them accessible to doctors.

[1866] The above are the specific processing steps and functions of the system. This process clarifies the patient's vague symptoms, enabling prompt guidance to the most appropriate doctor and improving diagnostic accuracy.

[1867] (Application example 1)

[1868] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1869] In today's medical field, it remains difficult for patients to accurately communicate vague symptoms they experience to medical professionals and receive optimal treatment. Much effort is also spent on selecting doctors, creating medical records, and collecting feedback to improve diagnostic accuracy. Online medical services, in particular, require systems that can convert vague symptoms entered by patients into concrete medical terms and provide optimal treatment.

[1870] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1871] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting an optimal doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on data at the time of the diagnosis; a means for the symptom input means to use a smartphone or smart glasses; and a means for inputting a prompt sentence to the generating AI model to convert the symptoms into specific medical terms. By converting vague symptoms into specific medical terms and inputting them, the server can guide the patient to the optimal doctor, improving diagnostic accuracy and automatically generating medical records.

[1872] "Means for patients to input vague symptoms" refers to an interface that allows patients to input vague symptoms via text or voice.

[1873] "Generative AI means for analyzing symptoms and converting the results into specific medical terms" refers to a device or program that uses artificial intelligence technology to analyze inputted vague symptoms and convert them into specific medical terms.

[1874] "Means for selecting the best doctor" refers to a method or device for selecting the doctor most suitable for a patient based on analyzed symptom data.

[1875] "Means for providing information about the selected physician to the patient" refers to a method or interface for transmitting information about the selected physician to the patient.

[1876] "Means for inputting feedback on the progression of symptoms after diagnosis" refers to an interface for inputting the symptoms and condition of a patient after diagnosis.

[1877] The term "database updating means for improving diagnostic accuracy based on feedback data" refers to a method or device for updating a database based on collected feedback data to improve diagnostic accuracy.

[1878] "Generative AI means for automatically generating medical records based on data at the time of diagnosis" refers to artificial intelligence technology for automatically creating medical records using data collected at the time of diagnosis.

[1879] "Means in which symptom input means uses a smartphone or smart glasses" refers to a method or device that allows patients to input vague symptoms using a smartphone or smart glasses.

[1880] "Means for inputting prompt sentences to a generative AI model" refers to a method or device for providing input sentences (prompt sentences) to a generative AI for analysis.

[1881] This system allows patients to input vague symptoms, converts them into specific medical terms, and guides them to the most appropriate doctor. It also collects post-diagnosis feedback to improve diagnostic accuracy and automatically generates medical records based on medical data. This system achieves these functions using a generative AI model.

[1882] First, the patient inputs their symptoms using a smartphone or smart glasses. The user enters vague symptoms into an input page and submits them. The device then sends the input data to the server. The server passes the received data to a data analysis module, where the generative AI analyzes the symptom data and converts it into specific medical terms. For example, if a patient inputs "I have a stomachache and feel sick," the generative AI will analyze this as "stomachache" and "nausea."

[1883] Next, the server selects the most suitable doctor based on the analysis results. The doctor selection module uses this analysis result to generate a list of the most suitable doctors. The information provision module then provides the user with information on the most suitable doctors. The user then selects the doctor they wish to see from the provided list and makes an appointment.

[1884] To input the progress of symptoms after diagnosis as feedback, the user inputs progress information into a feedback collection module. The terminal transmits the feedback data to a server, and the server passes the received feedback data to a database update module. The database update module updates the database based on this collected data to improve diagnostic accuracy.

[1885] Finally, a medical record is automatically generated based on the data at the time of diagnosis. The server sends the data at the time of diagnosis to the automatic medical record generation module. The generation AI automatically generates a medical record based on the sent data, registers it in the medical system, and makes it accessible to doctors.

[1886] This system is realized using the following specific hardware and software: Hardware includes a smartphone, smart glasses, a server, a user terminal, etc. Software includes a generative AI model (e.g., OpenAI API), a web browser, a data analysis module, a doctor selection module, an information provision module, a feedback collection module, a database update module, and an automatic medical record generation module.

[1887] For example, some examples of prompts to input to a generative AI model include:

[1888] "Please translate the following symptoms into specific medical terms: I have a stomach ache and feel sick."

[1889] This will create a system that converts vague symptoms entered by patients into concrete medical terms, guides them to the most appropriate doctor, and improves diagnostic accuracy.

