System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving patient data input by a healthcare professional; means comprising an artificial intelligence algorithm for analyzing the patient data and generating a candidate diagnosis and / or a treatment plan; and means for presenting the generated candidate diagnosis and / or treatment plan to the healthcare professional.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Contemporary health challenges in Japan include an increase in mental illness, lifestyle-related diseases, and an increase in the number of elderly people requiring nursing care. The rise in cancer, depression, diabetes, schizophrenia, dementia, and cardiovascular disease is particularly serious. Meanwhile, the rise in lifestyle-related diseases due to a declining birthrate and aging population, a stressful society, and the spread of remote work cannot be ignored. In response to these circumstances, it is necessary to improve the quality of medical care, reduce medical costs, and increase patient satisfaction while reducing the burden on medical professionals. It is also necessary to promote prevention and health promotion and achieve effective use of medical data. [Means for solving the problem]

[0005] The present invention provides the following means: A system including an artificial intelligence algorithm that receives patient data entered by a healthcare professional and analyzes the patient data to generate candidate diagnoses and treatment plans. The system presents the generated candidate diagnoses and treatment plans to the healthcare professional. The system also includes an artificial intelligence algorithm that receives daily health data entered by a user and analyzes the health data to identify health risks and areas for improvement. The system notifies the user of the generated health advice and improvement instructions. The system also includes an artificial intelligence algorithm that receives medical records and treatment data from multiple hospitals and analyzes the received data to identify treatment effects and trends. The system generates feedback for new research concepts and new drug development based on the analysis results and provides it to research institutions and pharmaceutical companies. These means enable improvement of medical quality, reduction of medical costs, improvement of patient satisfaction, support for healthcare professionals, prevention and health promotion, and utilization of medical data.

[0006] "Healthcare professionals" refers to professionals such as doctors, nurses, and pharmacists who diagnose, treat, care for, and provide medicines to patients.

[0007] "Patient Data" refers to a set of medical information relating to a patient, such as a patient's symptoms, vital signs, medical records, medical history, and test results.

[0008] An "electronic medical record" refers to a system that electronically records, stores, and manages patient medical information.

[0009] "Artificial intelligence algorithms" refer to computational methods that use machine learning and data mining techniques to analyze large amounts of data and discover patterns and trends.

[0010] "Candidate diagnoses" refers to a list of possible diseases or conditions based on a patient's symptoms and test results.

[0011] A "treatment plan" refers to a plan that proposes the optimal treatment method for a patient's disease or condition.

[0012] "Health data" refers to a set of information related to an individual's daily diet, exercise, sleep, physical condition, etc.

[0013] "Health risk" refers to risk factors that make an individual more likely to develop a particular disease or health problem.

[0014] "Improvements" refer to specific changes or modifications that improve an individual's health.

[0015] "Health advice" refers to specific guidance or advice to improve an individual's health.

[0016] "Health guidance" refers to specific instructions or guidelines for improving an individual's lifestyle or health.

[0017] "Medical records" refers to information recorded during the course of a patient's examination and treatment.

[0018] "Treatment Data" refers to data regarding a patient's treatment history and its effects.

[0019] "Treatment effect" refers to the results or impact that a particular treatment has on a patient.

[0020] A "trend" refers to a general tendency or pattern found in data.

[0021] "Research concept" refers to a new research direction or theme.

[0022] "New drug development" refers to the process of developing new drugs to treat existing diseases.

[0023] "Feedback" refers to improvement suggestions and advice provided based on the results of analysis and evaluation.

[0024] "Research institution" refers to a university or specialized facility that conducts research related to medicine or pharmacy.

[0025] "Pharmaceutical company" refers to a company that researches, develops, produces, and sells drugs. [Brief explanation of the drawings]

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

[0027] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0030] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0031] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

[0033] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0034] [First embodiment]

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

[0036] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0038] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

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

[0041] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0043] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0044] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[0047] The present invention provides a system that aims to reduce the burden on medical professionals, improve the quality of medical care, increase patient satisfaction, and effectively utilize medical data. This system is embodied in the following specific form.

[0048] The system consists of three main components: the server, the terminal, and the user.

[0049] Support for medical professionals

[0050] 1. Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[0051] 2. Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[0052] 3. Presentation of results: The server sends the generated diagnostic candidates and treatment plans to the terminal, which displays them to the medical professional.

[0053] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[0054] Prevention and health promotion

[0055] 1. Data collection: Users enter their daily health data, such as diet, exercise, sleep, and physical condition, into a smartphone app. The smartphone then sends the collected data to a server.

[0056] 2. Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[0057] 3. Notification of results: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[0058] Example: When a user enters their daily diet and exercise amount into an app, the server analyzes the information and identifies any nutrient deficiencies and areas for improvement in exercise. The app then notifies the user with messages such as "Eat more vegetables" or "We recommend walking 30 minutes every day."

[0059] Utilizing medical data

[0060] 1. Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[0061] 2. Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[0062] 3. Providing results: The server generates feedback for new research concepts and new drug development based on the analysis results and provides them to research institutions and pharmaceutical companies.

[0063] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[0064] A system with these functions will be able to comprehensively solve Japan's health issues through supporting medical professionals, prevention and health promotion, and effective use of medical data. In addition, the system's flexible structure allows it to adapt to different medical environments and user needs.

[0065] The processing flow will be explained below.

[0066] Support for medical professionals

[0067] Step 1:

[0068] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[0069] Step 2:

[0070] Terminal: Sends the entered patient data to the server.

[0071] Step 3:

[0072] Server: Stores the received patient data.

[0073] Step 4:

[0074] Server: Analyzes stored patient data using artificial intelligence algorithms.

[0075] Step 5:

[0076] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[0077] Step 6:

[0078] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[0079] Step 7:

[0080] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[0081] Prevention and health promotion

[0082] Step 1:

[0083] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[0084] Step 2:

[0085] Smartphone: Sends the entered health data to the server.

[0086] Step 3:

[0087] Server: Stores the received health data.

[0088] Step 4:

[0089] Server: Analyzes stored health data using artificial intelligence algorithms.

[0090] Step 5:

[0091] Server: Identifies health risks and areas for improvement based on the analysis results.

