system

Abstract

Provide a system. A terminal means for inputting symptoms and measurement data; a server means for storing data transmitted from the terminal means; a server means for analyzing the accumulated data based on a machine learning model to generate candidate cases and recommended treatments; means for transmitting the generated analysis results to said terminal means and displaying them; A system including:

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] In the medical field, there are cases where abnormal values ​​are overlooked during diagnosis, leading to missed symptoms and situations where treatment is too late. Also, when a doctor is faced with a case outside of his or her specialty, it can be difficult to quickly refer the patient to the appropriate department. There is a need for a system that can solve these problems, improve diagnostic accuracy, and promote early treatment. [Means for solving the problem]

[0005] The present invention provides a system including a terminal means for inputting symptoms and measurement data, a server means for storing data transmitted from the terminal means, a server means for analyzing the stored data based on a machine learning model to generate case candidates and recommended treatments, and a means for transmitting the generated analysis results to the terminal means and displaying them. The system also includes a means for periodically updating the machine learning model based on the stored data to improve the prediction accuracy of case candidates, and a means for recommending an appropriate medical department based on the analysis results and displaying the recommended medical department information on the terminal means. This reduces the risk of overlooking abnormal values ​​during diagnosis and enables the system to quickly recommend an appropriate medical department even for cases outside the patient's specialty.

[0006] "Symptoms" refer to physical or mental abnormalities or discomforts reported by a patient.

[0007] "Measurement data" refers to numerical information obtained through medical equipment or tests, such as blood sugar levels, blood pressure, and body temperature.

[0008] "Terminal means" refers to electronic equipment that allows medical staff to input symptoms and measurement data of patients and transmit the data to a server.

[0009] The term "server means" refers to a computer system that receives, stores, and analyzes data sent from the terminal means.

[0010] A "machine learning model" is an algorithm that learns specific patterns and relationships based on accumulated data and makes predictions and classifications based on new data.

[0011] "Analysis results" refers to information such as case candidates, symptoms, recommended treatments, and recommended medical departments generated by the machine learning model.

[0012] A "medical department" refers to a medical branch that specializes in a particular area, such as internal medicine, surgery, or dermatology.

[0013] "Recommendation" refers to suggesting an appropriate medical department or treatment method based on the analysis results.

[0014] "Display means" refers to an interface function for visually displaying the analysis results on the terminal means. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention provides a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, and a machine learning model. Detailed embodiments of this system are described below.

[0037] Overall system overview

[0038] The system consists of the following main components:

[0039] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[0040] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[0041] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. This allows predictions and diagnostic support for new data.

[0042] 4. Display means for analysis results: An interface that visually displays the analysis results on the terminal means, allowing the user to immediately check the analysis results.

[0043] Program processing (explained in natural language)

[0044] Data collection and storage

[0045] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure, blood sugar level, body temperature) are entered into the terminal.

[0046] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[0047] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[0048] AI learning

[0049] Server: Periodically retrieves data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results.

[0050] Analysis at the time of diagnosis

[0051] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[0052] Terminal: Sends the entered data to the server.

[0053] Server: Inputs the received data into the machine learning model and performs analysis. As a result, a list of candidate cases, their symptoms, recommended treatments, and appropriate medical departments are generated.

[0054] Output of analysis results

[0055] Server: Sends the generated analysis results to the terminal.

[0056] Terminal: Displays the analysis results to the user.

[0057] Specific examples

[0058] A concrete example from data entry at the first consultation to output of analysis results

[0059] User: Patient A visits the clinic complaining of headache and vomiting. He measures his blood pressure at 160 / 100 mmHg, blood sugar at 180 mg / dL, and body temperature at 37.5°C and enters the results into the terminal.

[0060] Terminal: Formats input data and sends it to the server.

[0061] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[0062] Server: Generates a list of potential cases for hypertension and diabetes, including their symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (ACE inhibitors and insulin therapy), and recommends internal medicine as the appropriate specialty.

[0063] Server: Sends analysis results to the device.

[0064] Terminal: Displays the analysis results to the user, who is a doctor, and issues a referral letter to an internal medicine department.

[0065] This system is expected to lead to improved diagnostic accuracy and earlier treatment.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] During consultation, the user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[0069] Step 2:

[0070] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[0071] Step 3:

[0072] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[0073] Step 4:

[0074] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[0075] Step 5:

[0076] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[0077] Step 6:

[0078] The terminal transmits the input data to the server again.

[0079] Step 7:

[0080] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[0081] Step 8:

[0082] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[0083] Step 9:

[0084] The server then sends the generated analysis results to the terminal, which include a list of potential cases, symptoms for each case, recommended treatment, and recommended medical department.

[0085] Step 10:

[0086] The terminal displays the analysis results to the user.

[0087] Step 11:

[0088] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[0089] Example 1

[0090] 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."

[0091] In current medical settings, there are problems such as the risk of overlooking abnormal values ​​during diagnosis and the difficulty of quickly referring patients to the appropriate department. In particular, efficiently analyzing large amounts of patient data and providing highly accurate diagnostic support are important challenges for doctors. This system aims to provide diagnostic support that quickly analyzes symptoms and measurement data and promotes early treatment.

[0092] 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.

[0093] In this invention, the server includes an information terminal means for inputting symptoms and measurement data, a means for accumulating data transmitted from the information terminal means and saving it in a database, a means for periodically updating a machine learning model using the accumulated data and learning from past clinical data, a means for analyzing new data in real time based on the machine learning model and generating candidate cases and recommended treatments, and a means for transmitting the generated analysis results to the information terminal means and visually displaying them. This enables efficient analysis of a large amount of patient data, improves diagnostic accuracy, and enables prompt referral to the appropriate department.

[0094] "Symptom" refers to a sign or characteristic of a disease or health condition exhibited by a patient.

[0095] "Measurement data" refers to data that indicates biological information such as blood pressure, blood sugar level, and body temperature.

[0096] "Information terminal means" refers to a device that allows the user to input symptoms and measurement data, and includes a personal computer or tablet terminal.

[0097] The "server means" refers to a computer system having the function of receiving data sent from the information terminal means and storing it in a database.

[0098] A "database" is a storage device that centrally manages accumulated data and allows it to be retrieved when needed.

[0099] A "machine learning model" is an algorithm that learns from accumulated data and makes predictions and inferences about new data.

[0100] "Real-time analysis" refers to the process of performing analysis immediately as new data is entered.

[0101] "Case candidate" refers to a disease or health condition that is suspected based on symptoms and measurement data.

[0102] "Recommended treatment" refers to a treatment method that can be applied to a candidate case.

[0103] "Visually displaying" means showing the analysis results on a screen or the like in a format that is easy for the user to understand.

[0104] A "referral letter" is an official document used to refer a patient to another medical department or specialist.

[0105] This invention is a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. The system includes a data input terminal, a server for storing and analyzing data, a machine learning model, and an interface for displaying the analysis results.

[0106] Detailed Embodiment of the System

[0107] Data Entry Terminal

[0108] The user enters the patient's symptoms and measurement data into a data entry terminal, which can be a standard PC or tablet. The entered data is formatted, personal identifying information is removed, and the data is sent to a server via an encrypted protocol (e.g., HTTPS).

[0109] Server for data storage and analysis

[0110] The server receives data sent from the information terminal and stores it in a database. The server also periodically retrieves data from the database and updates the machine learning model. The update is performed after data cleansing and preprocessing.

[0111] Machine learning models

[0112] The machine learning model is an algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and appropriate medical departments. When new data is input, it is analyzed immediately in real time and generates results.

[0113] Interface for displaying analysis results

[0114] The generated analysis results are then sent back to the device and visually displayed to the user, who is then a doctor who can make a diagnosis based on the displayed analysis results and, if necessary, refer the patient to the appropriate department.

[0115] Specific examples

[0116] A concrete example from data entry at the first consultation to output of analysis results

[0117] 1. User: Patient A comes to the clinic complaining of headache and vomiting. He enters his blood pressure (160 / 100 mmHg), blood glucose (180 mg / dL), and body temperature (37.5°C) into the terminal.

[0118] 2. Terminal: Formats input data and sends it to the server using an encryption protocol.

[0119] 3. Server: Stores the received data in a database and analyzes it in real time using machine learning models.

[0120] 4. Server: Generates a list of candidate cases for hypertension and diabetes, and recommends their symptoms (headache, vomiting, elevated blood sugar levels), recommended treatments (ACE inhibitors, insulin therapy), and the appropriate medical department for treatment: internal medicine.

[0121] 5. Server: Sends the analysis results to the device.

[0122] 6. Terminal: The analysis results are displayed to the user (physician) and a referral letter to an internal medicine department is issued if necessary.

[0123] Prompt Sentence Examples

[0124] "Patient A complains of headache and vomiting. Measurements include blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, and temperature 37.5°C. Based on these data, please provide appropriate case candidates, indications, recommended treatment, and department."

[0125] This system will enable efficient analysis of large amounts of patient data, improving diagnostic accuracy and enabling prompt referral to the appropriate department.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1:

[0128] Data Entry

[0129] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the information terminal.

[0130] Input: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C.

[0131] Output: Formatted symptom and measurement data.

[0132] Step 2:

[0133] Data transmission

[0134] Terminal: Formats the entered data and removes any personally identifiable information. The data is then sent to the server using an encrypted protocol (e.g., HTTPS).

[0135] Input: Formatted symptom and measurement data.

[0136] Output: The encrypted data.

[0137] Step 3:

[0138] Data accumulation

[0139] Server: Stores the received data in a database. The data is identified for each patient and classified appropriately.

[0140] Input: Encrypted data.

[0141] Output: Data stored in the database.

[0142] Step 4:

[0143] AI model learning

[0144] Server: Periodically retrieves data from the database and performs data cleansing. It complements outliers and missing values ​​in the data and updates the machine learning model. Learning is performed based on past medical data, learning the relationship between symptoms, measurement data, and diagnosis results.

[0145] Input: Data stored in a database.

[0146] Output: An updated machine learning model.

[0147] Step 5:

[0148] New Data Transmission

[0149] User: Enters new patient symptoms and measurement data into the terminal during consultation.

[0150] Terminal: Sends new formatted data to the server.

[0151] Input: New symptom and measurement data.

[0152] Output: The new formatted data.

[0153] Step 6:

[0154] Diagnostic Analysis

[0155] Server: Receives new data and feeds it into the machine learning model in real time. The model performs immediate analysis and generates a list of potential cases, indications, treatment recommendations, and appropriate departments.

[0156] Input: New data.

[0157] Output: A list of potential cases, symptoms, recommended treatments, and medical departments based on the analysis results.

[0158] Step 7:

[0159] Send analysis results

[0160] Server: The generated analysis results are re-encrypted and sent to the terminal.

[0161] Input: Analysis results, candidate case list, symptoms, recommended treatment, medical department.

[0162] Output: Encrypted analysis results.

[0163] Step 8:

[0164] Analysis result display

[0165] Terminal: The analysis results are interpreted and visually displayed on a dedicated interface for doctors, who then make a diagnosis based on the results and, if necessary, refer the patient to the appropriate department.

[0166] Input: Encrypted analysis results.

[0167] Output: A visual representation of the analysis results.

[0168] (Application example 1)

[0169] 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."

[0170] Conventional health monitoring systems have limited response capabilities when abnormal values ​​are detected, making it difficult to promptly and appropriately urge users to seek medical attention. There is also a need for a system that can monitor the health status of passengers in autonomous vehicles in real time and take appropriate measures immediately when an abnormality occurs.

[0171] 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.

[0172] In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model to generate case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, means for monitoring the data input by the terminal means in real time and displaying an alarm when an abnormality is detected, and means for providing an optimal route to a medical institution based on the displayed alarm. This enables real-time monitoring of the health condition of passengers and enables prompt and appropriate medical treatment when an abnormality occurs.

[0173] "Symptoms" refers to specific symptoms or abnormalities that indicate the user's health condition.

[0174] "Measurement data" refers to physiological data obtained from the patient's or user's body, such as blood pressure, heart rate, body temperature, and other numerical values.

[0175] "Terminal means" refers to a device through which a user inputs symptoms and measurement data, specifically an electronic device such as a smartphone or a head-mounted display.

[0176] "Server means" refers to a central server that stores data sent from the terminal means and analyzes it using a machine learning model.

[0177] A "machine learning model" refers to an algorithm that uses accumulated data to learn, detect abnormalities, and generate recommended treatments.

[0178] "Analysis results" refers to diagnostic support information such as case candidates, recommended treatments, and abnormality detection generated by the machine learning model.

[0179] "Real-time monitoring" refers to the process of instantly analyzing input data and constantly monitoring for abnormalities.

[0180] "Means for displaying a warning" refers to a function for visually or audibly alerting the user when an abnormality is detected.

[0181] "Guidance route to medical institution" refers to information that provides the most appropriate route to a medical institution and the appropriate response when an abnormality is detected.

[0182] This invention relates to a system that inputs symptoms and measurement data, monitors health conditions in real time based on the data, displays a warning if an abnormality is detected, and guides the user to an appropriate medical institution. Specific embodiments of the system are described below.

[0183] The system mainly consists of the following components:

[0184] 1. Terminal means: A device through which the user inputs symptoms and measurement data, including a smartphone or head-mounted display.

[0185] 2. Server means: A server that accumulates data sent from the terminal means and analyzes it using a machine learning model.

[0186] 3. Machine learning model: An algorithm that detects abnormalities based on accumulated data and provides recommended treatments and guidance routes to the most appropriate medical institution based on the analysis results.

[0187] 4. Means for displaying analysis results: An interface for visually or audibly displaying warnings and analysis results to the user.

[0188] Program processing (explained in natural language)

[0189] Data Collection and Monitoring

[0190] A user inputs their own health data (e.g., blood pressure, heart rate, body temperature) into the terminal means, which formats the input data and transmits it to the server means.

[0191] Real-time analytics

[0192] The server inputs the received data into a machine learning model and performs real-time analysis. If an abnormality is detected during the analysis, the server immediately sends the results to the terminal and displays a warning to the user.

[0193] Guidance and contact to medical institutions

[0194] The server also provides a route to the most appropriate medical institution when an abnormality is detected, and is equipped with a function that automatically notifies the appropriate medical institution or family member as necessary.

[0195] Hardware and software used

[0196] Hardware: Smartphones, head-mounted displays, and in-vehicle devices inside autonomous vehicles.

[0197] Software: Python program for data analysis, Requests library for sending and receiving data, machine learning models (such as TENSORFLOW (registered trademark) and Scikit-learn).

[0198] Specific examples

[0199] Example 1: In-car health monitoring

[0200] User: A passenger who becomes ill in an autonomous vehicle uses their smartphone to enter their blood pressure and heart rate.

[0201] Server: Analyzes the received data and detects abnormally high heart rates.

[0202] Terminal means: Displays a warning to passengers and provides guidance to the nearest medical facility.

[0203] Prompt Sentence Examples

[0204] Design a system that analyzes the following health data in real time for abnormal values, and if an abnormality is detected, suggests routes to the nearest medical facility and contact options.

[0205] *Example of health data: Blood pressure 150 / 90, heart rate 100, body temperature 38℃.

[0206] Please implement this using Python and the Requests library.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] The user inputs their own health data (blood pressure, heart rate, body temperature, etc.) into a terminal means (a smartphone or a head-mounted display). The input data is formatted into an appropriate format by the terminal means.

[0210] input:

[0211] Health data (e.g., blood pressure 130 / 85, heart rate 85, body temperature 36.8℃)

[0212] output:

[0213] Formatted Data

[0214] Specific operation:

[0215] The user inputs numerical values ​​through the interface of the terminal means, and the data is converted into JSON format.

[0216] Step 2:

[0217] The terminal means transmits the formatted data to the server means in real time via the Internet.

[0218] input:

[0219] Formatted Data

[0220] output:

[0221] Data sent to the server

[0222] Specific operation:

[0223] Use the Requests library to send data to the server's API with an HTTP POST request.

[0224] Step 3:

[0225] The server means stores the received data, which is then stored in a database for later analysis and model updating.

[0226] input:

[0227] Data sent

[0228] output:

[0229] Data stored in a database

[0230] Specific operation:

[0231] The received data is stored in a database using a database management system (e.g., MySQL (registered trademark), PostgreSQL).

[0232] Step 4:

[0233] The server inputs the accumulated data into a machine learning model and performs real-time analysis, thereby detecting the presence or absence of abnormalities.

[0234] input:

[0235] Data stored in a database

[0236] Machine learning models

[0237] output:

[0238] Analysis results showing whether or not there are any abnormalities

[0239] Specific operation:

[0240] Using Python machine learning libraries (e.g., TensorFlow, Scikit-learn), the received data is input into a model to generate analysis results.

[0241] Step 5:

[0242] The server unit transmits the generated analysis results to the terminal unit, which also include a warning message if an abnormality is detected.

[0243] input:

[0244] Analysis results

[0245] output:

[0246] Analysis results sent to the terminal means

[0247] Specific operation:

[0248] The analysis results are reformatted in JSON format and sent to the terminal means via an HTTP POST request.

[0249] Step 6:

[0250] The terminal means displays the received analysis results to the user, and if an abnormality is detected, a warning message is displayed.

[0251] input:

[0252] Received analysis results

[0253] output:

[0254] Results and warnings displayed to the user

[0255] Specific operation:

[0256] Results are displayed visually through a smartphone or head-mounted display interface, and audio alerts are provided if required.

[0257] Step 7:

[0258] When a warning is displayed, the terminal device also provides a route to the most appropriate medical institution, and automatically notifies the appropriate medical institution or family member as necessary.

[0259] input:

[0260] Warning messages based on analysis results

[0261] output:

[0262] Routes to medical institutions

[0263] Automatic notifications when needed

[0264] Specific operation:

[0265] It uses GPS data to search for the nearest medical facility, displays routes on a map, and notifies medical facilities and family members via phone or email based on contact information.

[0266] 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.

[0267] The present invention provides a system that takes user emotions into consideration during diagnosis, reducing the chance of overlooking abnormal values ​​and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, a machine learning model, and an emotion engine. Detailed embodiments of this system are described below.

[0268] Overall system overview

[0269] The system consists of the following main components:

[0270] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[0271] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[0272] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. It also provides predictions and diagnostic support for new data.

[0273] 4. Display of analysis results: An interface that visually displays the analysis results on the terminal, allowing users to immediately check the analysis results.

[0274] 5. Emotion Engine: An algorithm that recognizes the user's emotions and adjusts the display of analysis results and the provision of support. It infers emotions from the user's words, facial expressions, and typing pace.