[1890] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1891] Step 1:

[1892] The user inputs vague symptoms using a smartphone or smart glasses. The input vague symptoms might be, for example, "My stomach hurts and I feel sick." The device then sends the input data to the server.

[1893] Step 2:

[1894] The server passes the received data to the data analysis module, which sends a prompt to the generative AI model based on the vague symptoms entered. The prompt is, "Please translate the following symptoms into concrete medical terms: I have a stomachache and feel sick."

[1895] Step 3:

[1896] The generative AI model analyzes symptom data based on the prompt sentence. Specifically, it converts "I have a stomachache and feel sick" into specific medical terms such as "stomachache" and "nausea." The server receives the analysis results from the generative AI model.

[1897] Step 4:

[1898] The server passes the data to the doctor selection module to select the most suitable doctor based on the analysis results. The doctor selection module lists doctors suited to the specialty based on the analysis results, such as "stomach pain" or "nausea." This allows the most suitable doctor to be selected.

[1899] Step 5:

[1900] The server uses the information provision module to provide the user with information about the selected doctors. Based on this information, the user can select the doctor they wish to see and make an appointment online.

[1901] Step 6:

[1902] After the diagnosis, the user inputs feedback about the results of the diagnosis and treatment into the feedback collection module, and the terminal transmits the feedback data to the server.

[1903] Step 7:

[1904] The server passes the received feedback data to a database update module, which analyzes the feedback data and updates the database to improve diagnostic accuracy.

[1905] Step 8:

[1906] When automatically generating a medical record based on diagnostic data, the server sends the data to the automatic medical record generation module. The generation AI automatically generates a medical record based on the diagnostic data sent. The generated medical record is registered in the medical system and made accessible to doctors.

[1907] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1908] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses generative AI to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[1909] System Configuration

[1910] The system consists of the following main components:

[1911] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[1912] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[1913] 3. Data analysis module: A module that uses generative AI to analyze input symptom data and convert it into specific medical terms.

[1914] 4. Doctor selection module: A module that selects the most suitable doctor based on the analysis results.

[1915] 5. Information provision module: A module that provides patients with information about selected doctors.

[1916] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[1917] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[1918] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[1919] Program processing

[1920] Displaying the symptom entry page

[1921] The server transmits a web page to the user's terminal for the patient to input symptoms.

[1922] The terminal displays the received web page in the browser and makes it ready for input.

[1923] Symptom data analysis

[1924] The user enters symptoms such as "stomach ache" or "feeling sick" into the input form.

[1925] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expression or voice and transmits the emotion data to the server.

[1926] The server passes the input symptom data and emotion data to the data analysis module.

[1927] The generative AI analyzes symptom data and converts it into specific medical terms (e.g., "stomach pain" or "nausea"), and also analyzes emotional data to use as auxiliary information for diagnosis.

[1928] The server sends the analysis results to the physician selection module.

[1929] Selection and guidance of the most suitable doctor

[1930] The doctor selection module lists multiple doctors who are best suited to the patient's condition based on specific medical terms and emotional data.

[1931] The server passes the list of optimal doctors to the information providing module and displays it to the user (patient).

[1932] Collecting diagnostic feedback

[1933] After the diagnosis, the user uses the feedback collection module to input the diagnosis results and the subsequent progress of symptoms.

[1934] The terminal transmits the input feedback data to the server.

[1935] The server passes the received feedback data to the database update module.

[1936] The database update module updates the database to improve diagnostic accuracy based on the feedback data.

[1937] Automatic generation of medical records

[1938] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[1939] The generation AI automatically generates medical records based on the data sent.

[1940] The automatic medical record generation module registers the generated medical records in the medical system and makes them accessible to doctors.

[1941] Specific examples

[1942] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[1943] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[1944] The terminal transmits the input data and emotion data to the server.

[1945] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[1946] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[1947] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[1948] The user is examined and provides feedback after the diagnosis.

[1949] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[1950] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[1951] The above is a specific embodiment for carrying out the present invention. The present invention is a system that performs analysis based on symptom and emotion data, recommends the most appropriate doctor, improves diagnostic accuracy, and reduces the burden on medical professionals by automatically generating medical records.

[1952] The processing flow will be explained below.