[0092] Step 6:

[0093] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[0094] Step 7:

[0095] Server: Sends the generated health advice and improvement guidance to a smartphone.

[0096] Step 8:

[0097] Smartphone: Provides health advice and guidance to users.

[0098] Utilizing medical data

[0099] Step 1:

[0100] Hospital: Provides medical records and treatment data to the server.

[0101] Step 2:

[0102] Server: Receives and stores the data provided.

[0103] Step 3:

[0104] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[0105] Step 4:

[0106] Server: Identify treatment effects and trends from analysis results.

[0107] Step 5:

[0108] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[0109] Step 6:

[0110] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[0111] Example 1

[0112] 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."

[0113] In the medical field, medical professionals are required to efficiently collect patient data and quickly provide diagnoses and treatment plans based on that data. It is also important to accurately collect and analyze health data from patients' daily lives and provide appropriate health advice. Furthermore, there is a need to effectively analyze medical records and treatment data collected from multiple hospitals and use the data for new research and the development of new treatments. To solve these challenges, a system is needed to efficiently and safely perform each process of data collection, analysis, and provision.

[0114] 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.

[0115] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including a terminal for transmitting the patient data to the server using a secure communication protocol; and means for encrypting and transmitting the candidate diagnoses and treatment plans from the server to the terminal, thereby enabling medical professionals to quickly and safely collect and analyze patient data and provide appropriate diagnoses and treatment plans.

[0116] In this invention, the server includes means for receiving daily health data entered by the user, means including an artificial intelligence algorithm for analyzing the health data and identifying health risks and areas for improvement, means for notifying the user of the generated health advice and improvement guidance, means for transmitting the user's input data from a smartphone app to the server, and means for notifying the smartphone of the analysis results, thereby enabling the user to easily collect and analyze health data from their daily lives and receive appropriate health advice.

[0117] Furthermore, in this invention, the server includes: means for receiving medical records and treatment data from multiple hospitals; means including an artificial intelligence algorithm for analyzing the received data and identifying treatment effects and trends; means for generating feedback for new research concepts and new drug development based on the analysis results and providing the feedback to research institutions and pharmaceutical companies; means for analyzing the data using distributed processing technology; and means for storing the analysis results in secure storage, encrypting them, and providing them. This enables effective analysis of medical data and makes it possible to use the data for new research and development of new treatments.

[0118] "Healthcare professionals" is a general term for people who work in medical institutions such as hospitals and clinics, examining, treating, and caring for patients.

[0119] "Patient Data" means any data related to a patient's diagnosis or treatment, including symptoms, vital signs, and medical records.

[0120] "Means of receiving" refers to the function of inputting data into a specific device or system using a communication protocol or network.

[0121] "Analysis" is the process of analyzing collected data using technologies such as artificial intelligence algorithms to identify potential diagnoses, treatment plans, and areas for improvement.

[0122] "Candidate diagnoses" are a list of possible diagnoses identified by an artificial intelligence algorithm based on patient data.

[0123] A "treatment plan" is a detailed treatment policy and specific treatment method formulated based on the diagnostic results.

[0124] An "artificial intelligence algorithm" is a computer program that uses techniques such as machine learning and deep learning to analyze data and make inferences.

[0125] "Presentation means" refers to the function of visually showing the analysis results, diagnostic candidates, and treatment plans to the user via a display device or terminal.

[0126] A "communications protocol" is a set of rules and procedures for data communication, and is a set of regulations for standardizing and safely transmitting and receiving data.

[0127] A "terminal" is an electronic device for inputting and displaying data, and refers to PCs, tablets, and smartphones used by medical professionals and users.

[0128] "Encryption" is the process of transforming original information into another form using a specific algorithm in order to protect the data.

[0129] A "smartphone app" is a software application that runs on a smartphone and provides health data input and notification functions.

[0130] "Distributed processing technology" is a technology that uses multiple computer resources to analyze and process data simultaneously and in parallel.

[0131] "Secure storage" refers to a data storage system in which data is stored securely and has data access control and encryption functions.

[0132] This system aims to enable medical professionals to efficiently collect and analyze patient data and provide appropriate diagnoses and treatment plans. It also aims to analyze health data from users' daily lives and provide appropriate health advice, as well as analyze medical records and treatment data collected from multiple hospitals to aid in new research and the development of new treatments. This system consists of three main components: a server, a terminal, and a user.

[0133] Hardware and Software

[0134] server

[0135] The server plays a central role in receiving, analyzing, and storing data. The software used includes artificial intelligence algorithms for analysis (e.g., TensorFlow and PyTorch). HTTPS and TLS protocols are used to securely receive and transmit data. Apache Spark is used for distributed data processing.

[0136] Terminal

[0137] A device is a device where a healthcare professional or user enters data, and can be a PC, tablet, or smartphone. The device runs an electronic medical record system (e.g., Epic or Cerner) or a health app (e.g., HealthKit or Google Fit). Secure communication protocols are used to transmit data from the device.

[0138] User

[0139] Users are responsible for inputting and collecting health data in their daily lives. The collected data is sent to a server via a smartphone app, and notifications are received from the server.

[0140] Data collection and analysis

[0141] Support for medical professionals

[0142] 1. Data Collection:

[0143] The device allows medical professionals to input a patient's symptoms, vital signs, and medical records into an electronic medical record. For example, a doctor inputs and saves a patient's temperature and blood pressure, and the data is then sent to a server.

[0144] The terminal transmits the input data to the server using a secure protocol.

[0145] 2. Data Analysis:

[0146] The server analyzes the received patient data using AI algorithms, and for example, the server lists possible diagnoses such as cold, flu, or COVID-19.

[0147] The server generates the analysis results and sends them to the terminal.

[0148] 3. Results presentation:

[0149] The device then displays the received diagnostic candidates and treatment plans to the medical professional, who can then review the diagnosis results and modify the treatment plan as necessary.

[0150] Prevention and health promotion

[0151] 1. Data Collection:

[0152] Users input their daily diet, exercise, and sleep data into a health app on their smartphone. For example, when a user inputs and saves their dietary information, it is automatically sent to the server.