[0275] Program processing (explained in natural language)

[0276] Data collection and storage

[0277] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the terminal.

[0278] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[0279] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[0280] AI learning

[0281] Server: Periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[0282] Diagnostic and emotional analysis

[0283] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[0284] Terminal: Sends the entered data to the server.

[0285] Server: Inputs incoming data into machine learning models for real-time analysis. The analysis step generates candidate cases, their symptoms, and treatment recommendations.

[0286] Emotion Engine: At the same time, it analyzes the user's input, facial expressions, and words to infer their emotional state. The emotion engine identifies emotions such as impatience, confusion, and certainty.

[0287] Analysis output and emotion-based adjustment

[0288] Server: Based on the analysis results, if a specific medical department is required, the server identifies and recommends that department.

[0289] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[0290] Server: Sends the analysis results to the device.

[0291] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[0292] Specific examples

[0293] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[0294] User: Patient B visits the clinic complaining of headache and vomiting. His blood pressure is 160 / 100 mmHg, his blood sugar is 180 mg / dL, and his body temperature is 37.5°C. The results are entered into the terminal. The emotion engine also recognizes that the user is feeling a little impatient.

[0295] Terminal: Formats input data and sends it to the server.

[0296] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[0297] Server: Generates a list of potential cases of hypothyroidism and diabetes, including symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), and recommends thyroid clinic visits.

[0298] Emotion Engine: Detects the user's impatience and displays the analysis results with concise and specific alerts.

[0299] Server: Sends analysis results to the device.

[0300] Terminal: Displays analysis results (case candidates, symptoms, recommended treatments, and department information) and provides additional support information and instructions to reduce user impatience.

[0301] This system is expected to lead to improved diagnostic accuracy and earlier treatment. In addition, the introduction of an emotion engine will provide flexible and accurate support according to the user's situation, reducing stress in medical settings and enabling more efficient medical treatment.

[0302] The processing flow will be explained below.

[0303] Step 1:

[0304] During consultation, the user enters the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[0305] Step 2:

[0306] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[0307] Step 3:

[0308] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[0309] Step 4:

[0310] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[0311] Step 5:

[0312] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[0313] Step 6:

[0314] The terminal transmits the input data to the server again.

[0315] Step 7:

[0316] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[0317] Step 8:

[0318] The emotion engine collects emotional data from the device through the user's facial expressions, voice, input speed, etc., and estimates the user's emotional state.

[0319] Step 9:

[0320] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[0321] Step 10:

[0322] The server adjusts the analysis results in cooperation with the emotion engine and determines the content and method of display according to the user's emotional state.

[0323] Step 11:

[0324] The server transmits the generated analysis results and the adjustment results from the emotion engine to the terminal.

[0325] Step 12:

[0326] The device displays the analysis results to the user. If the user is feeling anxious or stressed, the device displays the analysis results concisely and provides additional support information or alerts.

[0327] Step 13:

[0328] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[0329] Example 2

[0330] 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."

[0331] Conventional diagnostic systems do not take into account the user's emotional state in the process from inputting symptoms and measurement data to outputting analysis results, resulting in problems such as insufficient diagnostic accuracy and insufficient reduction of user stress. Furthermore, improving the accuracy of case candidates and recommended treatments remains a challenge.

[0332] 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 an input device means for inputting symptoms and measurement data, a data processing device means for storing and analyzing data transmitted from the input device means, an analysis device means for analyzing the data stored in the data processing device means based on a machine learning algorithm and generating case candidates and recommended treatments, a display device means for transmitting and displaying the analysis results generated by the analysis device means to the input device means, and an emotion analysis device means for adjusting the analysis results based on the emotional state of the user. This enables improved data accuracy and user-friendly display of analysis results, thereby realizing efficient and stress-free medical treatment in medical settings.

[0333] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by a patient.

[0334] "Measurement data" refers to values ​​that quantitatively indicate the patient's physical condition, such as blood pressure, blood sugar level, and body temperature.

[0335] "Input device means" refers to a device for inputting symptoms and measurement data, and includes a personal computer, tablet, etc.

[0336] The "data processing device means" is a device that receives data sent from the input device means and stores it in a database.

[0337] A "machine learning algorithm" is an algorithm that learns patterns based on large amounts of data and makes predictions and classifications.

[0338] The "analysis device means" is a device that analyzes the accumulated data based on a machine learning algorithm and generates candidate cases and recommended treatments.

[0339] The "display device means" is a device that visually presents the analysis results generated by the analysis device means to the user.

[0340] The "emotion analysis device means" is a device that estimates emotions from the user's input state, facial expressions, words, etc., and adjusts the content and method of displaying the analysis results.

[0341] "Update means" refers to the means for periodically improving and updating the machine learning algorithm based on accumulated data.

[0342] "Learning improvement means" refers to means for improving the accuracy of predicting case candidates using machine learning algorithms.

[0343] The "medical department recommendation means" is a means for identifying an appropriate medical department based on the analysis results and recommending it to the user.

[0344] The "information display means" is a means for displaying recommended medical department information on the input device means.

[0345] The present invention provides a system that reduces the oversight of abnormal values ​​and promotes early treatment by taking a user's emotions into consideration during diagnosis. This system includes an input device means for a user to input a patient's symptoms and measurement data, a data processing device means for storing and analyzing the data, an analysis device means for performing analysis based on the stored data using a machine learning algorithm, a display device means for displaying the analysis results, and an emotion analysis device means for adjusting the display of the analysis results based on the user's emotional state. Detailed embodiments of this system are described below.

[0346] Data collection and storage

[0347] During medical examinations, a user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood glucose level 180 mg / dL, body temperature 37.5°C) into an input device means such as a personal computer or tablet. The input data is converted into a predetermined format within the terminal, and personally identifiable information is deleted. The formatted data is then transmitted to the data processing device means via a security protocol (e.g., HTTPS). The data processing device means stores the received data in a database and uses it for subsequent analysis and machine learning.

[0348] AI learning

[0349] The data processing device periodically retrieves accumulated data from the database and refreshes the model using a machine learning algorithm. Based on past medical data, the system learns the relationship between symptoms, measurement data, and diagnostic results. Random forests, neural networks, etc. are used as machine learning algorithms.

[0350] Diagnostic and emotional analysis

[0351] When a new patient is seen, the user again inputs the symptoms and measurement data into the terminal. The terminal reformats the input data and transmits it to the data processing means. The data processing means immediately inputs the received data into a machine learning algorithm for real-time analysis. The analysis step generates candidate cases, symptoms for each candidate, and recommended treatments.

[0352] At the same time, the emotion analyzer means analyzes the user's input status, facial expressions, and words to estimate the user's emotional state. The emotion analyzer means identifies emotions such as impatience, confusion, and certainty.

[0353] Analysis output and emotion-based adjustment

[0354] If a specific medical department is required based on the analysis results, the medical department is identified and recommended. The emotion analysis device means adjusts the generated analysis results according to the user's emotional state and determines the appropriate display content and method. The adjusted analysis results are sent back to the terminal and displayed to the user by the display device means. Depending on the emotional state, alerts and additional support information are provided.

[0355] Specific examples

[0356] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[0357] When the user visits the clinic complaining of Patient B's headache and vomiting, the user inputs the measurement results of blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, and body temperature 37.5°C into the input device means. At the same time, the emotion analysis device means recognizes that the user is feeling impatient. The terminal formats the input data and transmits it to the data processing device means via a security protocol.

[0358] The data processing means receives the data and stores it in a database. Machine learning algorithms are then used to generate a list of potential cases of hypothyroidism and diabetes, each with their respective symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), as well as recommendations for thyroid clinic visits.

[0359] The emotion analysis device means detects the user's impatience and adjusts the display of the analysis results to emphasize concise and specific alerts. Finally, the adjusted analysis results are sent to the terminal and displayed to the user. Additional support information and instructions may also be provided to reduce the user's impatience.

[0360] Prompt Sentence Examples

[0361] Below are some example prompts to input to a generative AI model:

[0362] "Analyze the following patient data and provide a possible diagnosis and recommended treatment: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C."

[0363] "When users are in a hurry, please display the diagnostic results in a concise and easy-to-understand manner."

[0364] "A new patient has arrived. After entering their symptoms and measurements, the emotion engine has detected impatience. Please adjust your analysis to take this information into account."

[0365] This allows the system to not only provide accurate and prompt diagnostic support, but also to respond flexibly while taking into consideration the user's feelings.

[0366] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0367] Step 1:

[0368] The user enters patient information

[0369] User: During medical examination, the user inputs the patient's symptoms (eg, headache, vomiting) and measurement data (eg, blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the input device means.

[0370] Input and output: The user inputs symptoms and measurement data into the input device, and the data is passed to the terminal.

[0371] Specific operation: The doctor uses the keyboard to enter measurement values ​​and symptoms into a dedicated input form and clicks the "Send" button.

[0372] Step 2:

[0373] The device formats the data and sends it to the server

[0374] Terminal: Converts the entered data into a specified format (e.g., JSON format), deletes any personally identifiable information, and then sends it to the server.

[0375] Input and Output: Takes raw input data and outputs formatted data that is sent to the server.

[0376] What it does: A program on the device filters and formats the data, then sends it securely to a server using the HTTPS protocol.

[0377] Step 3:

[0378] The server stores the data

[0379] Server: Stores the received data in a database and uses it for subsequent analysis and machine learning.

[0380] Input and Output: Receives formatted data and stores it in a database, providing feedback to confirm successful storage.

[0381] Specific behavior: The server adds the received data as a new entry in the database and generates a message indicating the save was successful.

[0382] Step 4:

[0383] The server updates the machine learning model.

[0384] Server: Periodically retrieves accumulated data from the database and refreshes the model using machine learning algorithms.

[0385] Input and Output: Retrieving historical data from the database and outputting an updated model.

[0386] What it does: A scheduled task on the server extracts all new data at a specified time (e.g., every weekend) and retrains it using machine learning algorithms.

[0387] Step 5:

[0388] User enters new patient information

[0389] User: Enters the new patient's symptoms and measurement data again into the input device means.

[0390] Input and Output: New symptoms and measurement data are entered and sent to the terminal.

[0391] Specific operation: As mentioned above, the doctor enters the patient's new symptoms and measurement data and clicks the "Submit" button.

[0392] Step 6:

[0393] The device sends data

[0394] Terminal: Reformats the entered data and sends it to the server.

[0395] Input and Output: Accepts raw data and sends formatted data to the server.

[0396] Specific behavior: Formats and sends the data a second time. Uses HTTPS protocol for security.

[0397] Step 7:

[0398] The server performs the analysis

[0399] Server: Inputs the received data into a machine learning algorithm for real-time analysis, generating candidate cases, their symptoms, and treatment recommendations.

[0400] Input and Output: Formatted data is input into the analysis and output is a list of potential cases and treatment recommendations.

[0401] What it does: It runs new data through machine learning algorithms, performs calculations to produce predictions, and temporarily stores the results.

[0402] Step 8:

[0403] The emotion engine performs emotion analysis

[0404] Emotion engine: Analyzes the user's input, facial expressions, and words to infer their emotional state. It identifies emotions such as impatience, confusion, and certainty.

[0405] Input and output: Receives user input speed and facial expression data and outputs estimated emotional state.

[0406] Specific operation: The emotion analysis algorithm estimates and outputs emotions based on the user's input speed, context, and facial expression data from the camera.

[0407] Step 9:

[0408] The server recommends a medical department

[0409] Server: Based on the analysis results, if a specific medical department is required, identify and recommend that department.

[0410] Input and output: Receives a list of analysis results and outputs recommended medical departments.

[0411] Specific operation: The analysis engine matches case candidates with medical departments and adds the most suitable medical departments to the recommendation list.

[0412] Step 10:

[0413] The server adjusts the analysis results

[0414] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[0415] Input and output: The initial analysis result and the estimated emotional state are input, and the adjusted analysis result is output.

[0416] Specific behavior: Dynamically change the display format and emphasis of results based on feedback from the emotion engine.

[0417] Step 11:

[0418] The server sends the analysis results

[0419] Server: Sends the adjusted analysis results to the device.

[0420] Input and output: Receives refined analysis results and sends them to the terminal.

[0421] Specific operation: Data is securely sent to the device using the HTTPS protocol.

[0422] Step 12:

[0423] The device displays the analysis results.

[0424] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[0425] Input and Output: Receives the adjusted analysis results, converts them into a display format for the user, and displays them.

[0426] What it does: Data is displayed in the end-user interface, notifications are activated, and warnings and additional information are provided when necessary.

[0427] This completes the entire process of the invention, improving diagnostic accuracy and providing user-friendly support.

[0428] (Application example 2)

[0429] 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."

[0430] Conventional medical systems only focus on analysis results based on symptoms and measurement data, and do not take the user's emotional state into consideration, which can lead to problems such as overlooking abnormal values ​​during diagnosis and not providing appropriate advice to the user.It also makes it difficult to recommend medicines and supplements that correspond to the user's emotional state.

[0431] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model and generating case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and means for recommending appropriate medicines and supplements. This enables more accurate diagnoses and appropriate advice and recommendations by taking the user's emotional state into consideration.

[0432] "Terminal means" refers to a device for inputting symptoms and measurement data, and includes smartphones, tablets, etc.

[0433] The term "server means" refers to a computer system that receives data sent from the terminal means and stores and analyzes the data.

[0434] A "machine learning model" is an algorithm that learns from accumulated data and generates case candidates and recommended treatments.

[0435] The "means for displaying the analysis results" refers to an interface for visually presenting the generated analysis results to the user.

[0436] The "emotion engine" is an algorithm for estimating the user's emotional state and adjusting the display of the analysis results accordingly.

[0437] "Means for recommending appropriate medicines and supplements" refers to a function that suggests necessary medicines and supplements based on the user's input data and analysis results.

[0438] This invention realizes a system including a terminal means for inputting symptoms and measurement data, a server means for storing data transmitted from the terminal means, a server means for analyzing the stored data based on a machine learning model and generating candidate cases and recommended treatments, a means for transmitting the generated analysis results to the terminal means and displaying them, an emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and a means for recommending appropriate medicines and supplements.

[0439] Program processing

[0440] Data collection and storage

[0441] The user inputs symptoms and measurement data into a terminal such as a smartphone. This data is formatted and sent to a server. The server stores the received data in a database and uses it for subsequent analysis and machine learning model training.

[0442] AI learning

[0443] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results. This process uses machine learning algorithms (e.g., TensorFlow, PyTorch).

[0444] Health status assessment and emotion analysis

[0445] When a user inputs new data, it is sent from the terminal device to the server. The server then inputs the received data into a machine learning model for real-time analysis. In the analysis step, case candidates, symptoms, and recommended treatments for each candidate are generated. The emotion engine also estimates the user's emotional state from the user's input, facial expressions, and speech patterns, and adjusts the display of the analysis results accordingly.

[0446] Alerts and Recommendations

[0447] The server recommends appropriate medicines and supplements based on the analysis results and the user's emotional state. The generated information is sent to the terminal and visually displayed to the user. Simple and specific alerts are highlighted for users who are feeling particularly anxious or stressed.

[0448] Specific examples

[0449] For example, if a patient complains of headache and fatigue and their blood pressure is measured at 150 / 90 mmHg, they can enter this information into their smartphone and send it to the server. The server analyzes this information and presents possible cases of hypertension along with appropriate treatments (e.g., blood pressure-lowering medication). At the same time, the emotion engine detects the user's stress level and recommends additional relaxation methods and supplements to relieve stress.

[0450] Example prompts for generative AI models

[0451] Please enter your health data (e.g. headache, blood pressure 150 / 90 mmHg, fatigue).

[0452] Assess your emotional state (e.g., stress, impatience).

[0453] Recommend necessary medications and supplements to users based on their health status.

[0454] When making recommendations, tailor alerts to the user's emotional state.

[0455] This system allows users to understand their health condition in detail and receive appropriate medicines, supplements, and treatments efficiently. In particular, the emotional engine reduces the user's psychological burden and provides an effective medical experience.

[0456] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0457] Step 1:

[0458] The user inputs symptoms and measurement data into a terminal such as a smartphone. The input data (e.g., headache, blood pressure 150 / 90 mmHg, fatigue) is formatted by the terminal and personal identifying information is deleted.

[0459] Step 2:

[0460] The terminal means transmits the formatted data to the server means, and the transmission process protects the data using a security protocol (e.g., HTTPS).

[0461] Step 3:

[0462] The server stores the received data in a database. The database uses a relational database (e.g., MySQL) to store the data in a structured manner.

[0463] Step 4:

[0464] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. A machine learning algorithm (e.g., TensorFlow) is used to learn the relationship between symptoms and diagnosis results from past medical data. During this process, training and validation are performed using large amounts of data.

[0465] Step 5:

[0466] When a user inputs new symptoms and measurement data, the data is sent from the terminal device to the server, which then inputs the received data into a machine learning model for real-time analysis. The analysis results in the generation of candidate cases and recommended treatments.

[0467] Step 6:

[0468] The server uses an emotion engine to estimate the user's emotional state based on input context, facial expressions, and speech patterns, and in some cases a natural language processing engine (e.g., Google® Cloud Natural Language API).

[0469] Step 7:

[0470] The server adjusts the display of the analysis results based on the analysis results and the user's estimated emotional state. For example, if a user is feeling anxious, the server will display the analysis results concisely and specifically, highlighting recommendations for necessary medicines and supplements.

[0471] Step 8:

[0472] The server sends the adjusted analysis results and recommendations to the terminal means, which visually displays the information to the user, allowing the user to understand their health status and select appropriate medicines and supplements.

[0473] This system enables diagnosis and recommendations that take into account the user's emotional state, providing highly accurate diagnoses and effective medical support.

[0474] 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.

[0475] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0476] 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.

[0477] [Second embodiment]

[0478] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0479] 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.

[0480] 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).

[0481] 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.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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.

[0487] 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.

[0488] In the smart glasses 214, 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.

[0489] 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."

[0490] The present invention provides a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, and a machine learning model. Detailed embodiments of this system are described below.

[0491] Overall system overview

[0492] The system consists of the following main components:

[0493] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[0494] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[0495] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. This allows predictions and diagnostic support for new data.

[0496] 4. Display means for analysis results: An interface that visually displays the analysis results on the terminal means, allowing the user to immediately check the analysis results.

[0497] Program processing (explained in natural language)

[0498] Data collection and storage

[0499] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure, blood sugar level, body temperature) are entered into the terminal.