[1953] Step 1:

[1954] The user launches a web browser, enters the URL of the symptom entry page, and accesses it.

[1955] Step 2:

[1956] The server sends the HTML file of the symptom input page to the user's terminal.

[1957] Step 3:

[1958] The terminal displays the received HTML file in a browser and provides a screen where the patient can enter their symptoms.

[1959] Step 4:

[1960] The user enters vague symptoms such as "stomach ache" or "feeling sick" into the input form.

[1961] Step 5:

[1962] The emotion engine operates to collect and analyze facial expression or voice data while the user is inputting symptoms to generate emotion data.

[1963] Step 6:

[1964] The terminal transmits the input symptom data and emotion data to the server.

[1965] Step 7:

[1966] The server passes the received symptom data and emotion data to a data analysis module.

[1967] Step 8:

[1968] The generative AI analyzes symptom data and converts "stomach ache" into specific medical terms such as "stomachache" and "feeling sick" into "nausea." It also analyzes emotional data and uses it as diagnostic aids.

[1969] Step 9:

[1970] The server transmits data to the doctor selection module based on the analysis results and emotion data.

[1971] Step 10:

[1972] The doctor selection module lists multiple doctors who are best suited to the patient's symptoms based on specific medical terms and emotional data, and selects the doctor who can provide the appropriate treatment for the patient, taking into account the emotional data.

[1973] Step 11:

[1974] The server passes the list of optimal doctors to the information providing module, which prepares it for display to the user.

[1975] Step 12:

[1976] The information module provides the user with a list of the most suitable doctors and prompts them to make a selection.

[1977] Step 13:

[1978] The user selects the doctor they wish to see from the list of doctors provided and makes an appointment.

[1979] Step 14:

[1980] The terminal transmits information about the doctor selected by the user to the server.

[1981] Step 15:

[1982] The server works in conjunction with the reservation system to confirm an appointment with the doctor selected by the user.

[1983] Step 16:

[1984] After the consultation, the user enters the diagnosis (e.g., "stomach ulcer") and the subsequent progress of symptoms into a feedback collection module.

[1985] Step 17:

[1986] The terminal transmits the input feedback data to the server.

[1987] Step 18:

[1988] The server passes the received feedback data to the database update module.

[1989] Step 19:

[1990] The database update module updates the database to improve diagnostic accuracy based on the feedback data and emotion data.

[1991] Step 20:

[1992] The server transmits the emotion data together with the diagnostic data and feedback data to the automatic medical record generation module.

[1993] Step 21:

[1994] The generation AI automatically generates medical records based on the data sent.

[1995] Step 22:

[1996] The server registers the generated medical records in the medical system and makes them accessible to doctors.

[1997] Example 2

[1998] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1999] Conventional medical systems have had problems leading to accurate diagnoses because patients are unable to clearly describe their symptoms or emotional information is not taken into account. Furthermore, the selection of doctors, improving diagnostic accuracy, and recording medical records are all largely manual and inefficient. This places a heavy burden on both doctors and patients.

[2000] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the patient to input vague symptoms, an emotion engine means for recognizing emotions at the time of symptom input, a generation AI means for analyzing symptoms and converting the results into specific medical terms, a means for selecting an optimal doctor based on the analysis results and emotion data, a means for providing the patient with information on the selected doctor, a means for inputting the progress of symptoms after the diagnosis as feedback, a database update means for improving diagnostic accuracy based on the feedback data, and a generation AI means for automatically generating a medical record based on data at the time of diagnosis. This enables accurate diagnosis based on the patient's vague symptoms and emotion data, selection of an optimal doctor, improvement of diagnostic accuracy, and automatic generation of a medical record.

[2001] A "patient" is a person who receives diagnosis or treatment at a medical institution.

[2002] "Vague symptoms" are physical or mental abnormalities that patients describe without using specific medical or technical terms.

[2003] An "emotion engine" is software or hardware that analyzes a patient's facial expressions and voice and recognizes their emotional state.

[2004] "Generative AI" is a type of artificial intelligence that uses machine learning algorithms to analyze input data and output the results.

[2005] "Specific medical terms" are medically standardized terminology used for diagnosis and treatment.

[2006] A "doctor selection tool" is software or an algorithm that has the function of selecting an appropriate doctor based on the patient's symptoms and emotional data.