[0153] The smartphone periodically synchronizes data with the server.

[0154] 2. Data Analysis:

[0155] The server then analyzes the received health data using AI algorithms, identifying, for example, nutritional deficiencies and areas for improvement in exercise habits.

[0156] The server generates health advice based on the analysis results and sends it to the smartphone.

[0157] 3. Result notification:

[0158] The smartphone will then notify the user of the health advice it has received, such as messages like "Eat more vegetables" or "We recommend walking 30 minutes a day."

[0159] Utilizing medical data

[0160] 1. Data Collection:

[0161] Multiple hospitals provide medical records and treatment data to the server, for example by exporting the data weekly and sending it to the server in a secure manner.

[0162] The server stores the received data and accumulates it in a data warehouse.

[0163] 2. Data Analysis:

[0164] The server then uses AI algorithms to analyze the large amounts of medical data it receives, for example by analyzing the data in detail to identify the effectiveness of new treatments.

[0165] The server identifies the analysis results as new research concepts and treatments and generates feedback.

[0166] 3. Results provided:

[0167] The server provides the analysis results to research institutions and pharmaceutical companies. The results are stored in secure storage and provided in encrypted form.

[0168] Examples of concrete examples and prompts

[0169] Specific examples include cases where a doctor enters data on a patient complaining of fever, cough, or fatigue into an electronic medical record, which is then analyzed by a server to suggest possible diagnoses, or where a user enters information about their diet and exercise into a health app, which then analyzes the information and provides health advice. Another example is the analysis of treatment data from hospitals across the country to help with new drug development.

[0170] Example prompt sentence:

[0171] 1. "Doctors enter fever, cough, and fatigue into patients' electronic medical records, and the server analyzes this data using AI to generate potential diagnoses."

[0172] 2. "Users enter their dietary information and exercise amount into the app, and the server analyzes that data using AI to generate health advice."

[0173] 3. "Please explain the process by which a server uses AI to analyze cancer treatment data provided by hospitals across the country, identify the effectiveness of new treatments, and provide the results to research institutions."

[0174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0175] Support for medical professionals

[0176] Data collection

[0177] Step 1:

[0178] A medical professional opens the electronic medical record system using a terminal (PC or tablet). For example, a doctor operates the electronic medical record software on the hospital's local server and logs in.

[0179] Step 2:

[0180] Medical staff enter data such as patient information, symptoms, and vital signs, such as the patient's temperature, blood pressure, and symptoms (fever, cough, fatigue) using a keyboard or touchscreen.

[0181] Input: Patient's vital signs and symptoms, including temperature and blood pressure

[0182] Output: Dataset of input patient information

[0183] Step 3:

[0184] The terminal sends the entered data to the server using a secure communication protocol (HTTPS or TLS). For example, when a doctor clicks the "Save" button, the electronic medical record system encrypts the data and sends it to the server in real time.

[0185] Input: Dataset of entered patient information

[0186] Output: Securely transmitted patient information

[0187] Data analysis

[0188] Step 4:

[0189] The server then passes the received patient data to an artificial intelligence algorithm for analysis. For example, a patient's symptom data is fed into an AI model running on TensorFlow or PyTorch.

[0190] Input: Dataset of patient information

[0191] Output: Analysis request by AI algorithm

[0192] Step 5:

[0193] The server analyzes the data and matches symptoms with potential diagnoses. For example, an AI model could analyze a patient's symptom data and come up with a list of possibilities, such as cold, flu, or COVID-19.

[0194] Input: Analysis request by AI algorithm

[0195] Output: Diagnosis candidate list

[0196] Step 6:

[0197] The server formats the generated diagnostic candidates and treatment plans for the electronic medical record system, encrypts them, and transmits them to the terminal.

[0198] Input: Diagnosis candidate list

[0199] Output: Encrypted diagnosis candidate list and treatment plan

[0200] Results presentation

[0201] Step 7:

[0202] The terminal receives the diagnosis candidates and treatment plans from the server and presents them to the medical staff. For example, a list of diagnosis candidates is displayed on the electronic medical record screen.

[0203] Input: Encrypted diagnostic candidate list and treatment plan

[0204] Output: A list of diagnostic candidates and a treatment plan displayed on the screen

[0205] Prevention and health promotion

[0206] Data collection

[0207] Step 1:

[0208] The user opens a health app on their smartphone, for example, HealthKit or Google Fit.

[0209] Step 2:

[0210] Users input their daily diet, exercise, and sleep data. For example, they record their diet and exercise amount in the app by tapping or voice input.

[0211] Input: Daily diet, exercise, and sleep data

[0212] Output: A dataset of the input health data

[0213] Step 3:

[0214] The smartphone securely transmits collected data to the server, and it is assumed that data will be transmitted periodically using the automatic synchronization function.

[0215] Input: A dataset of input health data

[0216] Output: Securely transmitted health data

[0217] Data analysis

[0218] Step 4:

[0219] The server passes the received health data to an artificial intelligence algorithm for analysis. For example, the health data is input into an AI model.

[0220] Input: Health data dataset

[0221] Output: AI analysis request

[0222] Step 5:

[0223] The server analyzes the data and identifies health risks and areas for improvement. For example, AI models can identify nutrient deficiencies or lack of exercise.

[0224] Input: AI analysis request

[0225] Output: List of health risks and improvements

[0226] Step 6:

[0227] The server formats the generated health advice so that it can be sent to a smartphone, encrypts it, and sends it.

[0228] Input: List of health risks and improvements

[0229] Output: Encrypted health advice

[0230] Result notification

[0231] Step 7:

[0232] The smartphone notifies the user of the health advice received from the server. For example, a health message is displayed in the notification area of ​​the app.

[0233] Input: Encrypted health advice

[0234] Output: Notified health advice

[0235] Utilizing medical data

[0236] Data collection

[0237] Step 1:

[0238] Multiple hospitals provide medical records and treatment data to the server. For example, hospital information system personnel export the data and send it to the server using a secure file transfer protocol.

[0239] Input: Medical records and treatment data

[0240] Output: Transmitted medical data

[0241] Data analysis

[0242] Step 2:

[0243] The server stores the received data and accumulates it in a data warehouse.