[0500] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[0501] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[0502] AI learning

[0503] Server: Periodically retrieves data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results.

[0504] Analysis at the time of diagnosis

[0505] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[0506] Terminal: Sends the entered data to the server.

[0507] Server: Inputs the received data into the machine learning model and performs analysis. As a result, a list of candidate cases, their symptoms, recommended treatments, and appropriate medical departments are generated.

[0508] Output of analysis results

[0509] Server: Sends the generated analysis results to the terminal.

[0510] Terminal: Displays the analysis results to the user.

[0511] Specific examples

[0512] A concrete example from data entry at the first consultation to output of analysis results

[0513] User: Patient A visits the clinic complaining of headache and vomiting. He measures his blood pressure at 160 / 100 mmHg, blood sugar at 180 mg / dL, and body temperature at 37.5°C and enters the results into the terminal.

[0514] Terminal: Formats input data and sends it to the server.

[0515] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[0516] Server: Generates a list of potential cases for hypertension and diabetes, including their symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (ACE inhibitors and insulin therapy), and recommends internal medicine as the appropriate specialty.

[0517] Server: Sends analysis results to the device.

[0518] Terminal: Displays the analysis results to the user, who is a doctor, and issues a referral letter to an internal medicine department.

[0519] This system is expected to lead to improved diagnostic accuracy and earlier treatment.

[0520] The processing flow will be explained below.

[0521] Step 1:

[0522] During consultation, the user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[0523] Step 2:

[0524] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[0525] Step 3:

[0526] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[0527] Step 4:

[0528] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[0529] Step 5:

[0530] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[0531] Step 6:

[0532] The terminal transmits the input data to the server again.

[0533] Step 7:

[0534] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[0535] Step 8:

[0536] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[0537] Step 9:

[0538] The server then sends the generated analysis results to the terminal, which include a list of potential cases, symptoms for each case, recommended treatment, and recommended medical department.

[0539] Step 10:

[0540] The terminal displays the analysis results to the user.

[0541] Step 11:

[0542] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[0543] Example 1

[0544] 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."

[0545] In current medical settings, there are problems such as the risk of overlooking abnormal values ​​during diagnosis and the difficulty of quickly referring patients to the appropriate department. In particular, efficiently analyzing large amounts of patient data and providing highly accurate diagnostic support are important challenges for doctors. This system aims to provide diagnostic support that quickly analyzes symptoms and measurement data and promotes early treatment.

[0546] 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.

[0547] In this invention, the server includes an information terminal means for inputting symptoms and measurement data, a means for accumulating data transmitted from the information terminal means and saving it in a database, a means for periodically updating a machine learning model using the accumulated data and learning from past clinical data, a means for analyzing new data in real time based on the machine learning model and generating candidate cases and recommended treatments, and a means for transmitting the generated analysis results to the information terminal means and visually displaying them. This enables efficient analysis of a large amount of patient data, improves diagnostic accuracy, and enables prompt referral to the appropriate department.

[0548] "Symptom" refers to a sign or characteristic of a disease or health condition exhibited by a patient.

[0549] "Measurement data" refers to data that indicates biological information such as blood pressure, blood sugar level, and body temperature.

[0550] "Information terminal means" refers to a device that allows the user to input symptoms and measurement data, and includes a personal computer or tablet terminal.

[0551] The "server means" refers to a computer system having the function of receiving data sent from the information terminal means and storing it in a database.

[0552] A "database" is a storage device that centrally manages accumulated data and allows it to be retrieved when needed.

[0553] A "machine learning model" is an algorithm that learns from accumulated data and makes predictions and inferences about new data.

[0554] "Real-time analysis" refers to the process of performing analysis immediately as new data is entered.

[0555] "Case candidate" refers to a disease or health condition that is suspected based on symptoms and measurement data.

[0556] "Recommended treatment" refers to a treatment method that can be applied to a candidate case.

[0557] "Visually displaying" means showing the analysis results on a screen or the like in a format that is easy for the user to understand.

[0558] A "referral letter" is an official document used to refer a patient to another medical department or specialist.

[0559] This invention is a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. The system includes a data input terminal, a server for storing and analyzing data, a machine learning model, and an interface for displaying the analysis results.

[0560] Detailed Embodiment of the System

[0561] Data Entry Terminal

[0562] The user enters the patient's symptoms and measurement data into a data entry terminal, which can be a standard PC or tablet. The entered data is formatted, personal identifying information is removed, and the data is sent to a server via an encrypted protocol (e.g., HTTPS).

[0563] Server for data storage and analysis

[0564] The server receives data sent from the information terminal and stores it in a database. The server also periodically retrieves data from the database and updates the machine learning model. The update is performed after data cleansing and preprocessing.

[0565] Machine learning models

[0566] The machine learning model is an algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and appropriate medical departments. When new data is input, it is analyzed immediately in real time and generates results.

[0567] Interface for displaying analysis results

[0568] The generated analysis results are then sent back to the device and visually displayed to the user, who is then a doctor who can make a diagnosis based on the displayed analysis results and, if necessary, refer the patient to the appropriate department.

[0569] Specific examples

[0570] A concrete example from data entry at the first consultation to output of analysis results

[0571] 1. User: Patient A comes to the clinic complaining of headache and vomiting. He enters his blood pressure (160 / 100 mmHg), blood glucose (180 mg / dL), and body temperature (37.5°C) into the terminal.

[0572] 2. Terminal: Formats input data and sends it to the server using an encryption protocol.

[0573] 3. Server: Stores the received data in a database and analyzes it in real time using machine learning models.

[0574] 4. Server: Generates a list of candidate cases for hypertension and diabetes, and recommends their respective symptoms (headache, vomiting, elevated blood sugar levels), recommended treatments (ACE inhibitors, insulin therapy), and the appropriate medical department for treatment: internal medicine.

[0575] 5. Server: Sends the analysis results to the device.

[0576] 6. Terminal: The analysis results are displayed to the user (physician) and a referral letter to an internal medicine department is issued if necessary.

[0577] Prompt Sentence Examples

[0578] "Patient A complains of headache and vomiting. Measurements include blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, and temperature 37.5°C. Based on these data, please provide appropriate case candidates, indications, recommended treatment, and department."

[0579] This system will enable efficient analysis of large amounts of patient data, improving diagnostic accuracy and enabling prompt referral to the appropriate department.

[0580] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0581] Step 1:

[0582] Data Entry

[0583] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the information terminal.

[0584] Input: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C.

[0585] Output: Formatted symptom and measurement data.

[0586] Step 2:

[0587] Data transmission

[0588] Terminal: Formats the entered data and removes any personally identifiable information. The data is then sent to the server using an encrypted protocol (e.g., HTTPS).

[0589] Input: Formatted symptom and measurement data.

[0590] Output: The encrypted data.

[0591] Step 3:

[0592] Data accumulation

[0593] Server: Stores the received data in a database. The data is identified for each patient and classified appropriately.

[0594] Input: Encrypted data.

[0595] Output: Data stored in the database.

[0596] Step 4:

[0597] AI model learning

[0598] Server: Periodically retrieves data from the database and performs data cleansing. It complements outliers and missing values ​​in the data and updates the machine learning model. Learning is performed based on past medical data, learning the relationship between symptoms, measurement data, and diagnosis results.

[0599] Input: Data stored in a database.

[0600] Output: An updated machine learning model.

[0601] Step 5:

[0602] New Data Transmission

[0603] User: Enters new patient symptoms and measurement data into the terminal during consultation.

[0604] Terminal: Sends new formatted data to the server.

[0605] Input: New symptom and measurement data.

[0606] Output: The new formatted data.

[0607] Step 6:

[0608] Diagnostic Analysis

[0609] Server: Receives new data and feeds it into the machine learning model in real time. The model performs immediate analysis and generates a list of potential cases, indications, treatment recommendations, and appropriate departments.

[0610] Input: New data.

[0611] Output: A list of potential cases, symptoms, recommended treatments, and medical departments based on the analysis results.

[0612] Step 7:

[0613] Send analysis results

[0614] Server: The generated analysis results are re-encrypted and sent to the terminal.

[0615] Input: Analysis results, candidate case list, symptoms, recommended treatment, medical department.

[0616] Output: Encrypted analysis results.

[0617] Step 8:

[0618] Analysis result display

[0619] Terminal: The analysis results are interpreted and visually displayed on a dedicated interface for doctors, who then make a diagnosis based on the results and, if necessary, refer the patient to the appropriate department.

[0620] Input: Encrypted analysis results.

[0621] Output: A visual representation of the analysis results.

[0622] (Application example 1)

[0623] 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."

[0624] Conventional health monitoring systems have limited response capabilities when abnormal values ​​are detected, making it difficult to promptly and appropriately urge users to seek medical attention. There is also a need for a system that can monitor the health status of passengers in autonomous vehicles in real time and take appropriate measures immediately when an abnormality occurs.

[0625] 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.

[0626] In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model to generate case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, means for monitoring the data input by the terminal means in real time and displaying an alarm when an abnormality is detected, and means for providing an optimal route to a medical institution based on the displayed alarm. This enables real-time monitoring of the health condition of passengers and enables prompt and appropriate medical treatment when an abnormality occurs.

[0627] "Symptoms" refers to specific symptoms or abnormalities that indicate the user's health condition.

[0628] "Measurement data" refers to physiological data obtained from the patient's or user's body, such as blood pressure, heart rate, body temperature, and other numerical values.

[0629] "Terminal means" refers to a device through which a user inputs symptoms and measurement data, specifically an electronic device such as a smartphone or a head-mounted display.

[0630] "Server means" refers to a central server that stores data sent from the terminal means and analyzes it using a machine learning model.

[0631] A "machine learning model" refers to an algorithm that uses accumulated data to learn, detect abnormalities, and generate recommended treatments.

[0632] "Analysis results" refers to diagnostic support information such as case candidates, recommended treatments, and abnormality detection generated by the machine learning model.

[0633] "Real-time monitoring" refers to the process of instantly analyzing input data and constantly monitoring for abnormalities.

[0634] "Means for displaying a warning" refers to a function for visually or audibly alerting the user when an abnormality is detected.

[0635] "Guidance route to medical institution" refers to information that provides the most appropriate route to a medical institution and the appropriate response when an abnormality is detected.

[0636] This invention relates to a system that inputs symptoms and measurement data, monitors health conditions in real time based on the data, displays a warning if an abnormality is detected, and guides the user to an appropriate medical institution. Specific embodiments of the system are described below.

[0637] The system mainly consists of the following components:

[0638] 1. Terminal means: A device through which the user inputs symptoms and measurement data, including a smartphone or head-mounted display.

[0639] 2. Server means: A server that accumulates data sent from the terminal means and analyzes it using a machine learning model.

[0640] 3. Machine learning model: An algorithm that detects abnormalities based on accumulated data and provides recommended treatments and guidance routes to the most appropriate medical institution based on the analysis results.

[0641] 4. Means for displaying analysis results: An interface for visually or audibly displaying warnings and analysis results to the user.

[0642] Program processing (explained in natural language)

[0643] Data Collection and Monitoring

[0644] A user inputs their own health data (e.g., blood pressure, heart rate, body temperature) into the terminal means, which formats the input data and transmits it to the server means.

[0645] Real-time analytics

[0646] The server inputs the received data into a machine learning model and performs real-time analysis. If an abnormality is detected during the analysis, the server immediately sends the results to the terminal and displays a warning to the user.

[0647] Guidance and contact to medical institutions

[0648] The server also provides a route to the most appropriate medical institution when an abnormality is detected, and is equipped with a function that automatically notifies the appropriate medical institution or family member as necessary.

[0649] Hardware and software used

[0650] Hardware: Smartphones, head-mounted displays, and in-vehicle devices inside autonomous vehicles.

[0651] Software: Python programs for data analysis, the Requests library for sending and receiving data, and machine learning models (such as TensorFlow or Scikit-learn).

[0652] Specific examples

[0653] Example 1: In-car health monitoring

[0654] User: A passenger who becomes ill in an autonomous vehicle uses their smartphone to enter their blood pressure and heart rate.

[0655] Server: Analyzes the received data and detects abnormally high heart rates.

[0656] Terminal means: Displays a warning to passengers and provides guidance to the nearest medical facility.

[0657] Prompt Sentence Examples

[0658] Design a system that analyzes the following health data in real time for abnormal values, and if an abnormality is detected, suggests routes to the nearest medical facility and contact options.

[0659] *Example of health data: Blood pressure 150 / 90, heart rate 100, body temperature 38℃.

[0660] Please implement this using Python and the Requests library.

[0661] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0662] Step 1:

[0663] The user inputs their own health data (blood pressure, heart rate, body temperature, etc.) into a terminal means (a smartphone or a head-mounted display). The input data is formatted into an appropriate format by the terminal means.

[0664] input:

[0665] Health data (e.g., blood pressure 130 / 85, heart rate 85, body temperature 36.8℃)

[0666] output:

[0667] Formatted Data

[0668] Specific operation:

[0669] The user inputs numerical values ​​through the interface of the terminal means, and the data is converted into JSON format.

[0670] Step 2:

[0671] The terminal means transmits the formatted data to the server means in real time via the Internet.

[0672] input:

[0673] Formatted Data

[0674] output:

[0675] Data sent to the server

[0676] Specific operation:

[0677] Use the Requests library to send data to the server's API with an HTTP POST request.

[0678] Step 3:

[0679] The server means stores the received data, which is then stored in a database for later analysis and model updating.

[0680] input:

[0681] Data sent

[0682] output:

[0683] Data stored in a database

[0684] Specific operation:

[0685] The received data is stored in a database using a database management system (e.g., MySQL, PostgreSQL).

[0686] Step 4:

[0687] The server inputs the accumulated data into a machine learning model and performs real-time analysis, thereby detecting the presence or absence of abnormalities.

[0688] input:

[0689] Data stored in a database

[0690] Machine learning models

[0691] output:

[0692] Analysis results showing whether or not there are any abnormalities

[0693] Specific operation:

[0694] Using Python machine learning libraries (e.g., TensorFlow, Scikit-learn), the received data is input into a model to generate analysis results.

[0695] Step 5:

[0696] The server unit transmits the generated analysis results to the terminal unit, which also include a warning message if an abnormality is detected.

[0697] input:

[0698] Analysis results

[0699] output:

[0700] Analysis results sent to the terminal means

[0701] Specific operation:

[0702] The analysis results are reformatted in JSON format and sent to the terminal means via an HTTP POST request.

[0703] Step 6:

[0704] The terminal means displays the received analysis results to the user, and if an abnormality is detected, a warning message is displayed.

[0705] input:

[0706] Received analysis results

[0707] output:

[0708] Results and warnings displayed to the user

[0709] Specific operation:

[0710] Results are displayed visually through a smartphone or head-mounted display interface, and audio alerts are provided if required.

[0711] Step 7:

[0712] When a warning is displayed, the terminal device also provides a route to the most appropriate medical institution, and automatically notifies the appropriate medical institution or family member as necessary.

[0713] input:

[0714] Warning messages based on analysis results

[0715] output:

[0716] Routes to medical institutions

[0717] Automatic notifications when needed

[0718] Specific operation:

[0719] It uses GPS data to search for the nearest medical facility, displays routes on a map, and notifies medical facilities and family members via phone or email based on contact information.

[0720] 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.

[0721] The present invention provides a system that takes user emotions into consideration during diagnosis, reducing the chance of overlooking abnormal values ​​and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, a machine learning model, and an emotion engine. Detailed embodiments of this system are described below.

[0722] Overall system overview

[0723] The system consists of the following main components:

[0724] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[0725] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[0726] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. It also provides predictions and diagnostic support for new data.

[0727] 4. Display of analysis results: An interface that visually displays the analysis results on the terminal, allowing users to immediately check the analysis results.

[0728] 5. Emotion Engine: An algorithm that recognizes the user's emotions and adjusts the display of analysis results and the provision of support. It infers emotions from the user's words, facial expressions, and typing pace.

[0729] Program processing (explained in natural language)

[0730] Data collection and storage

[0731] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the terminal.

[0732] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[0733] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[0734] AI learning

[0735] Server: Periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[0736] Diagnostic and emotional analysis

[0737] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[0738] Terminal: Sends the entered data to the server.

[0739] Server: Inputs incoming data into machine learning models for real-time analysis. The analysis step generates candidate cases, their symptoms, and treatment recommendations.

[0740] Emotion Engine: At the same time, it analyzes the user's input, facial expressions, and words to infer their emotional state. The emotion engine identifies emotions such as impatience, confusion, and certainty.

[0741] Analysis output and emotion-based adjustment

[0742] Server: Based on the analysis results, if a specific medical department is required, the server identifies and recommends that department.

[0743] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[0744] Server: Sends the analysis results to the device.

[0745] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[0746] Specific examples

[0747] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[0748] User: Patient B visits the clinic complaining of headache and vomiting. His blood pressure is 160 / 100 mmHg, his blood sugar is 180 mg / dL, and his body temperature is 37.5°C. The results are entered into the terminal. The emotion engine also recognizes that the user is feeling a little impatient.

[0749] Terminal: Formats input data and sends it to the server.

[0750] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[0751] Server: Generates a list of potential cases of hypothyroidism and diabetes, including symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), and recommends thyroid clinic visits.

[0752] Emotion Engine: Detects the user's impatience and displays the analysis results with concise and specific alerts.

[0753] Server: Sends analysis results to the device.

[0754] Terminal: Displays analysis results (case candidates, symptoms, recommended treatments, and department information) and provides additional support information and instructions to reduce user impatience.

[0755] This system is expected to lead to improved diagnostic accuracy and earlier treatment. In addition, the introduction of an emotion engine will provide flexible and accurate support according to the user's situation, reducing stress in medical settings and enabling more efficient medical treatment.

[0756] The processing flow will be explained below.

[0757] Step 1:

[0758] During consultation, the user enters the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[0759] Step 2:

[0760] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[0761] Step 3:

[0762] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[0763] Step 4:

[0764] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[0765] Step 5:

[0766] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[0767] Step 6:

[0768] The terminal transmits the input data to the server again.

[0769] Step 7:

[0770] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[0771] Step 8:

[0772] The emotion engine collects emotional data from the device through the user's facial expressions, voice, input speed, etc., and estimates the user's emotional state.

[0773] Step 9:

[0774] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[0775] Step 10:

[0776] The server adjusts the analysis results in cooperation with the emotion engine and determines the content and method of display according to the user's emotional state.