[2007] "Information providing means" refers to an interface or system for providing information about selected doctors to patients.

[2008] A "feedback collection means" is an interface or system for collecting information from a patient about the progress of their symptoms after diagnosis.

[2009] The "database update means" is software or algorithm that has the function of updating the database based on collected feedback data and improving diagnostic accuracy.

[2010] The "automatic medical record generation means" is a system that uses generation AI to automatically create medical records based on diagnostic data and feedback data.

[2011] This invention is a system that supports more accurate diagnoses by allowing patients to input vague symptoms and even recognizing their emotions when inputting. This system uses a generative AI model to analyze symptoms and automatically generate medical records, improving the work efficiency of medical professionals. It is also possible to continuously improve diagnostic accuracy through feedback.

[2012] System Configuration

[2013] The system consists of the following main components:

[2014] 1. Symptom entry page: A web browser-based interface for patients to enter vague symptoms.

[2015] 2. Emotion engine: An engine that recognizes the patient's emotions when entering symptoms. It analyzes facial expressions or voice when entering the symptoms.

[2016] 3. Data analysis module: A module that analyzes input symptom data using a generative AI model and converts it into specific medical terms.

[2017] 4. Doctor selection module: A module that selects the most suitable doctor based on analysis results and emotional data.

[2018] 5. Information provision module: A module that provides patients with information about selected doctors.

[2019] 6. Feedback collection module: An interface for inputting the progress of symptoms after diagnosis and a module for collecting that data.

[2020] 7. Database update module: This module updates the database to improve diagnostic accuracy based on collected feedback data.

[2021] 8. Automatic medical record generation module: A generative AI module that automatically generates medical records based on data from the time of diagnosis.

[2022] Program processing

[2023] Displaying the symptom entry page

[2024] The server sends a web page to the user's device, where the patient can enter their symptoms. This web page is composed of HTML and JavaScript and includes an input form, information fields, and a script for collecting emotion data.

[2025] The device displays the received web page in the browser, allowing the user to input symptoms. At the same time, the emotion engine is initialized.

[2026] Symptom data input and sentiment analysis

[2027] Users enter symptoms such as "stomach ache" or "feeling sick" into an input form. They can also provide additional information using a voice input function.

[2028] The device collects input symptom data in real time and simultaneously captures the patient's facial expressions and voice using a camera and microphone, which are then analyzed by an emotion engine.

[2029] The terminal transmits the collected symptom data and emotion data to the server.

[2030] Symptom and emotion data analysis

[2031] The server passes the received symptom data and emotion data to a data analysis module.

[2032] The generative AI model converts symptom data into specific medical terms and analyzes emotional data to generate diagnostic aids.

[2033] The server sends the analysis results and emotion data to the doctor selection module.

[2034] Selection and guidance of the most suitable doctor

[2035] The doctor selection module lists multiple optimal doctors based on the analysis results and emotional data.

[2036] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[2037] The information providing module displays the list to the user and prompts the user to make a selection.

[2038] Collecting diagnostic feedback

[2039] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[2040] The terminal transmits the input feedback data to the server.

[2041] The server sends the received feedback data to the database update module.

[2042] The database update module updates the database based on the feedback data to improve diagnostic accuracy.

[2043] Automatic generation of medical records

[2044] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[2045] The generative AI model automatically generates medical records based on the submitted data.

[2046] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[2047] Specific examples

[2048] For example, if the user inputs "my stomach hurts and I feel sick" as a symptom, the process proceeds as follows:

[2049] The user enters symptoms into the input page, and the emotion engine simultaneously analyzes emotion data from facial expressions or voice.

[2050] The terminal transmits the input data and emotion data to the server.

[2051] The server passes the data and emotional data to a data analysis module, converting "stomachache" into "stomachache" and "feeling sick" into "nausea." The emotional data is also analyzed and used as auxiliary diagnostic information.

[2052] The server uses the doctor selection module to generate a list of optimal doctors based on the analysis results and emotion data.

[2053] The information providing module provides the user with information on the most suitable doctor, and the user selects the doctor with whom he or she wishes to consult.

[2054] The user is examined and provides feedback after the diagnosis.

[2055] A feedback collection module sends the data to a server, and a database update module updates the database based on the feedback data.