[0244] Input: Transmitted medical data

[0245] Output: Stored medical data

[0246] Step 3:

[0247] The server inputs large amounts of medical data into an artificial intelligence algorithm for analysis, and the data is processed using distributed processing technology.

[0248] Input: Stored medical data

[0249] Output: AI analysis request

[0250] Step 4:

[0251] The server performs the analysis to identify treatment effects and trends. For example, data is analyzed in detail to identify the effects of new treatment A.

[0252] Input: AI analysis request

[0253] Output: Analysis results (treatment effects and trends)

[0254] Providing results

[0255] Step 5:

[0256] The server provides the analysis results to research institutions and pharmaceutical companies. The analysis results are stored in secure storage and provided in encrypted form.

[0257] Input: Analysis results (treatment effects and trends)

[0258] Output: Securely encrypted data provided

[0259] (Application example 1)

[0260] 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."

[0261] Currently, quality control is extremely important in the medical device manufacturing process, but conventional methods have issues such as delayed detection of defective products and the enormous effort and time required for overall product quality control. Furthermore, in medical settings, diagnoses and treatment plans must be made quickly and accurately, placing a heavy burden on medical professionals. Furthermore, to effectively utilize the large amounts of data collected in factories, real-time data analysis and quality control are required. To solve these issues, an advanced data analysis system utilizing AI technology and an efficient infrastructure to implement it are required.

[0262] 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.

[0263] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; data collection means for receiving manufacturing data acquired by machines used in a factory and performing quality evaluation; means including an artificial intelligence algorithm for analyzing the manufacturing data in real time and identifying potential defects and defective products; and means for displaying quality control information on the manufacturing line based on the analysis results. This enables the improvement of the accuracy of diagnoses and treatment plans in medical settings, as well as the efficiency of quality control on the manufacturing line in the factory and the reduction of defective products.

[0264] "Healthcare workers" is a general term for doctors, nurses, and other health care professionals who diagnose and treat patients in hospitals and clinics.

[0265] "Patient data" refers to information collected in medical settings, such as patient symptoms, vital signs, and medical records.

[0266] "Artificial intelligence algorithm" is a general term for computational methods and programs used to analyze large amounts of data and generate specific results.

[0267] "Candidate diagnoses" is a list of possible diagnostic results based on the input data.

[0268] A "treatment plan" refers to a set of proposed treatment methods or steps based on a particular diagnosis.

[0269] "Machinery used in factories" is a general term for all automated devices and machinery used in the manufacturing process.

[0270] "Manufacturing data" refers to process data and quality data acquired by machines in a factory.

[0271] "Data collection means" refers to a device or system for collecting patient data or manufacturing data.

[0272] "Quality evaluation" refers to the process of determining whether manufactured products meet standards.

[0273] "Real-time" refers to instantaneous processing and response, meaning there is little to no delay.

[0274] A "latent defect" refers to a problem or defect that is likely to be present in a product but has not yet become apparent.

[0275] "Defective Product" means a product that does not meet standards and is not suitable for use or sale.

[0276] "Quality control information" refers to information on the quality status of a product and defect detection, and management and improvements are carried out based on this information.

[0277] "Cloud server" is a general term for a remote server where data is stored and processed via the Internet.

[0278] "Improvement proposals" refer to methods and measures for improving products or processes proposed based on the analysis results.

[0279] "Pharmaceutical company" is a general term for companies that research, develop, manufacture, and sell new drugs.

[0280] "Research institute" is a general term for organizations that conduct research activities with the aim of developing new knowledge and technology.

[0281] This invention is a system that reduces the burden on medical professionals, improves the quality of medical care, and streamlines quality control in the manufacturing industry. This system utilizes AI technology in both medical and manufacturing settings to perform data analysis and realize diagnostic support and quality control.

[0282] Support for medical professionals

[0283] The server receives patient data entered by medical professionals and analyzes it using AI algorithms. For example, when a medical professional enters a patient's symptoms and vital signs into an electronic medical record, the server receives this information and uses an AI model to generate potential diagnoses, such as cold, flu, or COVID-19. This information is then sent to the medical professional's device to help with detailed examinations.

[0284] Factory quality control

[0285] The server receives manufacturing data acquired by machines used in the factory and collects the data for quality evaluation. For example, a camera attached to a factory device takes a picture of a medical device being manufactured and sends the image data to the server. The server then analyzes the image using an AI algorithm to identify potential defects or defective products. The analysis results are displayed on the production line and provided as quality control information.

[0286] Data collection and analysis for health promotion

[0287] When users enter their daily health data into their smartphone, the server receives it and uses AI algorithms to identify health risks and areas for improvement. For example, when a user enters their daily diet and exercise amount into the app, the server analyzes any nutrient deficiencies and areas for improvement in exercise, and sends appropriate advice to the smartphone.

[0288] Hardware and software used

[0289] The hardware used includes medical staff tablets and PCs, cameras on the production line, and users' smartphones, and the software used is Python, OpenCV, TensorFlow / Keras, and the Requests library.

[0290] Data processing and calculation

[0291] 1. Data collection: Collecting patient and manufacturing data from terminals and machines.

[0292] 2. Data Preprocessing: The image data undergoes preprocessing such as resizing, normalization, and reshaping.

[0293] 3. AI analysis: Analyze the data using pre-trained AI models to generate candidate diagnoses and quality assessments.

[0294] 4. Notification: The analysis results are sent to devices and production lines for use in medical and manufacturing settings.

[0295] Examples and prompts

[0296] For example, if a manufacturing line is making surgical tools, the robot will take a picture of the part with a camera and pass the image to an AI model for analysis, which will determine if the part is defective and, if necessary, send the data to a server.

[0297] Example prompt sentence:

[0298] Analyze images taken from a production line today and list the parts that are likely to be defective. Also, describe in detail which parts are problematic.

[0299] This system will improve the accuracy of diagnosis and treatment planning in medical settings, while also making quality control more efficient and reducing defective products on factory production lines.