[0777] Step 11:

[0778] The server transmits the generated analysis results and the adjustment results from the emotion engine to the terminal.

[0779] Step 12:

[0780] The device displays the analysis results to the user. If the user is feeling anxious or stressed, the device displays the analysis results concisely and provides additional support information or alerts.

[0781] Step 13:

[0782] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[0783] Example 2

[0784] 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."

[0785] Conventional diagnostic systems do not take into account the user's emotional state in the process from inputting symptoms and measurement data to outputting analysis results, resulting in problems such as insufficient diagnostic accuracy and insufficient reduction of user stress. Furthermore, improving the accuracy of case candidates and recommended treatments remains a challenge.

[0786] 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 an input device means for inputting symptoms and measurement data, a data processing device means for storing and analyzing data transmitted from the input device means, an analysis device means for analyzing the data stored in the data processing device means based on a machine learning algorithm and generating case candidates and recommended treatments, a display device means for transmitting and displaying the analysis results generated by the analysis device means to the input device means, and an emotion analysis device means for adjusting the analysis results based on the emotional state of the user. This enables improved data accuracy and user-friendly display of analysis results, thereby realizing efficient and stress-free medical treatment in medical settings.

[0787] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by a patient.

[0788] "Measurement data" refers to values ​​that quantitatively indicate the patient's physical condition, such as blood pressure, blood sugar level, and body temperature.

[0789] "Input device means" refers to a device for inputting symptoms and measurement data, and includes a personal computer, tablet, etc.

[0790] The "data processing device means" is a device that receives data sent from the input device means and stores it in a database.

[0791] A "machine learning algorithm" is an algorithm that learns patterns based on large amounts of data and makes predictions and classifications.

[0792] The "analysis device means" is a device that analyzes the accumulated data based on a machine learning algorithm and generates candidate cases and recommended treatments.

[0793] The "display device means" is a device that visually presents the analysis results generated by the analysis device means to the user.

[0794] The "emotion analysis device means" is a device that estimates emotions from the user's input state, facial expressions, words, etc., and adjusts the content and method of displaying the analysis results.

[0795] "Update means" refers to the means for periodically improving and updating the machine learning algorithm based on accumulated data.

[0796] "Learning improvement means" refers to means for improving the accuracy of predicting case candidates using machine learning algorithms.

[0797] The "medical department recommendation means" is a means for identifying an appropriate medical department based on the analysis results and recommending it to the user.

[0798] The "information display means" is a means for displaying recommended medical department information on the input device means.

[0799] The present invention provides a system that reduces the oversight of abnormal values ​​and promotes early treatment by taking a user's emotions into consideration during diagnosis. This system includes an input device means for a user to input a patient's symptoms and measurement data, a data processing device means for storing and analyzing the data, an analysis device means for performing analysis based on the stored data using a machine learning algorithm, a display device means for displaying the analysis results, and an emotion analysis device means for adjusting the display of the analysis results based on the user's emotional state. Detailed embodiments of this system are described below.

[0800] Data collection and storage

[0801] During medical examinations, a user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood glucose level 180 mg / dL, body temperature 37.5°C) into an input device means such as a personal computer or tablet. The input data is converted into a predetermined format within the terminal, and personally identifiable information is deleted. The formatted data is then transmitted to the data processing device means via a security protocol (e.g., HTTPS). The data processing device means stores the received data in a database and uses it for subsequent analysis and machine learning.

[0802] AI learning

[0803] The data processing device periodically retrieves accumulated data from the database and refreshes the model using a machine learning algorithm. Based on past medical data, the system learns the relationship between symptoms, measurement data, and diagnostic results. Random forests, neural networks, etc. are used as machine learning algorithms.

[0804] Diagnostic and emotional analysis

[0805] When a new patient is seen, the user again inputs the symptoms and measurement data into the terminal. The terminal reformats the input data and transmits it to the data processing means. The data processing means immediately inputs the received data into a machine learning algorithm for real-time analysis. The analysis step generates candidate cases, symptoms for each candidate, and recommended treatments.

[0806] At the same time, the emotion analyzer means analyzes the user's input status, facial expressions, and words to estimate the user's emotional state. The emotion analyzer means identifies emotions such as impatience, confusion, and certainty.

[0807] Analysis output and emotion-based adjustment

[0808] If a specific medical department is required based on the analysis results, the medical department is identified and recommended. The emotion analysis device means adjusts the generated analysis results according to the user's emotional state and determines the appropriate display content and method. The adjusted analysis results are sent back to the terminal and displayed to the user by the display device means. Depending on the emotional state, alerts and additional support information are provided.

[0809] Specific examples

[0810] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[0811] When the user visits the clinic complaining of Patient B's headache and vomiting, the user inputs the measurement results of blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, and body temperature 37.5°C into the input device means. At the same time, the emotion analysis device means recognizes that the user is feeling impatient. The terminal formats the input data and transmits it to the data processing device means via a security protocol.

[0812] The data processing means receives the data and stores it in a database. Machine learning algorithms are then used to generate a list of potential cases of hypothyroidism and diabetes, each with their respective symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), as well as recommendations for thyroid clinic visits.

[0813] The emotion analysis device means detects the user's impatience and adjusts the display of the analysis results to emphasize concise and specific alerts. Finally, the adjusted analysis results are sent to the terminal and displayed to the user. Additional support information and instructions may also be provided to reduce the user's impatience.

[0814] Prompt Sentence Examples

[0815] Below are some example prompts to input to a generative AI model:

[0816] "Analyze the following patient data and provide a possible diagnosis and recommended treatment: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C."

[0817] "When users are in a hurry, please display the diagnostic results in a concise and easy-to-understand manner."

[0818] "A new patient has arrived. After entering their symptoms and measurements, the emotion engine has detected impatience. Please adjust your analysis to take this information into account."

[0819] This allows the system to not only provide accurate and prompt diagnostic support, but also to respond flexibly while taking into consideration the user's feelings.

[0820] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0821] Step 1:

[0822] The user enters patient information

[0823] User: During medical examination, the user inputs the patient's symptoms (eg, headache, vomiting) and measurement data (eg, blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the input device means.

[0824] Input and output: The user inputs symptoms and measurement data into the input device, and the data is passed to the terminal.

[0825] Specific operation: The doctor uses the keyboard to enter measurement values ​​and symptoms into a dedicated input form and clicks the "Send" button.

[0826] Step 2:

[0827] The device formats the data and sends it to the server

[0828] Terminal: Converts the entered data into a specified format (e.g., JSON format), deletes any personally identifiable information, and then sends it to the server.

[0829] Input and Output: Takes raw input data and outputs formatted data that is sent to the server.

[0830] What it does: A program on the device filters and formats the data, then sends it securely to a server using the HTTPS protocol.

[0831] Step 3:

[0832] The server stores the data

[0833] Server: Stores the received data in a database and uses it for subsequent analysis and machine learning.

[0834] Input and Output: Receives formatted data and stores it in a database, providing feedback to confirm successful storage.

[0835] Specific behavior: The server adds the received data as a new entry in the database and generates a message indicating the save was successful.

[0836] Step 4:

[0837] The server updates the machine learning model.

[0838] Server: Periodically retrieves accumulated data from the database and refreshes the model using machine learning algorithms.

[0839] Input and Output: Retrieving historical data from the database and outputting an updated model.

[0840] What it does: A scheduled task on the server extracts all new data at a specified time (e.g., every weekend) and retrains it using machine learning algorithms.

[0841] Step 5:

[0842] User enters new patient information

[0843] User: Enters the new patient's symptoms and measurement data again into the input device means.

[0844] Input and Output: New symptoms and measurement data are entered and sent to the terminal.

[0845] Specific operation: As mentioned above, the doctor enters the patient's new symptoms and measurement data and clicks the "Submit" button.

[0846] Step 6:

[0847] The device sends data

[0848] Terminal: Reformats the entered data and sends it to the server.

[0849] Input and Output: Accepts raw data and sends formatted data to the server.

[0850] Specific behavior: Formats and sends the data a second time. Uses HTTPS protocol for security.

[0851] Step 7:

[0852] The server performs the analysis

[0853] Server: Inputs the received data into a machine learning algorithm for real-time analysis, generating candidate cases, their symptoms, and treatment recommendations.

[0854] Input and Output: Formatted data is input into the analysis and output is a list of potential cases and treatment recommendations.

[0855] What it does: It runs new data through machine learning algorithms, performs calculations to produce predictions, and temporarily stores the results.

[0856] Step 8:

[0857] The emotion engine performs emotion analysis

[0858] Emotion engine: Analyzes the user's input, facial expressions, and words to infer their emotional state. It identifies emotions such as impatience, confusion, and certainty.

[0859] Input and output: Receives user input speed and facial expression data and outputs estimated emotional state.

[0860] Specific operation: The emotion analysis algorithm estimates and outputs emotions based on the user's input speed, context, and facial expression data from the camera.

[0861] Step 9:

[0862] The server recommends a medical department

[0863] Server: Based on the analysis results, if a specific medical department is required, identify and recommend that department.

[0864] Input and output: Receives a list of analysis results and outputs recommended medical departments.

[0865] Specific operation: The analysis engine matches case candidates with medical departments and adds the most suitable medical departments to the recommendation list.

[0866] Step 10:

[0867] The server adjusts the analysis results

[0868] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[0869] Input and output: The initial analysis result and the estimated emotional state are input, and the adjusted analysis result is output.

[0870] Specific behavior: Dynamically change the display format and emphasis of results based on feedback from the emotion engine.

[0871] Step 11:

[0872] The server sends the analysis results

[0873] Server: Sends the adjusted analysis results to the device.

[0874] Input and output: Receives refined analysis results and sends them to the terminal.

[0875] Specific operation: Data is securely sent to the device using the HTTPS protocol.

[0876] Step 12:

[0877] The device displays the analysis results.

[0878] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[0879] Input and Output: Receives the adjusted analysis results, converts them into a display format for the user, and displays them.

[0880] What it does: Data is displayed in the end-user interface, notifications are activated, and warnings and additional information are provided when necessary.

[0881] This completes the entire process of the invention, improving diagnostic accuracy and providing user-friendly support.

[0882] (Application example 2)

[0883] 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."

[0884] Conventional medical systems only focus on analysis results based on symptoms and measurement data, and do not take the user's emotional state into consideration, which can lead to problems such as overlooking abnormal values ​​during diagnosis and not providing appropriate advice to the user.It also makes it difficult to recommend medicines and supplements that correspond to the user's emotional state.

[0885] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model and generating case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and means for recommending appropriate medicines and supplements. This enables more accurate diagnoses and appropriate advice and recommendations by taking the user's emotional state into consideration.

[0886] "Terminal means" refers to a device for inputting symptoms and measurement data, and includes smartphones, tablets, etc.

[0887] The term "server means" refers to a computer system that receives data sent from the terminal means and stores and analyzes the data.

[0888] A "machine learning model" is an algorithm that learns from accumulated data and generates case candidates and recommended treatments.

[0889] The "means for displaying the analysis results" refers to an interface for visually presenting the generated analysis results to the user.

[0890] The "emotion engine" is an algorithm for estimating the user's emotional state and adjusting the display of the analysis results accordingly.

[0891] "Means for recommending appropriate medicines and supplements" refers to a function that suggests necessary medicines and supplements based on the user's input data and analysis results.

[0892] This invention realizes a system including a terminal means for inputting symptoms and measurement data, a server means for storing data transmitted from the terminal means, a server means for analyzing the stored data based on a machine learning model and generating candidate cases and recommended treatments, a means for transmitting the generated analysis results to the terminal means and displaying them, an emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and a means for recommending appropriate medicines and supplements.

[0893] Program processing

[0894] Data collection and storage

[0895] The user inputs symptoms and measurement data into a terminal such as a smartphone. This data is formatted and sent to a server. The server stores the received data in a database and uses it for subsequent analysis and machine learning model training.

[0896] AI learning

[0897] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results. This process uses machine learning algorithms (e.g., TensorFlow, PyTorch).

[0898] Health status assessment and emotion analysis

[0899] When a user inputs new data, it is sent from the terminal device to the server. The server then inputs the received data into a machine learning model for real-time analysis. In the analysis step, case candidates, symptoms, and recommended treatments for each candidate are generated. The emotion engine also estimates the user's emotional state from the user's input, facial expressions, and speech patterns, and adjusts the display of the analysis results accordingly.

[0900] Alerts and Recommendations

[0901] The server recommends appropriate medicines and supplements based on the analysis results and the user's emotional state. The generated information is sent to the terminal and visually displayed to the user. Simple and specific alerts are highlighted for users who are feeling particularly anxious or stressed.

[0902] Specific examples

[0903] For example, if a patient complains of headache and fatigue and their blood pressure is measured at 150 / 90 mmHg, they can enter this information into their smartphone and send it to the server. The server analyzes this information and presents possible cases of hypertension along with appropriate treatments (e.g., blood pressure-lowering medication). At the same time, the emotion engine detects the user's stress level and recommends additional relaxation methods and supplements to relieve stress.

[0904] Example prompts for generative AI models

[0905] Please enter your health data (e.g. headache, blood pressure 150 / 90 mmHg, fatigue).

[0906] Assess your emotional state (e.g., stress, impatience).

[0907] Recommend necessary medications and supplements to users based on their health status.

[0908] When making recommendations, tailor alerts to the user's emotional state.

[0909] This system allows users to understand their health condition in detail and receive appropriate medicines, supplements, and treatments efficiently. In particular, the emotional engine reduces the user's psychological burden and provides an effective medical experience.

[0910] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0911] Step 1:

[0912] The user inputs symptoms and measurement data into a terminal such as a smartphone. The input data (e.g., headache, blood pressure 150 / 90 mmHg, fatigue) is formatted by the terminal and personal identifying information is deleted.

[0913] Step 2:

[0914] The terminal means transmits the formatted data to the server means, and the transmission process protects the data using a security protocol (e.g., HTTPS).

[0915] Step 3:

[0916] The server stores the received data in a database. The database uses a relational database (e.g., MySQL) to store the data in a structured manner.

[0917] Step 4:

[0918] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. A machine learning algorithm (e.g., TensorFlow) is used to learn the relationship between symptoms and diagnosis results from past medical data. During this process, training and validation are performed using large amounts of data.

[0919] Step 5:

[0920] When a user inputs new symptoms and measurement data, the data is sent from the terminal device to the server, which then inputs the received data into a machine learning model for real-time analysis. The analysis results in the generation of candidate cases and recommended treatments.

[0921] Step 6:

[0922] The server uses an emotion engine to estimate the user's emotional state, which is estimated from input context, facial expressions, and speech patterns, and in some cases, a natural language processing engine (e.g., Google Cloud Natural Language API) is used.

[0923] Step 7:

[0924] The server adjusts the display of the analysis results based on the analysis results and the user's estimated emotional state. For example, if a user is feeling anxious, the server will display the analysis results concisely and specifically, highlighting recommendations for necessary medicines and supplements.

[0925] Step 8:

[0926] The server sends the adjusted analysis results and recommendations to the terminal means, which visually displays the information to the user, allowing the user to understand their health status and select appropriate medicines and supplements.

[0927] This system enables diagnosis and recommendations that take into account the user's emotional state, providing highly accurate diagnoses and effective medical support.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] [Third embodiment]

[0932] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0933] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0934] 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).

[0935] 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.

[0936] 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.

[0937] 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).

[0938] 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.

[0939] 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.

[0940] 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.

[0941] 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.

[0942] 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.

[0943] 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."

[0944] The present invention provides a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, and a machine learning model. Detailed embodiments of this system are described below.

[0945] Overall system overview

[0946] The system consists of the following main components:

[0947] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[0948] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[0949] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. This allows predictions and diagnostic support for new data.

[0950] 4. Display means for analysis results: An interface that visually displays the analysis results on the terminal means, allowing the user to immediately check the analysis results.

[0951] Program processing (explained in natural language)

[0952] Data collection and storage

[0953] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure, blood sugar level, body temperature) are entered into the terminal.

[0954] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[0955] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[0956] AI learning

[0957] Server: Periodically retrieves data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results.

[0958] Analysis at the time of diagnosis

[0959] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[0960] Terminal: Sends the entered data to the server.

[0961] Server: Inputs the received data into the machine learning model and performs analysis. As a result, a list of candidate cases, their symptoms, recommended treatments, and appropriate medical departments are generated.

[0962] Output of analysis results

[0963] Server: Sends the generated analysis results to the terminal.

[0964] Terminal: Displays the analysis results to the user.

[0965] Specific examples

[0966] A concrete example from data entry at the first consultation to output of analysis results

[0967] User: Patient A visits the clinic complaining of headache and vomiting. He measures his blood pressure at 160 / 100 mmHg, blood sugar at 180 mg / dL, and body temperature at 37.5°C and enters the results into the terminal.

[0968] Terminal: Formats input data and sends it to the server.

[0969] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[0970] Server: Generates a list of potential cases for hypertension and diabetes, including their symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (ACE inhibitors and insulin therapy), and recommends internal medicine as the appropriate specialty.

[0971] Server: Sends analysis results to the device.

[0972] Terminal: Displays the analysis results to the user, who is a doctor, and issues a referral letter to an internal medicine department.

[0973] This system is expected to lead to improved diagnostic accuracy and earlier treatment.

[0974] The processing flow will be explained below.

[0975] Step 1:

[0976] During consultation, the user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[0977] Step 2:

[0978] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[0979] Step 3:

[0980] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[0981] Step 4:

[0982] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[0983] Step 5:

[0984] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[0985] Step 6:

[0986] The terminal transmits the input data to the server again.

[0987] Step 7:

[0988] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[0989] Step 8:

[0990] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[0991] Step 9:

[0992] The server then sends the generated analysis results to the terminal, which include a list of potential cases, symptoms for each case, recommended treatment, and recommended medical department.

[0993] Step 10:

[0994] The terminal displays the analysis results to the user.

[0995] Step 11:

[0996] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[0997] Example 1

[0998] 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."

[0999] In current medical settings, there are problems such as the risk of overlooking abnormal values ​​during diagnosis and the difficulty of quickly referring patients to the appropriate department. In particular, efficiently analyzing large amounts of patient data and providing highly accurate diagnostic support are important challenges for doctors. This system aims to provide diagnostic support that quickly analyzes symptoms and measurement data and promotes early treatment.

[1000] 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.