[2056] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[2057] Prompt Sentence Examples

[2058] 1. "Please convert the patient's symptom, 'I have a stomachache and feel sick,' into medical terms. Furthermore, please analyze the patient's emotional data and use it as diagnostic support information."

[2059] 2. "Automatically generate a medical record based on the diagnosis and feedback."

[2060] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2061] Step 1: Display the symptom entry page

[2062] The server sends a symptom input page composed of HTML and JavaScript to devices that access a specific URL. The input page includes a symptom input form and a script for collecting emotional data.

[2063] The device renders the received HTML and JavaScript in the browser, allowing the patient to enter their symptoms. When the input page is displayed, the emotion engine is also initialized.

[2064] Input: URL visited by patient

[2065] Output: A browser showing the symptom entry page

[2066] Step 2: Symptom data input and sentiment analysis

[2067] The user enters symptoms such as "stomach ache" or "feeling sick" into the form on the symptom input page, and provides additional information using the voice input function as needed.

[2068] The device collects input symptom data in real time and uses a camera and microphone to capture the patient's facial expressions and voice data, which are then analyzed by an emotion engine.

[2069] The terminal combines the collected symptom data and emotion data into a single data packet and transmits it to the server.

[2070] Input: Symptom data entered by the patient, captured facial and voice data

[2071] Output: Symptom data and emotion data sent to the server

[2072] Step 3: Analyze symptom and emotion data

[2073] The server passes the received symptom data and emotion data to a data analysis module.

[2074] The generative AI model converts symptom data into specific medical terms such as "stomach pain" or "nausea," and also analyzes emotion data to generate diagnostic support information.

[2075] The server sends the generated medical terms and the results of the sentiment analysis to the doctor selection module.

[2076] Input: Symptom data and emotion data received by the server

[2077] Output: Analysis results with specific medical terms and supporting information

[2078] Step 4: Selecting and recommending the best doctor

[2079] The doctor selection module uses the analysis results and emotional data to create a list of multiple doctors best suited to the patient's symptoms.

[2080] The server passes the information of the listed doctors to the information providing module, which then transmits it to the user's terminal.

[2081] The information providing module displays a list of doctors on the user's browser and prompts the user to select the doctor they wish to see.

[2082] Input: Analysis results, emotional data, doctor information

[2083] Output: A list of doctors displayed to the user

[2084] Step 5: Collect diagnostic feedback

[2085] After the consultation, the user uses the feedback collection module to input the diagnosis and subsequent progress of symptoms.

[2086] The terminal transmits the input feedback data to the server.

[2087] The server passes the received feedback data to a database update module to update the database.

[2088] Input: User-entered feedback data

[2089] Output: Feedback data updated in the database

[2090] Step 6: Automatic generation of medical records

[2091] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[2092] The generative AI model automatically generates detailed medical records based on the submitted data.

[2093] The automatic medical record generation module registers the generated medical records in the medical system so that the attending physician can access them.

[2094] Input: Diagnostic data, feedback data

[2095] Output: Medical records registered in the medical system

[2096] (Application example 2)

[2097] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2098] In conventional medical systems, it is difficult for patients to clearly communicate their symptoms and there is a lack of means to recognize their emotional state, making it difficult to make an appropriate diagnosis. Furthermore, many tasks, such as selecting the appropriate doctor, collecting feedback after diagnosis, and automatically generating medical records, are performed manually, placing a heavy burden on medical professionals. This leads to issues such as reduced diagnostic accuracy and worsening work efficiency.

[2099] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2100] In this invention, the server includes: a means for a patient to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; a means for selecting the most appropriate doctor based on the analysis results; a means for providing the patient with information about the selected doctor; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; a generating AI means for automatically generating a medical record based on the data at the time of the diagnosis; a means including an emotion engine for analyzing the patient's facial expressions or voice and recognizing emotional data; a means for inputting symptoms via a smartphone application and analyzing them together with the emotional data; and a means for listing and providing the most appropriate doctors for the application. This allows for a more accurate understanding of a patient's vague symptoms and emotional state, enabling the selection of an appropriate doctor, improving diagnostic accuracy, and enabling the automatic generation of medical records and the collection of feedback to be performed efficiently.

[2101] A "patient" is a person who seeks medical examination or treatment from a medical institution.

[2102] "Symptoms" refer to signs or conditions of a disease or abnormality that a patient is aware of.