[0300] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0301] Step 1:

[0302] Users input data using devices (medical staff's tablets or PCs, or cameras on the manufacturing line). The input data includes patient symptoms, vital signs, and images of medical equipment being manufactured. This prepares the data to be sent to the server.

[0303] Step 2:

[0304] The device sends the input data to the server. The server checks the format of the received data and performs preprocessing as necessary. For example, if the data is image data, it resizes or normalizes it, and if it is text data, it checks the format. This ensures data consistency and makes it suitable for analysis.

[0305] Step 3:

[0306] The server inputs the preprocessed data into an AI algorithm, which analyzes the data based on a pre-trained model and generates a diagnosis candidate, a treatment plan, or a quality assessment. For example, for image data sent from a manufacturing line, it scores the likelihood of a defective product. This generates a data analysis result.

[0307] Step 4:

[0308] The server checks the generated analysis results and performs additional analysis as necessary. The analysis results are also sent to the cloud server and used for further analysis and feedback. For example, new treatments or quality improvement measures may be proposed based on the analysis results. This improves the reliability and usefulness of the analysis results.

[0309] Step 5:

[0310] The server notifies the terminal of the generated analysis results and suggestions, which are then displayed on the terminal to medical professionals and production line workers. Specifically, medical professionals are shown potential diagnoses and treatment plans, while production line workers are shown a list of defective products and suggestions for quality improvement. This enables the data to be put to practical use.

[0311] Step 6:

[0312] Users (healthcare professionals and production line workers) can then take action based on the displayed analysis results and recommendations: healthcare professionals adjust diagnoses and treatment plans, and production line workers implement quality improvement measures, leading to continuous improvement of the entire system.

[0313] 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.

[0314] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[0315] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[0316] Support for medical professionals

[0317] Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[0318] Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[0319] Result presentation: The server sends the generated diagnosis candidates and treatment plans to the terminal, which displays them to the medical professional.

[0320] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[0321] Prevention and health promotion

[0322] Data collection: Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The smartphone then sends the collected data to a server.

[0323] Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[0324] Result notification: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[0325] Emotion recognition: The emotion engine recognizes emotions from smartphone input data and user behavior.

[0326] Emotion-based advice adjustment: Based on the emotions recognized by the emotion engine, the server adjusts health advice and improvement guidance.

[0327] Example: When a user enters their daily diet and exercise amount into the app, the server analyzes this and points out any missing nutrients or areas for improvement in exercise. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), it adjusts the advice more flexibly. For example, if the user is feeling stressed, it will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[0328] Utilizing medical data

[0329] Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[0330] Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[0331] Result provision: Based on the analysis results, the server generates feedback for new research concepts and new drug development and provides it to research institutions and pharmaceutical companies.

[0332] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[0333] The system with these functions will be able to provide flexible advice that takes into account the user's psychological state by incorporating an emotion engine, further improving the quality of medical care and health management. The system's flexible structure will allow it to adapt to different medical environments and user needs.

[0334] The processing flow will be explained below.

[0335] Support for medical professionals

[0336] Step 1:

[0337] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[0338] Step 2:

[0339] Terminal: Sends the entered patient data to the server.

[0340] Step 3:

[0341] Server: Stores the received patient data.

[0342] Step 4:

[0343] Server: Analyzes stored patient data using artificial intelligence algorithms.

[0344] Step 5:

[0345] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[0346] Step 6:

[0347] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[0348] Step 7:

[0349] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[0350] Prevention and health promotion

[0351] Step 1:

[0352] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[0353] Step 2:

[0354] Smartphone: Sends the entered health data to the server.

[0355] Step 3:

[0356] Server: Stores the received health data.

[0357] Step 4:

[0358] Server: Analyzes stored health data using artificial intelligence algorithms.

[0359] Step 5:

[0360] Server: Identifies health risks and areas for improvement based on the analysis results.

[0361] Step 6:

[0362] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[0363] Step 7:

[0364] Server: Sends the generated health advice and improvement guidance to a smartphone.

[0365] Step 8:

[0366] Smartphone: Provides health advice and guidance to users.

[0367] Step 9:

[0368] Emotion Engine: Recognizes emotions from user input data and their behavior.

[0369] Step 10:

[0370] Emotion Engine: Sends instructions to the server based on the recognized emotion.

[0371] Step 11:

[0372] Server: Receives instructions from the emotion engine and adjusts health advice and improvement guidance.

[0373] Step 12:

[0374] Server: Resends tailored advice and improvement guidance to the smartphone.

[0375] Step 13:

[0376] Smartphone: Notify users with tailored advice and guidance.

[0377] Utilizing medical data

[0378] Step 1:

[0379] Hospital: Provides medical records and treatment data to the server.

[0380] Step 2:

[0381] Server: Receives and stores the data provided.

[0382] Step 3:

[0383] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[0384] Step 4:

[0385] Server: Identify treatment effects and trends from analysis results.

[0386] Step 5:

[0387] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[0388] Step 6:

[0389] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[0390] Example 2

[0391] 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."

[0392] Conventional medical support systems were able to analyze medical and daily health data to provide potential diagnoses, treatment plans, and health advice. However, it was difficult to provide flexible advice and treatment plans that took the user's emotional state into account, which sometimes resulted in insufficient support for medical professionals and users. This created a challenge: improving the quality of medical care while simultaneously reducing the psychological burden on patients and users.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0394] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion recognition engine for analyzing the emotional state of the user; and means for adjusting the candidate diagnoses and treatment plans based on the emotional state obtained by the emotion recognition engine. This enables the provision of flexible advice and appropriate treatment plans that take the user's emotional state into consideration.

[0395] "Medical professionals" refer to professionals who perform medical procedures such as medical examinations, treatment, and nursing for patients at medical institutions.

[0396] "Patient data" refers to all information necessary for medical examination and treatment, such as a patient's symptoms, vital signs, and medical records.

[0397] An "artificial intelligence algorithm" refers to a program that uses techniques such as machine learning and deep learning to analyze large amounts of data and generate conclusions and predictions based on specific purposes.

[0398] "Candidate diagnoses" refers to a list of likely diseases or conditions based on a patient's symptoms and data.

[0399] A "treatment plan" is a plan that includes details of the treatment to be administered to a patient, based on the results of a diagnosis.