[1001] In this invention, the server includes an information terminal means for inputting symptoms and measurement data, a means for accumulating data transmitted from the information terminal means and saving it in a database, a means for periodically updating a machine learning model using the accumulated data and learning from past clinical data, a means for analyzing new data in real time based on the machine learning model and generating candidate cases and recommended treatments, and a means for transmitting the generated analysis results to the information terminal means and visually displaying them. This enables efficient analysis of a large amount of patient data, improves diagnostic accuracy, and enables prompt referral to the appropriate department.

[1002] "Symptom" refers to a sign or characteristic of a disease or health condition exhibited by a patient.

[1003] "Measurement data" refers to data that indicates biological information such as blood pressure, blood sugar level, and body temperature.

[1004] "Information terminal means" refers to a device that allows the user to input symptoms and measurement data, and includes a personal computer or tablet terminal.

[1005] The "server means" refers to a computer system having the function of receiving data sent from the information terminal means and storing it in a database.

[1006] A "database" is a storage device that centrally manages accumulated data and allows it to be retrieved when needed.

[1007] A "machine learning model" is an algorithm that learns from accumulated data and makes predictions and inferences about new data.

[1008] "Real-time analysis" refers to the process of performing analysis immediately as new data is entered.

[1009] "Case candidate" refers to a disease or health condition that is suspected based on symptoms and measurement data.

[1010] "Recommended treatment" refers to a treatment method that can be applied to a candidate case.

[1011] "Visually displaying" means showing the analysis results on a screen or the like in a format that is easy for the user to understand.

[1012] A "referral letter" is an official document used to refer a patient to another medical department or specialist.

[1013] This invention is a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. The system includes a data input terminal, a server for storing and analyzing data, a machine learning model, and an interface for displaying the analysis results.

[1014] Detailed Embodiment of the System

[1015] Data Entry Terminal

[1016] The user enters the patient's symptoms and measurement data into a data entry terminal, which can be a standard PC or tablet. The entered data is formatted, personal identifying information is removed, and the data is sent to a server via an encrypted protocol (e.g., HTTPS).

[1017] Server for data storage and analysis

[1018] The server receives data sent from the information terminal and stores it in a database. The server also periodically retrieves data from the database and updates the machine learning model. The update is performed after data cleansing and preprocessing.

[1019] Machine learning models

[1020] The machine learning model is an algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and appropriate medical departments. When new data is input, it is analyzed immediately in real time and generates results.

[1021] Interface for displaying analysis results

[1022] The generated analysis results are then sent back to the device and visually displayed to the user, who is then a doctor who can make a diagnosis based on the displayed analysis results and, if necessary, refer the patient to the appropriate department.

[1023] Specific examples

[1024] A concrete example from data entry at the first consultation to output of analysis results

[1025] 1. User: Patient A comes to the clinic complaining of headache and vomiting. He enters his blood pressure (160 / 100 mmHg), blood glucose (180 mg / dL), and body temperature (37.5°C) into the terminal.

[1026] 2. Terminal: Formats input data and sends it to the server using an encryption protocol.

[1027] 3. Server: Stores the received data in a database and analyzes it in real time using machine learning models.

[1028] 4. Server: Generates a list of candidate cases for hypertension and diabetes, and recommends their symptoms (headache, vomiting, elevated blood sugar levels), recommended treatments (ACE inhibitors, insulin therapy), and the appropriate medical department for treatment: internal medicine.

[1029] 5. Server: Sends the analysis results to the device.

[1030] 6. Terminal: The analysis results are displayed to the user (physician) and a referral letter to an internal medicine department is issued if necessary.

[1031] Prompt Sentence Examples

[1032] "Patient A complains of headache and vomiting. Measurements include blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, and temperature 37.5°C. Based on these data, please provide appropriate case candidates, indications, recommended treatment, and department."

[1033] This system will enable efficient analysis of large amounts of patient data, improving diagnostic accuracy and enabling prompt referral to the appropriate department.

[1034] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1035] Step 1:

[1036] Data Entry

[1037] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the information terminal.

[1038] Input: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C.

[1039] Output: Formatted symptom and measurement data.

[1040] Step 2:

[1041] Data transmission

[1042] Terminal: Formats the entered data and removes any personally identifiable information. The data is then sent to the server using an encrypted protocol (e.g., HTTPS).

[1043] Input: Formatted symptom and measurement data.

[1044] Output: The encrypted data.

[1045] Step 3:

[1046] Data accumulation

[1047] Server: Stores the received data in a database. The data is identified for each patient and classified appropriately.

[1048] Input: Encrypted data.

[1049] Output: Data stored in the database.

[1050] Step 4:

[1051] AI model learning

[1052] Server: Periodically retrieves data from the database and performs data cleansing. It complements outliers and missing values ​​in the data and updates the machine learning model. Learning is performed based on past medical data, learning the relationship between symptoms, measurement data, and diagnosis results.

[1053] Input: Data stored in a database.

[1054] Output: An updated machine learning model.

[1055] Step 5:

[1056] New Data Transmission

[1057] User: Enters new patient symptoms and measurement data into the terminal during consultation.

[1058] Terminal: Sends new formatted data to the server.

[1059] Input: New symptom and measurement data.

[1060] Output: The new formatted data.

[1061] Step 6:

[1062] Diagnostic Analysis

[1063] Server: Receives new data and feeds it into the machine learning model in real time. The model performs immediate analysis and generates a list of potential cases, indications, treatment recommendations, and appropriate departments.

[1064] Input: New data.

[1065] Output: A list of potential cases, symptoms, recommended treatments, and medical departments based on the analysis results.

[1066] Step 7:

[1067] Send analysis results

[1068] Server: The generated analysis results are re-encrypted and sent to the terminal.

[1069] Input: Analysis results, candidate case list, symptoms, recommended treatment, medical department.

[1070] Output: Encrypted analysis results.

[1071] Step 8:

[1072] Analysis result display

[1073] Terminal: The analysis results are interpreted and visually displayed on a dedicated interface for doctors, who then make a diagnosis based on the results and, if necessary, refer the patient to the appropriate department.

[1074] Input: Encrypted analysis results.

[1075] Output: A visual representation of the analysis results.

[1076] (Application example 1)

[1077] 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."

[1078] Conventional health monitoring systems have limited response capabilities when abnormal values ​​are detected, making it difficult to promptly and appropriately urge users to seek medical attention. There is also a need for a system that can monitor the health status of passengers in autonomous vehicles in real time and take appropriate measures immediately when an abnormality occurs.

[1079] 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.

[1080] In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model to generate case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, means for monitoring the data input by the terminal means in real time and displaying an alarm when an abnormality is detected, and means for providing an optimal route to a medical institution based on the displayed alarm. This enables real-time monitoring of the health condition of passengers and enables prompt and appropriate medical treatment when an abnormality occurs.

[1081] "Symptoms" refers to specific symptoms or abnormalities that indicate the user's health condition.

[1082] "Measurement data" refers to physiological data obtained from the patient's or user's body, such as blood pressure, heart rate, body temperature, and other numerical values.

[1083] "Terminal means" refers to a device through which a user inputs symptoms and measurement data, specifically an electronic device such as a smartphone or a head-mounted display.

[1084] "Server means" refers to a central server that stores data sent from the terminal means and analyzes it using a machine learning model.

[1085] A "machine learning model" refers to an algorithm that uses accumulated data to learn, detect abnormalities, and generate recommended treatments.

[1086] "Analysis results" refers to diagnostic support information such as case candidates, recommended treatments, and abnormality detection generated by the machine learning model.

[1087] "Real-time monitoring" refers to the process of instantly analyzing input data and constantly monitoring for abnormalities.

[1088] "Means for displaying a warning" refers to a function for visually or audibly alerting the user when an abnormality is detected.

[1089] "Guidance route to medical institution" refers to information that provides the most appropriate route to a medical institution and the appropriate response when an abnormality is detected.

[1090] This invention relates to a system that inputs symptoms and measurement data, monitors health conditions in real time based on the data, displays a warning if an abnormality is detected, and guides the user to an appropriate medical institution. Specific embodiments of the system are described below.

[1091] The system mainly consists of the following components:

[1092] 1. Terminal means: A device through which the user inputs symptoms and measurement data, including a smartphone or head-mounted display.

[1093] 2. Server means: A server that accumulates data sent from the terminal means and analyzes it using a machine learning model.

[1094] 3. Machine learning model: An algorithm that detects abnormalities based on accumulated data and provides recommended treatments and guidance routes to the most appropriate medical institution based on the analysis results.

[1095] 4. Means for displaying analysis results: An interface for visually or audibly displaying warnings and analysis results to the user.

[1096] Program processing (explained in natural language)

[1097] Data Collection and Monitoring

[1098] A user inputs their own health data (e.g., blood pressure, heart rate, body temperature) into the terminal means, which formats the input data and transmits it to the server means.

[1099] Real-time analytics

[1100] The server inputs the received data into a machine learning model and performs real-time analysis. If an abnormality is detected during the analysis, the server immediately sends the results to the terminal and displays a warning to the user.

[1101] Guidance and contact to medical institutions

[1102] The server also provides a route to the most appropriate medical institution when an abnormality is detected, and is equipped with a function that automatically notifies the appropriate medical institution or family member as necessary.

[1103] Hardware and software used

[1104] Hardware: Smartphones, head-mounted displays, and in-vehicle devices inside autonomous vehicles.

[1105] Software: Python programs for data analysis, the Requests library for sending and receiving data, and machine learning models (such as TensorFlow or Scikit-learn).

[1106] Specific examples

[1107] Example 1: In-car health monitoring

[1108] User: A passenger who becomes ill in an autonomous vehicle uses their smartphone to enter their blood pressure and heart rate.

[1109] Server: Analyzes the received data and detects abnormally high heart rates.

[1110] Terminal means: Displays a warning to passengers and provides guidance to the nearest medical facility.

[1111] Prompt Sentence Examples

[1112] Design a system that analyzes the following health data in real time for abnormal values, and if an abnormality is detected, suggests routes to the nearest medical facility and contact options.

[1113] *Example of health data: Blood pressure 150 / 90, heart rate 100, body temperature 38℃.

[1114] Please implement this using Python and the Requests library.

[1115] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1116] Step 1:

[1117] The user inputs their own health data (blood pressure, heart rate, body temperature, etc.) into a terminal means (a smartphone or a head-mounted display). The input data is formatted into an appropriate format by the terminal means.

[1118] input:

[1119] Health data (e.g., blood pressure 130 / 85, heart rate 85, body temperature 36.8℃)

[1120] output:

[1121] Formatted Data

[1122] Specific operation:

[1123] The user inputs numerical values ​​through the interface of the terminal means, and the data is converted into JSON format.

[1124] Step 2:

[1125] The terminal means transmits the formatted data to the server means in real time via the Internet.

[1126] input:

[1127] Formatted Data

[1128] output:

[1129] Data sent to the server

[1130] Specific operation:

[1131] Use the Requests library to send data to the server's API with an HTTP POST request.

[1132] Step 3:

[1133] The server means stores the received data, which is then stored in a database for later analysis and model updating.

[1134] input:

[1135] Data sent

[1136] output:

[1137] Data stored in a database

[1138] Specific operation:

[1139] The received data is stored in a database using a database management system (e.g., MySQL, PostgreSQL).

[1140] Step 4:

[1141] The server inputs the accumulated data into a machine learning model and performs real-time analysis, thereby detecting the presence or absence of abnormalities.

[1142] input:

[1143] Data stored in a database

[1144] Machine learning models

[1145] output:

[1146] Analysis results showing whether or not there are any abnormalities

[1147] Specific operation:

[1148] Using Python machine learning libraries (e.g., TensorFlow, Scikit-learn), the received data is input into a model to generate analysis results.

[1149] Step 5:

[1150] The server unit transmits the generated analysis results to the terminal unit, which also include a warning message if an abnormality is detected.

[1151] input:

[1152] Analysis results

[1153] output:

[1154] Analysis results sent to the terminal means

[1155] Specific operation:

[1156] The analysis results are reformatted in JSON format and sent to the terminal means via an HTTP POST request.

[1157] Step 6:

[1158] The terminal means displays the received analysis results to the user, and if an abnormality is detected, a warning message is displayed.

[1159] input:

[1160] Received analysis results

[1161] output:

[1162] Results and warnings displayed to the user

[1163] Specific operation:

[1164] Results are displayed visually through a smartphone or head-mounted display interface, and audio alerts are provided if required.

[1165] Step 7:

[1166] When a warning is displayed, the terminal device also provides a route to the most appropriate medical institution, and automatically notifies the appropriate medical institution or family member as necessary.

[1167] input:

[1168] Warning messages based on analysis results

[1169] output:

[1170] Routes to medical institutions

[1171] Automatic notifications when needed

[1172] Specific operation:

[1173] It uses GPS data to search for the nearest medical facility, displays routes on a map, and notifies medical facilities and family members via phone or email based on contact information.

[1174] 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.

[1175] The present invention provides a system that takes user emotions into consideration during diagnosis, reducing the chance of overlooking abnormal values ​​and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, a machine learning model, and an emotion engine. Detailed embodiments of this system are described below.

[1176] Overall system overview

[1177] The system consists of the following main components:

[1178] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[1179] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[1180] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. It also provides predictions and diagnostic support for new data.

[1181] 4. Display of analysis results: An interface that visually displays the analysis results on the terminal, allowing users to immediately check the analysis results.

[1182] 5. Emotion Engine: An algorithm that recognizes the user's emotions and adjusts the display of analysis results and the provision of support. It infers emotions from the user's words, facial expressions, and typing pace.

[1183] Program processing (explained in natural language)

[1184] Data collection and storage

[1185] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the terminal.

[1186] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[1187] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[1188] AI learning

[1189] Server: Periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[1190] Diagnostic and emotional analysis

[1191] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[1192] Terminal: Sends the entered data to the server.

[1193] Server: Inputs incoming data into machine learning models for real-time analysis. The analysis step generates candidate cases, their symptoms, and treatment recommendations.

[1194] Emotion Engine: At the same time, it analyzes the user's input, facial expressions, and words to infer their emotional state. The emotion engine identifies emotions such as impatience, confusion, and certainty.

[1195] Analysis output and emotion-based adjustment

[1196] Server: Based on the analysis results, if a specific medical department is required, the server identifies and recommends that department.

[1197] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[1198] Server: Sends the analysis results to the device.

[1199] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[1200] Specific examples

[1201] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[1202] User: Patient B visits the clinic complaining of headache and vomiting. His blood pressure is 160 / 100 mmHg, his blood sugar is 180 mg / dL, and his body temperature is 37.5°C. The results are entered into the terminal. The emotion engine also recognizes that the user is feeling a little impatient.

[1203] Terminal: Formats input data and sends it to the server.

[1204] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[1205] Server: Generates a list of potential cases of hypothyroidism and diabetes, including symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), and recommends thyroid clinic visits.

[1206] Emotion Engine: Detects the user's impatience and displays the analysis results with concise and specific alerts.

[1207] Server: Sends analysis results to the device.

[1208] Terminal: Displays analysis results (case candidates, symptoms, recommended treatments, and department information) and provides additional support information and instructions to reduce user impatience.

[1209] This system is expected to lead to improved diagnostic accuracy and earlier treatment. In addition, the introduction of an emotion engine will provide flexible and accurate support according to the user's situation, reducing stress in medical settings and enabling more efficient medical treatment.

[1210] The processing flow will be explained below.

[1211] Step 1:

[1212] During consultation, the user enters the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[1213] Step 2:

[1214] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[1215] Step 3:

[1216] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[1217] Step 4:

[1218] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[1219] Step 5:

[1220] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[1221] Step 6:

[1222] The terminal transmits the input data to the server again.

[1223] Step 7:

[1224] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[1225] Step 8:

[1226] The emotion engine collects emotional data from the device through the user's facial expressions, voice, input speed, etc., and estimates the user's emotional state.

[1227] Step 9:

[1228] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[1229] Step 10:

[1230] The server adjusts the analysis results in cooperation with the emotion engine and determines the content and method of display according to the user's emotional state.

[1231] Step 11:

[1232] The server transmits the generated analysis results and the adjustment results from the emotion engine to the terminal.

[1233] Step 12:

[1234] The device displays the analysis results to the user. If the user is feeling anxious or stressed, the device displays the analysis results concisely and provides additional support information or alerts.

[1235] Step 13:

[1236] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[1237] Example 2

[1238] 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."

[1239] Conventional diagnostic systems do not take into account the user's emotional state in the process from inputting symptoms and measurement data to outputting analysis results, resulting in problems such as insufficient diagnostic accuracy and insufficient reduction of user stress. Furthermore, improving the accuracy of case candidates and recommended treatments remains a challenge.

[1240] 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 an input device means for inputting symptoms and measurement data, a data processing device means for storing and analyzing data transmitted from the input device means, an analysis device means for analyzing the data stored in the data processing device means based on a machine learning algorithm and generating case candidates and recommended treatments, a display device means for transmitting and displaying the analysis results generated by the analysis device means to the input device means, and an emotion analysis device means for adjusting the analysis results based on the emotional state of the user. This enables improved data accuracy and user-friendly display of analysis results, thereby realizing efficient and stress-free medical treatment in medical settings.

[1241] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by a patient.

[1242] "Measurement data" refers to values ​​that quantitatively indicate the patient's physical condition, such as blood pressure, blood sugar level, and body temperature.

[1243] "Input device means" refers to a device for inputting symptoms and measurement data, and includes a personal computer, tablet, etc.

[1244] The "data processing device means" is a device that receives data sent from the input device means and stores it in a database.

[1245] A "machine learning algorithm" is an algorithm that learns patterns based on large amounts of data and makes predictions and classifications.

[1246] The "analysis device means" is a device that analyzes the accumulated data based on a machine learning algorithm and generates candidate cases and recommended treatments.

[1247] The "display device means" is a device that visually presents the analysis results generated by the analysis device means to the user.

[1248] The "emotion analysis device means" is a device that estimates emotions from the user's input state, facial expressions, words, etc., and adjusts the content and method of displaying the analysis results.

[1249] "Update means" refers to the means for periodically improving and updating the machine learning algorithm based on accumulated data.

[1250] "Learning improvement means" refers to means for improving the accuracy of predicting case candidates using machine learning algorithms.

[1251] The "medical department recommendation means" is a means for identifying an appropriate medical department based on the analysis results and recommending it to the user.

[1252] The "information display means" is a means for displaying recommended medical department information on the input device means.

[1253] The present invention provides a system that reduces the oversight of abnormal values ​​and promotes early treatment by taking a user's emotions into consideration during diagnosis. This system includes an input device means for a user to input a patient's symptoms and measurement data, a data processing device means for storing and analyzing the data, an analysis device means for performing analysis based on the stored data using a machine learning algorithm, a display device means for displaying the analysis results, and an emotion analysis device means for adjusting the display of the analysis results based on the user's emotional state. Detailed embodiments of this system are described below.