[2103] "Input" is the act of providing information or data to a system.

[2104] "Generative AI" uses artificial intelligence techniques to analyze data and automatically generate specific results.

[2105] "Analysis" is the act of breaking down data or information and analyzing its contents in detail.

[2106] "Medical terminology" refers to specialized words and expressions related to medicine and health.

[2107] "Selection" is the act of choosing the best option from among many candidates.

[2108] A "physician" is a medical professional who has medical expertise and qualifications and who provides medical examinations and treatment.

[2109] "Information" refers to content such as knowledge and data.

[2110] "Providing" is the act of giving something that is needed to someone else.

[2111] "Diagnosis" is the medical procedure for identifying a patient's illness or abnormality.

[2112] "Feedback" is the act of giving a reaction or opinion to a certain action or result.

[2113] A "database" is a system that systematically collects and centrally manages a large amount of data.

[2114] "Update" is the act of changing existing information or data into new information or data.

[2115] A "medical record" is a document that compiles records and data related to a patient's medical treatment.

[2116] "Emotion engine" refers to technology that recognizes a patient's emotional state from their facial expressions and voice.

[2117] A "smartphone application" is software that runs on a smartphone.

[2118] "Listing" is the act of presenting suitable options from a number of options in list form.

[2119] A "system" is a system in which interrelated parts and elements are combined to perform a specific function.

[2120] This invention relates to a system that improves diagnostic accuracy by allowing patients to input vague symptoms using a smartphone application and even recognizing their emotions at the time of input. This system has the function of analyzing symptoms using a generative AI model and automatically generating medical records. It also allows for continuous improvement of diagnostic accuracy through feedback.

[2121] System Configuration

[2122] The system consists of the following main components:

[2123] 1. Symptom input method

[2124] This is an interface for patients to input their vague symptoms. This interface uses a smartphone application.

[2125] 2. Emotion Engine

[2126] The system analyzes the patient's facial expressions and voice when entering symptoms and recognizes emotional data, using Google Cloud Vision and IBM Watson's emotion analysis API.

[2127] 3. Data Analysis Module

[2128] It uses a generative AI model, such as OpenAI's GPT-4, that analyzes input symptom and emotion data and converts the results into specific medical terms.

[2129] 4. Doctor Selection Module

[2130] This module lists the most suitable doctors based on the analysis results. It is built using Python and utilizes libraries such as SciPy and TensorFlow.

[2131] 5. Information Module

[2132] This module provides patients with information about selected doctors. The information is presented through a smartphone application interface.

[2133] 6. Feedback Collection Module

[2134] This module collects feedback from patients about the progress of their symptoms after diagnosis. The collected feedback data is sent to the server.

[2135] 7. Database Update Module

[2136] This module periodically updates the database to improve diagnostic accuracy based on feedback data.

[2137] 8. Automatic medical record generation module

[2138] It uses a generative AI model that automatically generates medical records based on diagnostic data and feedback data, and the generated medical records are registered in the medical system and made accessible to doctors.

[2139] Program processing

[2140] Displaying the symptom entry page

[2141] The server generates a web page or smartphone application interface for patients to enter their symptoms and sends it to the user's device.

[2142] The terminal displays the received interface and makes it possible for the patient to input information.

[2143] Symptom data analysis

[2144] Users use a smartphone application to input symptoms such as "stomach ache" or "nausea."

[2145] While the input is being made, the emotion engine of the terminal analyzes the patient's facial expressions or voice, and also transmits the emotion data to the server.

[2146] The server passes this data to a data analysis module, where a generative AI model analyzes it and converts it into specific medical terms.

[2147] Selection and guidance of the most suitable doctor

[2148] The doctor selection module lists the most suitable doctors based on medical terminology and emotional data received from the generative AI.

[2149] The server passes this list to the information providing module and displays it to the patient.

[2150] Collecting diagnostic feedback

[2151] Users input their post-diagnosis progress and impressions through a feedback collection module.

[2152] The terminal transmits this feedback data to the server.

[2153] The server passes the received feedback data to a database update module to update the database.

[2154] Automatic generation of medical records

[2155] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[2156] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[2157] Specific examples

[2158] For example, if the user inputs "My stomach hurts and I feel sick," the process proceeds as follows:

[2159] The user enters symptoms into a smartphone application, and the emotion engine simultaneously analyzes emotional data from facial expressions and voice.