[0400] "User" refers to medical professionals and general individuals who use the system, and who input health data and check diagnosis results.

[0401] "Health data" refers to all information related to an individual's health status, such as diet, exercise, sleep, and physical condition.

[0402] An "emotion recognition engine" refers to a program that analyzes and identifies a user's emotional state (e.g., stress, joy, sadness, etc.) from input data and user behavior.

[0403] "Health advice" refers to suggestions and guidance for maintaining and improving health that are provided to users based on health data and analysis results.

[0404] A "research institution" refers to an organization or group that develops new medical technologies and drugs, researches treatment methods, etc.

[0405] "Drug development companies" refer to companies that research, develop, manufacture, and sell new drugs.

[0406] "Medical record" means any record relating to the examination, treatment, and follow-up of a patient.

[0407] "Treatment data" refers to information about the effectiveness, results, and patient response of a particular treatment.

[0408] "Analysis results" refers to output information such as conclusions, predictions, and findings obtained as a result of data analysis by AI algorithms.

[0409] "Feedback" refers to advice and suggestions for new research concepts, treatments, and new drug development that are generated based on the analysis results.

[0410] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[0411] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[0412] Support for medical professionals

[0413] Data collection

[0414] On the terminal (healthcare worker's PC or tablet), healthcare workers input the patient's symptoms, vital signs, and medical records into the electronic medical record. Specific hardware used is a standard PC or tablet. The terminal sends the input data to a server. The software used is an electronic medical record system.

[0415] Data analysis

[0416] The server then analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used. During the analysis process, potential diagnoses are listed based on the patient's symptoms and vital signs.

[0417] Results presentation

[0418] The server sends the generated diagnosis candidates and treatment plans to a terminal, which then displays them to the medical staff via an electronic medical record system or medical information system.

[0419] Examples:

[0420] When a patient visits the hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses TensorFlow to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional then conducts a detailed examination based on this list.

[0421] Prevention and health promotion

[0422] Data collection

[0423] Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The hardware used is a smartphone, and the specific software used is a health management app. The smartphone then sends the collected data to a server.

[0424] Data analysis

[0425] The server then analyzes the received health data using AI algorithms to identify health risks and areas for improvement, using machine learning frameworks such as Keras.

[0426] Result notification

[0427] The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[0428] Emotion recognition

[0429] The emotion engine recognizes emotions from smartphone input data and user behavior. The software used is an emotion recognition algorithm.

[0430] Emotion-based advice adjustment

[0431] Based on the emotions recognized by the emotion engine, the server tailors health advice and improvement guidance.

[0432] Examples:

[0433] When a user enters their daily diet and exercise amount into a health management app, the server analyzes the data and identifies any nutrient deficiencies or areas for improvement. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), the advice is adjusted more flexibly. For example, if the user is feeling stressed, the server will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[0434] Utilizing medical data

[0435] Data collection

[0436] Hospitals provide medical records and treatment data to the server, which receives and stores the data.

[0437] Data analysis

[0438] The server uses AI algorithms to analyze the large amounts of medical data it receives and identify treatment effects and trends, using big data analysis tools such as Apache Spark and H2O.ai.

[0439] Providing results

[0440] Based on the analysis results, the server generates feedback for new research concepts and new drug development, and provides it to research institutions and drug development companies.

[0441] Examples:

[0442] Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If new treatments are found to be significantly effective against specific types of cancer, the server can provide this information to research institutions and drug development companies to promote further research and new drug development.

[0443] Example prompt for a generative AI model:

[0444] "Please suggest what health advice should be given to users who are experiencing stress."

[0445] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0446] Support for medical professionals

[0447] Step 1: User (healthcare professional) enters patient data

[0448] Users (healthcare professionals) input patients' symptoms, vital signs, and medical records into the electronic medical record system using devices such as PCs and tablets.

[0449] Input: Patient symptoms, vital signs, medical records

[0450] Output: Data entered into the electronic medical record system

[0451] Specific action: A healthcare professional types text or clicks an option on a PC or tablet.

[0452] Step 2: The device sends the data to the server

[0453] The terminal transmits the input data to the server via the network.

[0454] Input: Data entered into the electronic medical record system

[0455] Output: Patient data sent to the server

[0456] What it does: The device encrypts the data and sends it to the server using the HTTPS protocol.

[0457] Step 3: The server parses the data

[0458] The server analyzes the received patient data using AI algorithms, specifically software such as TensorFlow and PyTorch.

[0459] Input: Patient data sent to the server

[0460] Output: A list of diagnostic candidates and a treatment plan as the analysis results

[0461] Specific operation: The server cleanses the data, supplies it to the AI ​​model, and executes a Python script to generate analysis results.

[0462] Step 4: The server sends the results to the device

[0463] The server sends the generated diagnosis candidates and treatment plans to the terminal.

[0464] Input: A list of diagnostic candidates and a treatment plan as the analysis results

[0465] Output: Result data sent to the terminal

[0466] Specific operation: The server encrypts the analysis results and sends them to the device through a secure channel.

[0467] Step 5: The terminal displays the results

[0468] The device displays the received diagnostic candidates and treatment plans to medical professionals.

[0469] Input: Result data sent to the terminal

[0470] Output: Possible diagnoses and treatment plans displayed to healthcare professionals

[0471] Specific operation: The terminal displays data on the screen of an electronic medical record system, etc.

[0472] Prevention and health promotion

[0473] Step 1: User enters health data

[0474] Users enter their daily health data (diet, exercise, sleep, physical condition, etc.) into a health management app on their smartphone.

[0475] Input: Daily health data (diet, exercise, sleep, physical condition)

[0476] Output: Data entered into the health management app

[0477] Specific action: A user taps and swipes on a smartphone to enter data.

[0478] Step 2: The device sends the data to the server

[0479] The smartphone sends the entered health data to a server.

[0480] Input: Data entered into the health management app

[0481] Output: Health data sent to the server

[0482] Specific operation: The smartphone sends data to the server via Wi-Fi or mobile data communication.

[0483] Step 3: The server parses the data

[0484] The server analyzes the received health data using an AI algorithm, specifically the software Keras.