[1254] Data collection and storage

[1255] During medical examinations, a user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood glucose level 180 mg / dL, body temperature 37.5°C) into an input device means such as a personal computer or tablet. The input data is converted into a predetermined format within the terminal, and personally identifiable information is deleted. The formatted data is then transmitted to the data processing device means via a security protocol (e.g., HTTPS). The data processing device means stores the received data in a database and uses it for subsequent analysis and machine learning.

[1256] AI learning

[1257] The data processing device periodically retrieves accumulated data from the database and refreshes the model using a machine learning algorithm. Based on past medical data, the system learns the relationship between symptoms, measurement data, and diagnostic results. Random forests, neural networks, etc. are used as machine learning algorithms.

[1258] Diagnostic and emotional analysis

[1259] When a new patient is seen, the user again inputs the symptoms and measurement data into the terminal. The terminal reformats the input data and transmits it to the data processing means. The data processing means immediately inputs the received data into a machine learning algorithm for real-time analysis. The analysis step generates candidate cases, symptoms for each candidate, and recommended treatments.

[1260] At the same time, the emotion analyzer means analyzes the user's input status, facial expressions, and words to estimate the user's emotional state. The emotion analyzer means identifies emotions such as impatience, confusion, and certainty.

[1261] Analysis output and emotion-based adjustment

[1262] If a specific medical department is required based on the analysis results, the medical department is identified and recommended. The emotion analysis device means adjusts the generated analysis results according to the user's emotional state and determines the appropriate display content and method. The adjusted analysis results are sent back to the terminal and displayed to the user by the display device means. Depending on the emotional state, alerts and additional support information are provided.

[1263] Specific examples

[1264] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[1265] When the user visits the clinic complaining of Patient B's headache and vomiting, the user inputs the measurement results of blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, and body temperature 37.5°C into the input device means. At the same time, the emotion analysis device means recognizes that the user is feeling impatient. The terminal formats the input data and transmits it to the data processing device means via a security protocol.

[1266] The data processing means receives the data and stores it in a database. Machine learning algorithms are then used to generate a list of potential cases of hypothyroidism and diabetes, each with their respective symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), as well as recommendations for thyroid clinic visits.

[1267] The emotion analysis device means detects the user's impatience and adjusts the display of the analysis results to emphasize concise and specific alerts. Finally, the adjusted analysis results are sent to the terminal and displayed to the user. Additional support information and instructions may also be provided to reduce the user's impatience.

[1268] Prompt Sentence Examples

[1269] Below are some example prompts to input to a generative AI model:

[1270] "Analyze the following patient data and provide a possible diagnosis and recommended treatment: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C."

[1271] "When users are in a hurry, please display the diagnostic results in a concise and easy-to-understand manner."

[1272] "A new patient has arrived. After entering their symptoms and measurements, the emotion engine has detected impatience. Please adjust your analysis to take this information into account."

[1273] This allows the system to not only provide accurate and prompt diagnostic support, but also to respond flexibly while taking into consideration the user's feelings.

[1274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1275] Step 1:

[1276] The user enters patient information

[1277] User: During medical examination, the user inputs the patient's symptoms (eg, headache, vomiting) and measurement data (eg, blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the input device means.

[1278] Input and output: The user inputs symptoms and measurement data into the input device, and the data is passed to the terminal.

[1279] Specific operation: The doctor uses the keyboard to enter measurement values ​​and symptoms into a dedicated input form and clicks the "Send" button.

[1280] Step 2:

[1281] The device formats the data and sends it to the server

[1282] Terminal: Converts the entered data into a specified format (e.g., JSON format), deletes any personally identifiable information, and then sends it to the server.

[1283] Input and Output: Takes raw input data and outputs formatted data that is sent to the server.

[1284] What it does: A program on the device filters and formats the data, then sends it securely to a server using the HTTPS protocol.

[1285] Step 3:

[1286] The server stores the data

[1287] Server: Stores the received data in a database and uses it for subsequent analysis and machine learning.

[1288] Input and Output: Receives formatted data and stores it in a database, providing feedback to confirm successful storage.

[1289] Specific behavior: The server adds the received data as a new entry in the database and generates a message indicating the save was successful.

[1290] Step 4:

[1291] The server updates the machine learning model.

[1292] Server: Periodically retrieves accumulated data from the database and refreshes the model using machine learning algorithms.

[1293] Input and Output: Retrieving historical data from the database and outputting an updated model.

[1294] What it does: A scheduled task on the server extracts all new data at a specified time (e.g., every weekend) and retrains it using machine learning algorithms.

[1295] Step 5:

[1296] User enters new patient information

[1297] User: Enters the new patient's symptoms and measurement data again into the input device means.

[1298] Input and Output: New symptoms and measurement data are entered and sent to the terminal.

[1299] Specific operation: As mentioned above, the doctor enters the patient's new symptoms and measurement data and clicks the "Submit" button.

[1300] Step 6:

[1301] The device sends data

[1302] Terminal: Reformats the entered data and sends it to the server.

[1303] Input and Output: Accepts raw data and sends formatted data to the server.

[1304] Specific behavior: Formats and sends the data a second time. Uses HTTPS protocol for security.

[1305] Step 7:

[1306] The server performs the analysis

[1307] Server: Inputs the received data into a machine learning algorithm for real-time analysis, generating candidate cases, their symptoms, and treatment recommendations.

[1308] Input and Output: Formatted data is input into the analysis and output is a list of potential cases and treatment recommendations.

[1309] What it does: It runs new data through machine learning algorithms, performs calculations to produce predictions, and temporarily stores the results.

[1310] Step 8:

[1311] The emotion engine performs emotion analysis

[1312] Emotion engine: Analyzes the user's input, facial expressions, and words to infer their emotional state. It identifies emotions such as impatience, confusion, and certainty.

[1313] Input and output: Receives user input speed and facial expression data and outputs estimated emotional state.

[1314] Specific operation: The emotion analysis algorithm estimates and outputs emotions based on the user's input speed, context, and facial expression data from the camera.

[1315] Step 9:

[1316] The server recommends a medical department

[1317] Server: Based on the analysis results, if a specific medical department is required, identify and recommend that department.

[1318] Input and output: Receives a list of analysis results and outputs recommended medical departments.

[1319] Specific operation: The analysis engine matches case candidates with medical departments and adds the most suitable medical departments to the recommendation list.

[1320] Step 10:

[1321] The server adjusts the analysis results

[1322] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[1323] Input and output: The initial analysis result and the estimated emotional state are input, and the adjusted analysis result is output.

[1324] Specific behavior: Dynamically change the display format and emphasis of results based on feedback from the emotion engine.

[1325] Step 11:

[1326] The server sends the analysis results

[1327] Server: Sends the adjusted analysis results to the device.

[1328] Input and output: Receives refined analysis results and sends them to the terminal.

[1329] Specific operation: Data is securely sent to the device using the HTTPS protocol.

[1330] Step 12:

[1331] The device displays the analysis results.

[1332] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[1333] Input and Output: Receives the adjusted analysis results, converts them into a display format for the user, and displays them.

[1334] What it does: Data is displayed in the end-user interface, notifications are activated, and warnings and additional information are provided when necessary.

[1335] This completes the entire process of the invention, improving diagnostic accuracy and providing user-friendly support.

[1336] (Application example 2)

[1337] 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."

[1338] Conventional medical systems only focus on analysis results based on symptoms and measurement data, and do not take the user's emotional state into consideration, which can lead to problems such as overlooking abnormal values ​​during diagnosis and not providing appropriate advice to the user.It also makes it difficult to recommend medicines and supplements that correspond to the user's emotional state.

[1339] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model and generating case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and means for recommending appropriate medicines and supplements. This enables more accurate diagnoses and appropriate advice and recommendations by taking the user's emotional state into consideration.

[1340] "Terminal means" refers to a device for inputting symptoms and measurement data, and includes smartphones, tablets, etc.

[1341] The term "server means" refers to a computer system that receives data sent from the terminal means and stores and analyzes the data.

[1342] A "machine learning model" is an algorithm that learns from accumulated data and generates case candidates and recommended treatments.

[1343] The "means for displaying the analysis results" refers to an interface for visually presenting the generated analysis results to the user.

[1344] The "emotion engine" is an algorithm for estimating the user's emotional state and adjusting the display of the analysis results accordingly.

[1345] "Means for recommending appropriate medicines and supplements" refers to a function that suggests necessary medicines and supplements based on the user's input data and analysis results.

[1346] This invention realizes a system including a terminal means for inputting symptoms and measurement data, a server means for storing data transmitted from the terminal means, a server means for analyzing the stored data based on a machine learning model and generating candidate cases and recommended treatments, a means for transmitting the generated analysis results to the terminal means and displaying them, an emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and a means for recommending appropriate medicines and supplements.

[1347] Program processing

[1348] Data collection and storage

[1349] The user inputs symptoms and measurement data into a terminal such as a smartphone. This data is formatted and sent to a server. The server stores the received data in a database and uses it for subsequent analysis and machine learning model training.

[1350] AI learning

[1351] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results. This process uses machine learning algorithms (e.g., TensorFlow, PyTorch).

[1352] Health status assessment and emotion analysis

[1353] When a user inputs new data, it is sent from the terminal device to the server. The server then inputs the received data into a machine learning model for real-time analysis. In the analysis step, case candidates, symptoms, and recommended treatments for each candidate are generated. The emotion engine also estimates the user's emotional state from the user's input, facial expressions, and speech patterns, and adjusts the display of the analysis results accordingly.

[1354] Alerts and Recommendations

[1355] The server recommends appropriate medicines and supplements based on the analysis results and the user's emotional state. The generated information is sent to the terminal and visually displayed to the user. Simple and specific alerts are highlighted for users who are feeling particularly anxious or stressed.

[1356] Specific examples

[1357] For example, if a patient complains of headache and fatigue and their blood pressure is measured at 150 / 90 mmHg, they can enter this information into their smartphone and send it to the server. The server analyzes this information and presents possible cases of hypertension along with appropriate treatments (e.g., blood pressure-lowering medication). At the same time, the emotion engine detects the user's stress level and recommends additional relaxation methods and supplements to relieve stress.

[1358] Example prompts for generative AI models

[1359] Please enter your health data (e.g. headache, blood pressure 150 / 90 mmHg, fatigue).

[1360] Assess your emotional state (e.g., stress, impatience).

[1361] Recommend necessary medications and supplements to users based on their health status.

[1362] When making recommendations, tailor alerts to the user's emotional state.

[1363] This system allows users to understand their health condition in detail and receive appropriate medicines, supplements, and treatments efficiently. In particular, the emotional engine reduces the user's psychological burden and provides an effective medical experience.

[1364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1365] Step 1:

[1366] The user inputs symptoms and measurement data into a terminal such as a smartphone. The input data (e.g., headache, blood pressure 150 / 90 mmHg, fatigue) is formatted by the terminal and personal identifying information is deleted.

[1367] Step 2:

[1368] The terminal means transmits the formatted data to the server means, and the transmission process protects the data using a security protocol (e.g., HTTPS).

[1369] Step 3:

[1370] The server stores the received data in a database. The database uses a relational database (e.g., MySQL) to store the data in a structured manner.

[1371] Step 4:

[1372] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. A machine learning algorithm (e.g., TensorFlow) is used to learn the relationship between symptoms and diagnosis results from past medical data. During this process, training and validation are performed using large amounts of data.

[1373] Step 5:

[1374] When a user inputs new symptoms and measurement data, the data is sent from the terminal device to the server, which then inputs the received data into a machine learning model for real-time analysis. The analysis results in the generation of candidate cases and recommended treatments.

[1375] Step 6:

[1376] The server uses an emotion engine to estimate the user's emotional state, which is estimated from input context, facial expressions, and speech patterns, and in some cases, a natural language processing engine (e.g., Google Cloud Natural Language API) is used.

[1377] Step 7:

[1378] The server adjusts the display of the analysis results based on the analysis results and the user's estimated emotional state. For example, if a user is feeling anxious, the server will display the analysis results concisely and specifically, highlighting recommendations for necessary medicines and supplements.

[1379] Step 8:

[1380] The server sends the adjusted analysis results and recommendations to the terminal means, which visually displays the information to the user, allowing the user to understand their health status and select appropriate medicines and supplements.

[1381] This system enables diagnosis and recommendations that take into account the user's emotional state, providing highly accurate diagnoses and effective medical support.

[1382] 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.

[1383] 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.

[1384] 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.

[1385] [Fourth embodiment]

[1386] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1387] 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.

[1388] 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).

[1389] 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.

[1390] 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.

[1391] 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).

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] 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.

[1398] 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."

[1399] The present invention provides a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, and a machine learning model. Detailed embodiments of this system are described below.

[1400] Overall system overview

[1401] The system consists of the following main components:

[1402] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[1403] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[1404] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. This allows predictions and diagnostic support for new data.

[1405] 4. Display means for analysis results: An interface that visually displays the analysis results on the terminal means, allowing the user to immediately check the analysis results.

[1406] Program processing (explained in natural language)

[1407] Data collection and storage

[1408] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure, blood sugar level, body temperature) are entered into the terminal.

[1409] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[1410] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[1411] AI learning

[1412] Server: Periodically retrieves data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results.

[1413] Analysis at the time of diagnosis

[1414] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[1415] Terminal: Sends the entered data to the server.

[1416] Server: Inputs the received data into the machine learning model and performs analysis. As a result, a list of candidate cases, their symptoms, recommended treatments, and appropriate medical departments are generated.

[1417] Output of analysis results

[1418] Server: Sends the generated analysis results to the terminal.

[1419] Terminal: Displays the analysis results to the user.

[1420] Specific examples

[1421] A concrete example from data entry at the first consultation to output of analysis results

[1422] User: Patient A visits the clinic complaining of headache and vomiting. He measures his blood pressure at 160 / 100 mmHg, blood sugar at 180 mg / dL, and body temperature at 37.5°C and enters the results into the terminal.

[1423] Terminal: Formats input data and sends it to the server.

[1424] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[1425] Server: Generates a list of potential cases for hypertension and diabetes, including their symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (ACE inhibitors and insulin therapy), and recommends internal medicine as the appropriate specialty.

[1426] Server: Sends analysis results to the device.

[1427] Terminal: Displays the analysis results to the user, who is a doctor, and issues a referral letter to an internal medicine department.

[1428] This system is expected to lead to improved diagnostic accuracy and earlier treatment.

[1429] The processing flow will be explained below.

[1430] Step 1:

[1431] During consultation, the user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[1432] Step 2:

[1433] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[1434] Step 3:

[1435] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[1436] Step 4:

[1437] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[1438] Step 5:

[1439] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[1440] Step 6:

[1441] The terminal transmits the input data to the server again.

[1442] Step 7:

[1443] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[1444] Step 8:

[1445] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[1446] Step 9:

[1447] The server then sends the generated analysis results to the terminal, which include a list of potential cases, symptoms for each case, recommended treatment, and recommended medical department.

[1448] Step 10:

[1449] The terminal displays the analysis results to the user.

[1450] Step 11:

[1451] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[1452] Example 1

[1453] 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."

[1454] In current medical settings, there are problems such as the risk of overlooking abnormal values ​​during diagnosis and the difficulty of quickly referring patients to the appropriate department. In particular, efficiently analyzing large amounts of patient data and providing highly accurate diagnostic support are important challenges for doctors. This system aims to provide diagnostic support that quickly analyzes symptoms and measurement data and promotes early treatment.

[1455] 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.

[1456] In this invention, the server includes an information terminal means for inputting symptoms and measurement data, a means for accumulating data transmitted from the information terminal means and saving it in a database, a means for periodically updating a machine learning model using the accumulated data and learning from past clinical data, a means for analyzing new data in real time based on the machine learning model and generating candidate cases and recommended treatments, and a means for transmitting the generated analysis results to the information terminal means and visually displaying them. This enables efficient analysis of a large amount of patient data, improves diagnostic accuracy, and enables prompt referral to the appropriate department.

[1457] "Symptom" refers to a sign or characteristic of a disease or health condition exhibited by a patient.

[1458] "Measurement data" refers to data that indicates biological information such as blood pressure, blood sugar level, and body temperature.

[1459] "Information terminal means" refers to a device that allows the user to input symptoms and measurement data, and includes a personal computer or tablet terminal.

[1460] The "server means" refers to a computer system having the function of receiving data sent from the information terminal means and storing it in a database.

[1461] A "database" is a storage device that centrally manages accumulated data and allows it to be retrieved when needed.

[1462] A "machine learning model" is an algorithm that learns from accumulated data and makes predictions and inferences about new data.

[1463] "Real-time analysis" refers to the process of performing analysis immediately as new data is entered.

[1464] "Case candidate" refers to a disease or health condition that is suspected based on symptoms and measurement data.

[1465] "Recommended treatment" refers to a treatment method that can be applied to a candidate case.

[1466] "Visually displaying" means showing the analysis results on a screen or the like in a format that is easy for the user to understand.

[1467] A "referral letter" is an official document used to refer a patient to another medical department or specialist.

[1468] This invention is a system for reducing oversight of abnormal values ​​during diagnosis and promoting early treatment. The system includes a data input terminal, a server for storing and analyzing data, a machine learning model, and an interface for displaying the analysis results.

[1469] Detailed Embodiment of the System

[1470] Data Entry Terminal

[1471] The user enters the patient's symptoms and measurement data into a data entry terminal, which can be a standard PC or tablet. The entered data is formatted, personal identifying information is removed, and the data is sent to a server via an encrypted protocol (e.g., HTTPS).

[1472] Server for data storage and analysis

[1473] The server receives data sent from the information terminal and stores it in a database. The server also periodically retrieves data from the database and updates the machine learning model. The update is performed after data cleansing and preprocessing.

[1474] Machine learning models

[1475] The machine learning model is an algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and appropriate medical departments. When new data is input, it is analyzed immediately in real time and generates results.

[1476] Interface for displaying analysis results

[1477] The generated analysis results are then sent back to the device and visually displayed to the user, who is then a doctor who can make a diagnosis based on the displayed analysis results and, if necessary, refer the patient to the appropriate department.

[1478] Specific examples

[1479] A concrete example from data entry at the first consultation to output of analysis results

[1480] 1. User: Patient A comes to the clinic complaining of headache and vomiting. He enters his blood pressure (160 / 100 mmHg), blood glucose (180 mg / dL), and body temperature (37.5°C) into the terminal.