[2160] The terminal transmits the input symptom data and emotion data to the server.

[2161] The server passes the data to a data analysis module, where a generative AI model converts the data into specific medical terms.

[2162] The server sends the analysis results to the doctor selection module, which generates a list of the most suitable doctors.

[2163] The information provision module provides the list to the patient, who then schedules an appointment.

[2164] After the patient is seen, feedback is collected and sent to the server.

[2165] The database update module updates the database to improve diagnostic accuracy.

[2166] The automatic medical record generation module automatically generates medical records and registers them in the medical system.

[2167] Prompt Sentence Examples

[2168] Patient's stated symptoms: Stomach pain, feeling sick

[2169] Emotional data: sad facial expression, nervous voice

[2170] Translate the symptoms into specific medical terms and list the doctors who are suitable for the patient.

[2171] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2172] Step 1:

[2173] Display of symptom entry screen

[2174] The server generates a web page or smartphone application interface for patients to enter their symptoms.

[2175] The server sends this interface to the user's terminal, which displays the received interface.

[2176] As a result, the patient is ready to enter their symptoms.

[2177] Step 2:

[2178] Symptom entry and emotional data collection

[2179] Users input their symptoms (e.g., "I have a stomachache" or "I feel sick") using the smartphone application interface.

[2180] At the same time, the emotion engine analyzes emotion data using video and audio data input from the device's camera and microphone.

[2181] The terminal transmits the collected symptom data and emotion data to a server.

[2182] Input data: Symptoms (text), emotion data (voice, facial expression)

[2183] Output data: Symptom data, emotion data

[2184] Step 3:

[2185] Data analysis

[2186] The server passes the received symptom data and emotion data to a data analysis module.

[2187] The data analysis module uses a generative AI model (e.g., GPT-4) to analyze this data and translate vague symptoms into concrete medical terms.

[2188] Input data: symptom data, emotion data

[2189] Output data: Data converted into medical terms

[2190] Step 4:

[2191] Doctor Selection

[2192] The server passes the specific medical terms obtained from the data analysis module to the physician selection module.

[2193] The doctor selection module uses libraries such as Python, SciPy, and TensorFlow to list the most suitable doctors based on the analysis results.

[2194] Input data: Data converted into medical terms

[2195] Output data: List of best doctors

[2196] Step 5:

[2197] Providing optimal doctor information

[2198] The server passes the list of optimal doctors obtained from the doctor selection module to the information providing module.

[2199] The information provision module provides this list to the patient through the smartphone application interface.

[2200] Input data: List of best doctors

[2201] Output data: Optimal doctor information displayed to the patient

[2202] Step 6:

[2203] Collecting diagnostic feedback

[2204] Users enter information about the progression of symptoms after diagnosis and their evaluation of the diagnostic results through the feedback collection module of the smartphone application.

[2205] The terminal transmits the feedback data to the server.

[2206] Input data: Feedback data

[2207] Output data: Feedback data sent to the server

[2208] Step 7:

[2209] Database Update

[2210] The server passes the received feedback data to the database update module.

[2211] The database update module updates the database based on this data to improve diagnostic accuracy.

[2212] Input data: Feedback data

[2213] Output data: Updated database

[2214] Step 8:

[2215] Automatic generation of medical records

[2216] The server transmits diagnostic data and feedback data to the automatic medical record generation module.

[2217] The generation AI automatically generates medical records based on the submitted data and registers them in the medical system.

[2218] Input data: diagnostic data, feedback data

[2219] Output data: Automatically generated medical records

[2220] 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.

[2221] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2222] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2223] 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.

[2224] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2225] 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.

[2226] 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).

[2227] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation i...

Claims

1. A means for patients to input vague symptoms; a generating AI means for analyzing the symptoms and converting the results into specific medical terms; A means for selecting an optimal doctor based on the analysis results; a means for providing information about the selected doctor to the patient; a means for inputting the progress of symptoms after the diagnosis as feedback; a database update means for improving diagnostic accuracy based on the feedback data; A generation AI means for automatically generating medical records based on the data at the time of diagnosis. Including system.

2. 2. The system according to claim 1, wherein the symptom input means is an interface using a web browser.

3. The system of claim 1 , wherein the generating AI means utilizes a machine learning algorithm.

Images