[0485] Input: Health data sent to the server

[0486] Output: Health risks and improvements as a result of the analysis

[0487] Specific operation: The server supplies data to the AI ​​model, which then calculates risks and areas for improvement.

[0488] Step 4: The server analyzes the emotional state

[0489] An emotion recognition engine recognizes the user's emotional state from the received data.

[0490] Input: Health data and related data

[0491] Output: Emotional state as a result of analysis

[0492] Specific operation: The server identifies the emotion using an emotion recognition algorithm.

[0493] Step 5: Servers adjust advice

[0494] The server adjusts health advice and improvement guidance based on the emotional state obtained from the emotion recognition engine.

[0495] Input: Emotion recognition results and health analysis results

[0496] Output: Tailored health advice and guidance

[0497] Specific behavior: The server generates advice and modifies the content according to the emotional state.

[0498] Step 6: The server sends the results to the device

[0499] The server then sends the generated health advice and improvement guidance to a smartphone.

[0500] Input: Tailored health advice and guidance

[0501] Output: Advice and guidance sent to your smartphone

[0502] Specific operation: The server encrypts the notification data and sends it to the smartphone.

[0503] Step 7: Your device will notify you of the results

[0504] The smartphone notifies the user of the advice and guidance received.

[0505] Input: Advice and guidance sent to your smartphone

[0506] Output: Advice and guidance to be given to the user

[0507] Specific action: The smartphone notifies the user via push notification or in-app message.

[0508] Utilizing medical data

[0509] Step 1: The hospital provides medical records and treatment data to the server

[0510] Multiple medical institutions provide medical records and treatment data to the server.

[0511] Input: medical records and treatment data

[0512] Output: Medical data stored on the server

[0513] Specific operation: The medical record system automatically transfers data to the server.

[0514] Step 2: The server parses the data

[0515] The server analyzes the received medical data using AI algorithms to identify treatment effects and trends, using software such as Apache Spark and H2O.ai.

[0516] Input: Medical data stored on the server

[0517] Output: Treatment effects and trend information as analysis results

[0518] Specific operation: The server supplies data to the AI ​​model and performs large-scale data analysis.

[0519] Step 3: Server generates feedback

[0520] The server generates feedback for new research concepts and new drug development based on the analysis results.

[0521] Input: Treatment effects and trend information as analysis results

[0522] Output: Feedback on research concepts and new drug development

[0523] Specific operation: The server formats the analysis results into a report format and generates the report.

[0524] Step 4: The server serves the results

[0525] The server provides the generated feedback to research institutions and drug development companies.

[0526] Input: Feedback on research concepts and new drug development

[0527] Output: Feedback provided to research institutions and drug development companies

[0528] What it does: The server encrypts the feedback and sends it to the relevant authority over a secure channel.

[0529] (Application example 2)

[0530] 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."

[0531] Current medical and health management systems do not adequately consider the psychological state of medical professionals and users, resulting in a lack of reduction in stress and emotional burden, and suboptimal treatment effectiveness and quality of health care. Furthermore, data analysis results are often significantly influenced by emotional states, making it difficult to provide appropriate diagnoses and treatment plans. Therefore, a system that can provide high-quality diagnoses, treatments, and health care recommendations while taking into account individual emotional states is needed.

[0532] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0533] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion engine for recognizing the emotional state of the user; and means for adjusting the generated candidate diagnoses and treatment plans based on the emotion recognized by the emotion engine. This enables more flexible and appropriate diagnosis, treatment, and health management proposals that take the emotional state into consideration.

[0534] A "healthcare professional" is someone whose occupation regularly provides health care services to patients.

[0535] "Patient data" refers to data that includes medical information such as a patient's symptoms, vital signs, and medical records.

[0536] "Artificial intelligence algorithms" are algorithms for analyzing data and generating predictive models in computers.

[0537] "Candidate diagnoses" are multiple disease names and pathological conditions that are presumed based on patient data.

[0538] A "treatment plan" is a specific treatment method or protocol proposed for a diagnosed disease or condition.

[0539] A "user" is an individual who uses the system, and in this context refers primarily to a person receiving health care or medical services.

[0540] "Health data" refers to data that includes information about daily health conditions such as diet, exercise, sleep, and physical condition.

[0541] An "emotion engine" is a system that recognizes the user's emotional state and provides feedback and advice based on that information.

[0542] "Drug development" is the process of developing new medicines and is based on research.

[0543] "Health advice" refers to specific guidance and suggestions aimed at reducing health risks and improving lifestyle habits.

[0544] "Treatment data" refers to medical records and data related to treatment behavior at hospitals and healthcare institutions.

[0545] To implement this invention, a medical support system incorporating an emotion engine is required. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0546] Support for medical professionals

[0547] Data collection

[0548] The terminal (a personal computer or tablet used by a healthcare professional) acts as a device where the healthcare professional inputs the patient's symptoms, vital signs, and medical records. This information is sent from the terminal to a server. The software used is an electronic medical record system, such as Epic or Cerner.

[0549] Data analysis

[0550] The server analyzes the received patient data using artificial intelligence algorithms (e.g., TensorFlow or PyTorch) to generate potential diagnoses and treatment plans. The emotion engine plays a part in this process, adjusting the diagnosis and treatment plan based on the patient's psychological state.

[0551] Results presentation

[0552] The server then sends the generated diagnosis candidates and treatment plans to a terminal, which displays them to the medical professional. For example, if a patient visits the hospital complaining of fever, cough, and fatigue, the medical professional enters these symptoms and the patient's vital signs into the electronic medical record and sends the data to the server. The server uses AI to list the most likely causes, such as cold, flu, and COVID-19, and provides a treatment plan.

[0553] Prevention and health promotion

[0554] Data collection

[0555] Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The smartphone then sends the collected data to a server. Examples of such applications include Apple Health and Google Fit.

[0556] Data analysis

[0557] The server uses AI algorithms to analyze the received health data and identify health risks and areas for improvement. An emotion engine recognizes emotions from smartphone input data and user behavior. Software such as Emotion API and DeepFace is utilized.