[1481] 2. Terminal: Formats input data and sends it to the server using an encryption protocol.

[1482] 3. Server: Stores the received data in a database and analyzes it in real time using machine learning models.

[1483] 4. Server: Generates a list of candidate cases for hypertension and diabetes, and recommends their symptoms (headache, vomiting, elevated blood sugar levels), recommended treatments (ACE inhibitors, insulin therapy), and the appropriate medical department for treatment: internal medicine.

[1484] 5. Server: Sends the analysis results to the device.

[1485] 6. Terminal: The analysis results are displayed to the user (physician) and a referral letter to an internal medicine department is issued if necessary.

[1486] Prompt Sentence Examples

[1487] "Patient A complains of headache and vomiting. Measurements include blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, and temperature 37.5°C. Based on these data, please provide appropriate case candidates, indications, recommended treatment, and department."

[1488] This system will enable efficient analysis of large amounts of patient data, improving diagnostic accuracy and enabling prompt referral to the appropriate department.

[1489] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1490] Step 1:

[1491] Data Entry

[1492] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the information terminal.

[1493] Input: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C.

[1494] Output: Formatted symptom and measurement data.

[1495] Step 2:

[1496] Data transmission

[1497] Terminal: Formats the entered data and removes any personally identifiable information. The data is then sent to the server using an encrypted protocol (e.g., HTTPS).

[1498] Input: Formatted symptom and measurement data.

[1499] Output: The encrypted data.

[1500] Step 3:

[1501] Data accumulation

[1502] Server: Stores the received data in a database. The data is identified for each patient and classified appropriately.

[1503] Input: Encrypted data.

[1504] Output: Data stored in the database.

[1505] Step 4:

[1506] AI model learning

[1507] Server: Periodically retrieves data from the database and performs data cleansing. It complements outliers and missing values ​​in the data and updates the machine learning model. Learning is performed based on past medical data, learning the relationship between symptoms, measurement data, and diagnosis results.

[1508] Input: Data stored in a database.

[1509] Output: An updated machine learning model.

[1510] Step 5:

[1511] New Data Transmission

[1512] User: Enters new patient symptoms and measurement data into the terminal during consultation.

[1513] Terminal: Sends new formatted data to the server.

[1514] Input: New symptom and measurement data.

[1515] Output: The new formatted data.

[1516] Step 6:

[1517] Diagnostic Analysis

[1518] Server: Receives new data and feeds it into the machine learning model in real time. The model performs immediate analysis and generates a list of potential cases, indications, treatment recommendations, and appropriate departments.

[1519] Input: New data.

[1520] Output: A list of potential cases, symptoms, recommended treatments, and medical departments based on the analysis results.

[1521] Step 7:

[1522] Send analysis results

[1523] Server: The generated analysis results are re-encrypted and sent to the terminal.

[1524] Input: Analysis results, candidate case list, symptoms, recommended treatment, medical department.

[1525] Output: Encrypted analysis results.

[1526] Step 8:

[1527] Analysis result display

[1528] Terminal: The analysis results are interpreted and visually displayed on a dedicated interface for doctors, who then make a diagnosis based on the results and, if necessary, refer the patient to the appropriate department.

[1529] Input: Encrypted analysis results.

[1530] Output: A visual representation of the analysis results.

[1531] (Application example 1)

[1532] 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."

[1533] Conventional health monitoring systems have limited response capabilities when abnormal values ​​are detected, making it difficult to promptly and appropriately urge users to seek medical attention. There is also a need for a system that can monitor the health status of passengers in autonomous vehicles in real time and take appropriate measures immediately when an abnormality occurs.

[1534] 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.

[1535] In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model to generate case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, means for monitoring the data input by the terminal means in real time and displaying an alarm when an abnormality is detected, and means for providing an optimal route to a medical institution based on the displayed alarm. This enables real-time monitoring of the health condition of passengers and enables prompt and appropriate medical treatment when an abnormality occurs.

[1536] "Symptoms" refers to specific symptoms or abnormalities that indicate the user's health condition.

[1537] "Measurement data" refers to physiological data obtained from the patient's or user's body, such as blood pressure, heart rate, body temperature, and other numerical values.

[1538] "Terminal means" refers to a device through which a user inputs symptoms and measurement data, specifically an electronic device such as a smartphone or a head-mounted display.

[1539] "Server means" refers to a central server that stores data sent from the terminal means and analyzes it using a machine learning model.

[1540] A "machine learning model" refers to an algorithm that uses accumulated data to learn, detect abnormalities, and generate recommended treatments.

[1541] "Analysis results" refers to diagnostic support information such as case candidates, recommended treatments, and abnormality detection generated by the machine learning model.

[1542] "Real-time monitoring" refers to the process of instantly analyzing input data and constantly monitoring for abnormalities.

[1543] "Means for displaying a warning" refers to a function for visually or audibly alerting the user when an abnormality is detected.

[1544] "Guidance route to medical institution" refers to information that provides the most appropriate route to a medical institution and the appropriate response when an abnormality is detected.

[1545] This invention relates to a system that inputs symptoms and measurement data, monitors health conditions in real time based on the data, displays a warning if an abnormality is detected, and guides the user to an appropriate medical institution. Specific embodiments of the system are described below.

[1546] The system mainly consists of the following components:

[1547] 1. Terminal means: A device through which the user inputs symptoms and measurement data, including a smartphone or head-mounted display.

[1548] 2. Server means: A server that accumulates data sent from the terminal means and analyzes it using a machine learning model.

[1549] 3. Machine learning model: An algorithm that detects abnormalities based on accumulated data and provides recommended treatments and guidance routes to the most appropriate medical institution based on the analysis results.

[1550] 4. Means for displaying analysis results: An interface for visually or audibly displaying warnings and analysis results to the user.

[1551] Program processing (explained in natural language)

[1552] Data Collection and Monitoring

[1553] A user inputs their own health data (e.g., blood pressure, heart rate, body temperature) into the terminal means, which formats the input data and transmits it to the server means.

[1554] Real-time analytics

[1555] The server inputs the received data into a machine learning model and performs real-time analysis. If an abnormality is detected during the analysis, the server immediately sends the results to the terminal and displays a warning to the user.

[1556] Guidance and contact to medical institutions

[1557] The server also provides a route to the most appropriate medical institution when an abnormality is detected, and is equipped with a function that automatically notifies the appropriate medical institution or family member as necessary.

[1558] Hardware and software used

[1559] Hardware: Smartphones, head-mounted displays, and in-vehicle devices inside autonomous vehicles.

[1560] Software: Python programs for data analysis, the Requests library for sending and receiving data, and machine learning models (such as TensorFlow or Scikit-learn).

[1561] Specific examples

[1562] Example 1: In-car health monitoring

[1563] User: A passenger who becomes ill in an autonomous vehicle uses their smartphone to enter their blood pressure and heart rate.

[1564] Server: Analyzes the received data and detects abnormally high heart rates.

[1565] Terminal means: Displays a warning to passengers and provides guidance to the nearest medical facility.

[1566] Prompt Sentence Examples

[1567] Design a system that analyzes the following health data in real time for abnormal values, and if an abnormality is detected, suggests routes to the nearest medical facility and contact options.

[1568] *Example of health data: Blood pressure 150 / 90, heart rate 100, body temperature 38℃.

[1569] Please implement this using Python and the Requests library.

[1570] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1571] Step 1:

[1572] The user inputs their own health data (blood pressure, heart rate, body temperature, etc.) into a terminal means (a smartphone or a head-mounted display). The input data is formatted into an appropriate format by the terminal means.

[1573] input:

[1574] Health data (e.g., blood pressure 130 / 85, heart rate 85, body temperature 36.8℃)

[1575] output:

[1576] Formatted Data

[1577] Specific operation:

[1578] The user inputs numerical values ​​through the interface of the terminal means, and the data is converted into JSON format.

[1579] Step 2:

[1580] The terminal means transmits the formatted data to the server means in real time via the Internet.

[1581] input:

[1582] Formatted Data

[1583] output:

[1584] Data sent to the server

[1585] Specific operation:

[1586] Use the Requests library to send data to the server's API with an HTTP POST request.

[1587] Step 3:

[1588] The server means stores the received data, which is then stored in a database for later analysis and model updating.

[1589] input:

[1590] Data sent

[1591] output:

[1592] Data stored in a database

[1593] Specific operation:

[1594] The received data is stored in a database using a database management system (e.g., MySQL, PostgreSQL).

[1595] Step 4:

[1596] The server inputs the accumulated data into a machine learning model and performs real-time analysis, thereby detecting the presence or absence of abnormalities.

[1597] input:

[1598] Data stored in a database

[1599] Machine learning models

[1600] output:

[1601] Analysis results showing whether or not there are any abnormalities

[1602] Specific operation:

[1603] Using Python machine learning libraries (e.g., TensorFlow, Scikit-learn), the received data is input into a model to generate analysis results.

[1604] Step 5:

[1605] The server unit transmits the generated analysis results to the terminal unit, which also include a warning message if an abnormality is detected.

[1606] input:

[1607] Analysis results

[1608] output:

[1609] Analysis results sent to the terminal means

[1610] Specific operation:

[1611] The analysis results are reformatted in JSON format and sent to the terminal means via an HTTP POST request.

[1612] Step 6:

[1613] The terminal means displays the received analysis results to the user, and if an abnormality is detected, a warning message is displayed.

[1614] input:

[1615] Received analysis results

[1616] output:

[1617] Results and warnings displayed to the user

[1618] Specific operation:

[1619] Results are displayed visually through a smartphone or head-mounted display interface, and audio alerts are provided if required.

[1620] Step 7:

[1621] When a warning is displayed, the terminal device also provides a route to the most appropriate medical institution, and automatically notifies the appropriate medical institution or family member as necessary.

[1622] input:

[1623] Warning messages based on analysis results

[1624] output:

[1625] Routes to medical institutions

[1626] Automatic notifications when needed

[1627] Specific operation:

[1628] It uses GPS data to search for the nearest medical facility, displays routes on a map, and notifies medical facilities and family members via phone or email based on contact information.

[1629] 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.

[1630] The present invention provides a system that takes user emotions into consideration during diagnosis, reducing the chance of overlooking abnormal values ​​and promoting early treatment. This system includes a terminal where a user inputs patient symptoms and measurement data, a server that stores and analyzes the data, a terminal for displaying the analysis results, a machine learning model, and an emotion engine. Detailed embodiments of this system are described below.

[1631] Overall system overview

[1632] The system consists of the following main components:

[1633] 1. Terminal means: A device into which users (doctors and medical staff) input patient symptoms and measurement data. This includes PCs, tablets, etc.

[1634] 2. Server means: A server that receives data sent from the terminal means, stores it, and analyzes it using a machine learning model. The server includes a database and periodically updates the machine learning model based on the stored data.

[1635] 3. Machine learning model: An algorithm that learns from accumulated data and generates case candidates, symptoms, recommended treatments, and recommended medical departments during analysis. It also provides predictions and diagnostic support for new data.

[1636] 4. Display of analysis results: An interface that visually displays the analysis results on the terminal, allowing users to immediately check the analysis results.

[1637] 5. Emotion Engine: An algorithm that recognizes the user's emotions and adjusts the display of analysis results and the provision of support. It infers emotions from the user's words, facial expressions, and typing pace.

[1638] Program processing (explained in natural language)

[1639] Data collection and storage

[1640] User: During medical examination, the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) are entered into the terminal.

[1641] Terminal: Formats the entered data, removes any personally identifiable information, and sends it to the server.

[1642] Server: The received data is stored in a database and used for subsequent analysis and machine learning.

[1643] AI learning

[1644] Server: Periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[1645] Diagnostic and emotional analysis

[1646] User: When a new patient is seen, the symptoms and measurement data are entered into the terminal.

[1647] Terminal: Sends the entered data to the server.

[1648] Server: Inputs incoming data into machine learning models for real-time analysis. The analysis step generates candidate cases, their symptoms, and treatment recommendations.

[1649] Emotion Engine: At the same time, it analyzes the user's input, facial expressions, and words to infer their emotional state. The emotion engine identifies emotions such as impatience, confusion, and certainty.

[1650] Analysis output and emotion-based adjustment

[1651] Server: Based on the analysis results, if a specific medical department is required, the server identifies and recommends that department.

[1652] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[1653] Server: Sends the analysis results to the device.

[1654] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[1655] Specific examples

[1656] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[1657] User: Patient B visits the clinic complaining of headache and vomiting. His blood pressure is 160 / 100 mmHg, his blood sugar is 180 mg / dL, and his body temperature is 37.5°C. The results are entered into the terminal. The emotion engine also recognizes that the user is feeling a little impatient.

[1658] Terminal: Formats input data and sends it to the server.

[1659] Server: Receives data, stores it in a database, and analyzes it using machine learning models.

[1660] Server: Generates a list of potential cases of hypothyroidism and diabetes, including symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), and recommends thyroid clinic visits.

[1661] Emotion Engine: Detects the user's impatience and displays the analysis results with concise and specific alerts.

[1662] Server: Sends analysis results to the device.

[1663] Terminal: Displays analysis results (case candidates, symptoms, recommended treatments, and department information) and provides additional support information and instructions to reduce user impatience.

[1664] This system is expected to lead to improved diagnostic accuracy and earlier treatment. In addition, the introduction of an emotion engine will provide flexible and accurate support according to the user's situation, reducing stress in medical settings and enabling more efficient medical treatment.

[1665] The processing flow will be explained below.

[1666] Step 1:

[1667] During consultation, the user enters the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the terminal.

[1668] Step 2:

[1669] The terminal formats the entered data, removes any personally identifiable information, and then transmits it to the server.

[1670] Step 3:

[1671] The server stores the received data in a database and uses it for subsequent analysis and machine learning.

[1672] Step 4:

[1673] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the machine learning model learns the relationship between symptoms, measurement data, and diagnosis results.

[1674] Step 5:

[1675] When a user sees a new patient, the user inputs symptoms and measurement data into the terminal.

[1676] Step 6:

[1677] The terminal transmits the input data to the server again.

[1678] Step 7:

[1679] The server inputs the received data into a machine learning model for real-time analysis, which generates candidate cases, their symptoms, and treatment recommendations.

[1680] Step 8:

[1681] The emotion engine collects emotional data from the device through the user's facial expressions, voice, input speed, etc., and estimates the user's emotional state.

[1682] Step 9:

[1683] If a specific medical department is required based on the analysis results, the server identifies and recommends that medical department.

[1684] Step 10:

[1685] The server adjusts the analysis results in cooperation with the emotion engine and determines the content and method of display according to the user's emotional state.

[1686] Step 11:

[1687] The server transmits the generated analysis results and the adjustment results from the emotion engine to the terminal.

[1688] Step 12:

[1689] The device displays the analysis results to the user. If the user is feeling anxious or stressed, the device displays the analysis results concisely and provides additional support information or alerts.

[1690] Step 13:

[1691] The user checks the displayed analysis results and issues a referral letter to the appropriate medical department if necessary.

[1692] Example 2

[1693] 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."

[1694] Conventional diagnostic systems do not take into account the user's emotional state in the process from inputting symptoms and measurement data to outputting analysis results, resulting in problems such as insufficient diagnostic accuracy and insufficient reduction of user stress. Furthermore, improving the accuracy of case candidates and recommended treatments remains a challenge.

[1695] 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 an input device means for inputting symptoms and measurement data, a data processing device means for storing and analyzing data transmitted from the input device means, an analysis device means for analyzing the data stored in the data processing device means based on a machine learning algorithm and generating case candidates and recommended treatments, a display device means for transmitting and displaying the analysis results generated by the analysis device means to the input device means, and an emotion analysis device means for adjusting the analysis results based on the emotional state of the user. This enables improved data accuracy and user-friendly display of analysis results, thereby realizing efficient and stress-free medical treatment in medical settings.

[1696] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by a patient.

[1697] "Measurement data" refers to values ​​that quantitatively indicate the patient's physical condition, such as blood pressure, blood sugar level, and body temperature.

[1698] "Input device means" refers to a device for inputting symptoms and measurement data, and includes a personal computer, tablet, etc.

[1699] The "data processing device means" is a device that receives data sent from the input device means and stores it in a database.

[1700] A "machine learning algorithm" is an algorithm that learns patterns based on large amounts of data and makes predictions and classifications.

[1701] The "analysis device means" is a device that analyzes the accumulated data based on a machine learning algorithm and generates candidate cases and recommended treatments.

[1702] The "display device means" is a device that visually presents the analysis results generated by the analysis device means to the user.

[1703] The "emotion analysis device means" is a device that estimates emotions from the user's input state, facial expressions, words, etc., and adjusts the content and method of displaying the analysis results.

[1704] "Update means" refers to the means for periodically improving and updating the machine learning algorithm based on accumulated data.

[1705] "Learning improvement means" refers to means for improving the accuracy of predicting case candidates using machine learning algorithms.

[1706] The "medical department recommendation means" is a means for identifying an appropriate medical department based on the analysis results and recommending it to the user.

[1707] The "information display means" is a means for displaying recommended medical department information on the input device means.

[1708] The present invention provides a system that reduces the oversight of abnormal values ​​and promotes early treatment by taking a user's emotions into consideration during diagnosis. This system includes an input device means for a user to input a patient's symptoms and measurement data, a data processing device means for storing and analyzing the data, an analysis device means for performing analysis based on the stored data using a machine learning algorithm, a display device means for displaying the analysis results, and an emotion analysis device means for adjusting the display of the analysis results based on the user's emotional state. Detailed embodiments of this system are described below.

[1709] Data collection and storage

[1710] During medical examinations, a user inputs the patient's symptoms (e.g., headache, vomiting) and measurement data (e.g., blood pressure 160 / 100 mmHg, blood glucose level 180 mg / dL, body temperature 37.5°C) into an input device means such as a personal computer or tablet. The input data is converted into a predetermined format within the terminal, and personally identifiable information is deleted. The formatted data is then transmitted to the data processing device means via a security protocol (e.g., HTTPS). The data processing device means stores the received data in a database and uses it for subsequent analysis and machine learning.

[1711] AI learning

[1712] The data processing device periodically retrieves accumulated data from the database and refreshes the model using a machine learning algorithm. Based on past medical data, the system learns the relationship between symptoms, measurement data, and diagnostic results. Random forests, neural networks, etc. are used as machine learning algorithms.

[1713] Diagnostic and emotional analysis

[1714] When a new patient is seen, the user again inputs the symptoms and measurement data into the terminal. The terminal reformats the input data and transmits it to the data processing means. The data processing means immediately inputs the received data into a machine learning algorithm for real-time analysis. The analysis step generates candidate cases, symptoms for each candidate, and recommended treatments.

[1715] At the same time, the emotion analyzer means analyzes the user's input status, facial expressions, and words to estimate the user's emotional state. The emotion analyzer means identifies emotions such as impatience, confusion, and certainty.

[1716] Analysis output and emotion-based adjustment

[1717] If a specific medical department is required based on the analysis results, the medical department is identified and recommended. The emotion analysis device means adjusts the generated analysis results according to the user's emotional state and determines the appropriate display content and method. The adjusted analysis results are sent back to the terminal and displayed to the user by the display device means. Depending on the emotional state, alerts and additional support information are provided.

[1718] Specific examples

[1719] Specific examples of data entry at the time of initial consultation, output of analysis results, and emotion analysis

[1720] When the user visits the clinic complaining of Patient B's headache and vomiting, the user inputs the measurement results of blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, and body temperature 37.5°C into the input device means. At the same time, the emotion analysis device means recognizes that the user is feeling impatient. The terminal formats the input data and transmits it to the data processing device means via a security protocol.

[1721] The data processing means receives the data and stores it in a database. Machine learning algorithms are then used to generate a list of potential cases of hypothyroidism and diabetes, each with their respective symptoms (headache, vomiting, and elevated blood sugar) and recommended treatments (hormone replacement therapy, insulin therapy), as well as recommendations for thyroid clinic visits.

[1722] The emotion analysis device means detects the user's impatience and adjusts the display of the analysis results to emphasize concise and specific alerts. Finally, the adjusted analysis results are sent to the terminal and displayed to the user. Additional support information and instructions may also be provided to reduce the user's impatience.

[1723] Prompt Sentence Examples

[1724] Below are some example prompts to input to a generative AI model:

[1725] "Analyze the following patient data and provide a possible diagnosis and recommended treatment: headache, vomiting, blood pressure 160 / 100 mmHg, blood glucose 180 mg / dL, temperature 37.5°C."

[1726] "When users are in a hurry, please display the diagnostic results in a concise and easy-to-understand manner."

[1727] "A new patient has arrived. After entering their symptoms and measurements, the emotion engine has detected impatience. Please adjust your analysis to take this information into account."

[1728] This allows the system to not only provide accurate and prompt diagnostic support, but also to respond flexibly while taking into consideration the user's feelings.

[1729] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1730] Step 1:

[1731] The user enters patient information

[1732] User: During medical examination, the user inputs the patient's symptoms (eg, headache, vomiting) and measurement data (eg, blood pressure 160 / 100 mmHg, blood sugar level 180 mg / dL, body temperature 37.5°C) into the input device means.

[1733] Input and output: The user inputs symptoms and measurement data into the input device, and the data is passed to the terminal.

[1734] Specific operation: The doctor uses the keyboard to enter measurement values ​​and symptoms into a dedicated input form and clicks the "Send" button.

[1735] Step 2:

[1736] The device formats the data and sends it to the server

[1737] Terminal: Converts the entered data into a specified format (e.g., JSON format), deletes any personally identifiable information, and then sends it to the server.

[1738] Input and Output: Takes raw input data and outputs formatted data that is sent to the server.

[1739] What it does: A program on the device filters and formats the data, then sends it securely to a server using the HTTPS protocol.

[1740] Step 3:

[1741] The server stores the data

[1742] Server: Stores the received data in a database and uses it for subsequent analysis and machine learning.

[1743] Input and Output: Receives formatted data and stores it in a database, providing feedback to confirm successful storage.

[1744] Specific behavior: The server adds the received data as a new entry in the database and generates a message indicating the save was successful.

[1745] Step 4:

[1746] The server updates the machine learning model.

[1747] Server: Periodically retrieves accumulated data from the database and refreshes the model using machine learning algorithms.

[1748] Input and Output: Retrieving historical data from the database and outputting an updated model.

[1749] What it does: A scheduled task on the server extracts all new data at a specified time (e.g., every weekend) and retrains it using machine learning algorithms.

[1750] Step 5:

[1751] User enters new patient information

[1752] User: Enters the new patient's symptoms and measurement data again into the input device means.

[1753] Input and Output: New symptoms and measurement data are entered and sent to the terminal.

[1754] Specific operation: As mentioned above, the doctor enters the patient's new symptoms and measurement data and clicks the "Submit" button.

[1755] Step 6:

[1756] The device sends data

[1757] Terminal: Reformats the entered data and sends it to the server.

[1758] Input and Output: Accepts raw data and sends formatted data to the server.

[1759] Specific behavior: Formats and sends the data a second time. Uses HTTPS protocol for security.

[1760] Step 7:

[1761] The server performs the analysis

[1762] Server: Inputs the received data into a machine learning algorithm for real-time analysis, generating candidate cases, their symptoms, and treatment recommendations.

[1763] Input and Output: Formatted data is input into the analysis and output is a list of potential cases and treatment recommendations.

[1764] What it does: It runs new data through machine learning algorithms, performs calculations to produce predictions, and temporarily stores the results.

[1765] Step 8:

[1766] The emotion engine performs emotion analysis

[1767] Emotion engine: Analyzes the user's input, facial expressions, and words to infer their emotional state. It identifies emotions such as impatience, confusion, and certainty.

[1768] Input and output: Receives user input speed and facial expression data and outputs estimated emotional state.

[1769] Specific operation: The emotion analysis algorithm estimates and outputs emotions based on the user's input speed, context, and facial expression data from the camera.

[1770] Step 9:

[1771] The server recommends a medical department

[1772] Server: Based on the analysis results, if a specific medical department is required, identify and recommend that department.

[1773] Input and output: Receives a list of analysis results and outputs recommended medical departments.

[1774] Specific operation: The analysis engine matches case candidates with medical departments and adds the most suitable medical departments to the recommendation list.

[1775] Step 10:

[1776] The server adjusts the analysis results

[1777] Server: The generated analysis results are adjusted through the emotion engine, and the content and method of display are determined according to the user's emotional state.

[1778] Input and output: The initial analysis result and the estimated emotional state are input, and the adjusted analysis result is output.

[1779] Specific behavior: Dynamically change the display format and emphasis of results based on feedback from the emotion engine.

[1780] Step 11:

[1781] The server sends the analysis results

[1782] Server: Sends the adjusted analysis results to the device.

[1783] Input and output: Receives refined analysis results and sends them to the terminal.

[1784] Specific operation: Data is securely sent to the device using the HTTPS protocol.

[1785] Step 12:

[1786] The device displays the analysis results.

[1787] Terminal: The analysis results are displayed to the user, and alerts and additional support information are provided depending on the emotional state.

[1788] Input and Output: Receives the adjusted analysis results, converts them into a display format for the user, and displays them.

[1789] What it does: Data is displayed in the end-user interface, notifications are activated, and warnings and additional information are provided when necessary.

[1790] This completes the entire process of the invention, improving diagnostic accuracy and providing user-friendly support.

[1791] (Application example 2)

[1792] 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."

[1793] Conventional medical systems only focus on analysis results based on symptoms and measurement data, and do not take the user's emotional state into consideration, which can lead to problems such as overlooking abnormal values ​​during diagnosis and not providing appropriate advice to the user.It also makes it difficult to recommend medicines and supplements that correspond to the user's emotional state.

[1794] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means for inputting symptoms and measurement data, server means for storing data transmitted from the terminal means, means for analyzing the stored data based on a machine learning model and generating case candidates and recommended treatments, means for transmitting the generated analysis results to the terminal means and displaying them, emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and means for recommending appropriate medicines and supplements. This enables more accurate diagnoses and appropriate advice and recommendations by taking the user's emotional state into consideration.

[1795] "Terminal means" refers to a device for inputting symptoms and measurement data, and includes smartphones, tablets, etc.

[1796] The term "server means" refers to a computer system that receives data sent from the terminal means and stores and analyzes the data.

[1797] A "machine learning model" is an algorithm that learns from accumulated data and generates case candidates and recommended treatments.

[1798] The "means for displaying the analysis results" refers to an interface for visually presenting the generated analysis results to the user.

[1799] The "emotion engine" is an algorithm for estimating the user's emotional state and adjusting the display of the analysis results accordingly.

[1800] "Means for recommending appropriate medicines and supplements" refers to a function that suggests necessary medicines and supplements based on the user's input data and analysis results.

[1801] This invention realizes a system including a terminal means for inputting symptoms and measurement data, a server means for storing data transmitted from the terminal means, a server means for analyzing the stored data based on a machine learning model and generating candidate cases and recommended treatments, a means for transmitting the generated analysis results to the terminal means and displaying them, an emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results, and a means for recommending appropriate medicines and supplements.

[1802] Program processing

[1803] Data collection and storage

[1804] The user inputs symptoms and measurement data into a terminal such as a smartphone. This data is formatted and sent to a server. The server stores the received data in a database and uses it for subsequent analysis and machine learning model training.

[1805] AI learning

[1806] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. Based on past medical data, the model learns the relationship between symptoms, measurement data, and diagnosis results. This process uses machine learning algorithms (e.g., TensorFlow, PyTorch).

[1807] Health status assessment and emotion analysis

[1808] When a user inputs new data, it is sent from the terminal device to the server. The server then inputs the received data into a machine learning model for real-time analysis. In the analysis step, case candidates, symptoms, and recommended treatments for each candidate are generated. The emotion engine also estimates the user's emotional state from the user's input, facial expressions, and speech patterns, and adjusts the display of the analysis results accordingly.

[1809] Alerts and Recommendations

[1810] The server recommends appropriate medicines and supplements based on the analysis results and the user's emotional state. The generated information is sent to the terminal and visually displayed to the user. Simple and specific alerts are highlighted for users who are feeling particularly anxious or stressed.

[1811] Specific examples

[1812] For example, if a patient complains of headache and fatigue and their blood pressure is measured at 150 / 90 mmHg, they can enter this information into their smartphone and send it to the server. The server analyzes this information and presents possible cases of hypertension along with appropriate treatments (e.g., blood pressure-lowering medication). At the same time, the emotion engine detects the user's stress level and recommends additional relaxation methods and supplements to relieve stress.

[1813] Example prompts for generative AI models

[1814] Please enter your health data (e.g. headache, blood pressure 150 / 90 mmHg, fatigue).

[1815] Assess your emotional state (e.g., stress, impatience).

[1816] Recommend necessary medications and supplements to users based on their health status.

[1817] When making recommendations, tailor alerts to the user's emotional state.

[1818] This system allows users to understand their health condition in detail and receive appropriate medicines, supplements, and treatments efficiently. In particular, the emotional engine reduces the user's psychological burden and provides an effective medical experience.

[1819] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1820] Step 1:

[1821] The user inputs symptoms and measurement data into a terminal such as a smartphone. The input data (e.g., headache, blood pressure 150 / 90 mmHg, fatigue) is formatted by the terminal and personal identifying information is deleted.

[1822] Step 2:

[1823] The terminal means transmits the formatted data to the server means, and the transmission process protects the data using a security protocol (e.g., HTTPS).

[1824] Step 3:

[1825] The server stores the received data in a database. The database uses a relational database (e.g., MySQL) to store the data in a structured manner.

[1826] Step 4:

[1827] The server periodically retrieves accumulated data from the database and refreshes the machine learning model. A machine learning algorithm (e.g., TensorFlow) is used to learn the relationship between symptoms and diagnosis results from past medical data. During this process, training and validation are performed using large amounts of data.

[1828] Step 5:

[1829] When a user inputs new symptoms and measurement data, the data is sent from the terminal device to the server, which then inputs the received data into a machine learning model for real-time analysis. The analysis results in the generation of candidate cases and recommended treatments.

[1830] Step 6:

[1831] The server uses an emotion engine to estimate the user's emotional state, which is estimated from input context, facial expressions, and speech patterns, and in some cases, a natural language processing engine (e.g., Google Cloud Natural Language API) is used.

[1832] Step 7:

[1833] The server adjusts the display of the analysis results based on the analysis results and the user's estimated emotional state. For example, if a user is feeling anxious, the server will display the analysis results concisely and specifically, highlighting recommendations for necessary medicines and supplements.

[1834] Step 8:

[1835] The server sends the adjusted analysis results and recommendations to the terminal means, which visually displays the information to the user, allowing the user to understand their health status and select appropriate medicines and supplements.

[1836] This system enables diagnosis and recommendations that take into account the user's emotional state, providing highly accurate diagnoses and effective medical support.

[1837] 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.

[1838] 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.

[1839] 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 robot 414.

[1840] 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.

[1841] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion 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.

[1842] 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.

[1843] 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).

[1844] 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 is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1845] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1846] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1847] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1848] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1849] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1850] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1851] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1852] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1853] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1854] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1855] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1856] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1857] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1858] The following is further disclosed regarding the above embodiment.

[1859] (Claim 1)

[1860] a terminal means for inputting symptoms and measurement data;

[1861] a server means for storing data transmitted from the terminal means;

[1862] a server means for analyzing the accumulated data based on a machine learning model to generate candidate cases and recommended treatments;

[1863] means for transmitting the generated analysis results to said terminal means and displaying them;

[1864] A system including:

[1865] (Claim 2)

[1866] A means to periodically update the machine learning model from the accumulated data, and

[1867] A means for learning with the machine learning model to improve the prediction accuracy of case candidates;

[1868] 10. The system of claim 1, further comprising:

[1869] (Claim 3)

[1870] A method for recommending appropriate medical departments based on the analysis results;

[1871] a means for displaying the recommended medical department information on a terminal means;

[1872] 10. The system of claim 1, further comprising:

[1873] "Example 1"

[1874] (Claim 1)

[1875] an information terminal means for inputting symptoms and measurement data;

[1876] a server means for accumulating data transmitted from the information terminal means and storing the data in a database;

[1877] A means to update the machine learning model using periodically accumulated data and learn from past clinical data;

[1878] A means to analyze new data in real time based on machine learning models to generate case candidates and treatment recommendations; and

[1879] means for transmitting the generated analysis results to the information terminal means and visually displaying them;

[1880] A system including:

[1881] (Claim 2)

[1882] A means to periodically retrieve the accumulated data, perform data cleansing and preprocessing, and refresh the machine learning model;

[1883] A means for improving the accuracy of new data analysis during diagnosis using the machine learning model;

[1884] 10. The system of claim 1, further comprising:

[1885] (Claim 3)

[1886] a means for recommending an appropriate medical department based on the analysis result and displaying the information on the information terminal means;

[1887] A means of providing referrals and information for deciding on treatment options;

[1888] 10. The system of claim 1, further comprising:

[1889] "Application Example 1"

[1890] (Claim 1)

[1891] a terminal means for inputting symptoms and measurement data;

[1892] a server means for storing data transmitted from the terminal means;

[1893] a server means for analyzing the accumulated data based on a machine learning model to generate candidate cases and recommended treatments;

[1894] means for transmitting the generated analysis results to said terminal means and displaying them;

[1895] means for monitoring the data input by the terminal means in real time and displaying a warning when an abnormality is detected;

[1896] a means for providing an optimal route to a medical institution based on the display of the warning;

[1897] A system including:

[1898] (Claim 2)

[1899] A means to periodically update the machine learning model from the accumulated data, and

[1900] A means for learning with the machine learning model to improve the prediction accuracy of case candidates;

[1901] means for automatically contacting a medical institution or notifying relevant persons based on said terminal means;

[1902] 10. The system of claim 1, further comprising:

[1903] (Claim 3)

[1904] A method for recommending appropriate medical departments based on the analysis results;

[1905] a means for displaying the recommended medical department information on a terminal means;

[1906] a means for making an emergency contact with a medical institution based on the analysis result displayed on the terminal means;

[1907] 10. The system of claim 1, further comprising:

[1908] "Example 2: Combining Emotion Engines"

[1909] (Claim 1)

[1910] an input device means for inputting symptoms and measurement data;

[1911] a data processing unit for storing and analyzing data transmitted from the input unit;

[1912] an analysis device means for analyzing the data stored in the data processing device means based on a machine learning algorithm to generate candidate cases and recommended treatments;

[1913] a display device means for transmitting the analysis results generated by the analysis device means to the input device means and displaying the results;

[1914] an emotion analysis device means for adjusting the analysis result based on the emotional state of the user;

[1915] A system including:

[1916] (Claim 2)

[1917] A means of periodically updating the machine learning algorithm from the accumulated data;

[1918] a learning improvement means for learning using the machine learning algorithm to improve the prediction accuracy of case candidates;

[1919] 10. The system of claim 1, further comprising:

[1920] (Claim 3)

[1921] a medical department recommendation means for recommending an appropriate medical department based on the analysis results;

[1922] an information display means for displaying the recommended medical department information on an input device means;

[1923] 10. The system of claim 1, further comprising:

[1924] "Application example 2 when combining emotion engines"

[1925] (Claim 1)

[1926] a terminal means for inputting symptoms and measurement data;

[1927] a server means for storing data transmitted from the terminal means;

[1928] a server means for analyzing the accumulated data based on a machine learning model to generate candidate cases and recommended treatments;

[1929] means for transmitting the generated analysis results to said terminal means and displaying them;

[1930] an emotion engine means for estimating the user's emotional state and adjusting the display of the analysis results;

[1931] A means of recommending appropriate medications and supplements;

[1932] A system including:

[1933] (Claim 2)

[1934] A means to periodically update the machine learning model from the accumulated data, and

[1935] A means for learning with the machine learning model to improve the prediction accuracy of case candidates;

[1936] 10. The system of claim 1, further comprising:

[1937] (Claim 3)

[1938] A method for recommending appropriate medical departments based on the analysis results;

[1939] a means for displaying the recommended medical department information on a terminal means;

[1940] 10. The system of claim 1, further comprising: [Explanation of symbols]

[1941] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a terminal means for inputting symptoms and measurement data; a server means for storing data transmitted from the terminal means; a server means for analyzing the accumulated data based on a machine learning model to generate candidate cases and recommended treatments; means for transmitting the generated analysis results to said terminal means and displaying them; A system including:

2. A means to periodically update the machine learning model from the accumulated data, and A means for learning with the machine learning model to improve the prediction accuracy of case candidates; The system of claim 1 further comprising:

3. A method for recommending appropriate medical departments based on the analysis results; a means for displaying the recommended medical department information on a terminal means; The system of claim 1 further comprising:

Images