[0558] Result notification

[0559] The server sends the generated health advice and guidance for improvement to the smartphone, which then notifies the user. The emotion engine flexibly adjusts the advice based on the user's emotional state. For example, if a user enters their daily diet and exercise amount into the app, the server will point out any nutrient deficiencies and areas for improvement in exercise, and if the user is feeling stressed, the server will notify them by saying, "Start with a short exercise session" or "We recommend a relaxing meal."

[0560] Example prompt sentence:

[0561] "How are you feeling today? For example, if you're feeling stressed, please enter that."

[0562] "We'll suggest the best menu for you based on your food preferences and mood. Just tell us your recent diet history."

[0563] Utilizing medical data

[0564] Data collection

[0565] Multiple healthcare institutions provide medical records and treatment data to the server, which is collected using a comprehensive electronic medical record system.

[0566] Data analysis

[0567] The server analyzes large amounts of medical data using AI algorithms to identify treatment effects and trends, and an emotion engine further analyzes the data based on the patient's psychological trends.

[0568] Providing results

[0569] Based on the analysis results, feedback for new research concepts and new drug development is generated and provided to research institutions and pharmaceutical companies. This will promote the discovery of new treatments and the development of new drugs. As a specific example, if cancer treatment data is collected from hospitals across the country and AI analyzes it, and it is found that new treatment A is showing significant effectiveness against a specific type of cancer, this information can be provided to research institutions and pharmaceutical companies to enable further research and new drug development.

[0570] This system will enable medical care and health management that takes emotional states into account, improving the quality of medical care and user satisfaction.

[0571] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0572] Step 1:

[0573] The device collects patient data (symptoms, vital signs, medical records) entered by medical professionals and sends the data to a server. The input data includes information such as fever, cough, and fatigue. This data is collected and sent using an electronic medical record system (e.g., Epic, Cerner).

[0574] Step 2:

[0575] The server analyzes the patient data it receives using an artificial intelligence algorithm (e.g., TensorFlow or PyTorch). Specifically, it preprocesses the data and generates appropriate diagnostic candidates (e.g., cold, flu, COVID-19, etc.). At this time, the AI ​​model lists the diagnostic candidates in descending order based on the input data (patient symptoms).

[0576] Step 3:

[0577] The generated diagnosis candidates and treatment plans are sent to a terminal, which displays them to medical professionals. Specifically, a list of diagnosis candidates and a treatment plan based on them are displayed on the screen, and medical professionals can evaluate and make decisions.

[0578] Step 4:

[0579] The emotion engine uses the smartphone's camera and voice input functions to recognize the user's emotional state. It uses image and voice data to analyze the user's emotions (e.g., tiredness, stress, optimism, etc.). This process utilizes the Emotion API and DeepFace.

[0580] Step 5:

[0581] The server takes the user's emotional state into account to adjust potential diagnoses and treatment plans. Specifically, it modifies the usual diagnosis and treatment plan based on the user's emotional state. For example, if stress is causing symptoms to worsen, the server generates a treatment plan that also addresses that.

[0582] Step 6:

[0583] Users enter their daily health data (food, exercise, sleep, physical condition) into a smartphone app, and this data is sent to a server via applications such as Apple Health and Google Fit.

[0584] Step 7:

[0585] The server analyzes the received health data and uses an artificial intelligence algorithm to identify health risks and areas for improvement. As a result of the analysis, it identifies areas for improvement such as nutrient deficiencies and exercise. Specific health advice is generated based on this data.

[0586] Step 8:

[0587] The emotion engine analyzes the user's emotional state and adjusts health advice and guidance accordingly. For example, a user feeling stressed may be given flexible advice such as "Start with a short workout" or "Recommend a relaxing diet."

[0588] Step 9:

[0589] The server then sends the generated health advice and guidance to the smartphone, which then notifies the user by displaying the information to the user via a pop-up notification or push notification.

[0590] Step 10:

[0591] Multiple healthcare institutions provide medical records and treatment data to the server, which is collected using a comprehensive electronic medical record system.

[0592] Step 11:

[0593] The server analyzes large amounts of medical data using AI algorithms to identify treatment effects and trends, and an emotion engine analyzes the data while taking into account the patient's psychological trends.

[0594] Step 12:

[0595] Based on the analysis results, feedback for new research concepts and new drug development will be generated and provided to research institutions and pharmaceutical companies, thereby accelerating the discovery of new treatments and the development of new drugs.

[0596] This provides a concrete explanation of the processing steps of the entire system, clarifying the data processing and calculations performed at each step, as well as the output based on these.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] [Second embodiment]

[0601] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0602] 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.

[0603] 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).

[0604] 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.

[0605] 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.

[0606] 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).

[0607] 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.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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."

[0613] The present invention provides a system that aims to reduce the burden on medical professionals, improve the quality of medical care, increase patient satisfaction, and effectively utilize medical data. This system is embodied in the following specific form.

[0614] The system consists of three main components: the server, the terminal, and the user.

[0615] Support for medical professionals

[0616] 1. Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[0617] 2. Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[0618] 3. Presentation of results: The server sends the generated diagnostic candidates and treatment plans to the terminal, which displays them to the medical professional.

[0619] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[0620] Prevention and health promotion

[0621] 1. Data collection: Users enter their daily health data, such as diet, exercise, sleep, and physical condition, into a smartphone app. The smartphone then sends the collected data to a server.

[0622] 2. Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[0623] 3. Notification of results: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[0624] Example: When a user enters their daily diet and exercise amount into an app, the server analyzes the information and identifies any nutrient deficiencies and areas for improvement in exercise. The app then notifies the user with messages such as "Eat more vegetables" or "We recommend walking 30 minutes every day."

[0625] Utilizing medical data

[0626] 1. Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[0627] 2. Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[0628] 3. Providing results: The server generates feedback for new research concepts and new drug development based on the analysis results and provides them to research institutions and pharmaceutical companies.

[0629] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[0630] A system with these functions will be able to comprehensively solve Japan's health issues through supporting medical professionals, prevention and health promotion, and effective use of medical data. In addition, the system's flexible structure allows it to adapt to different medical environments and user needs.

[0631] The processing flow will be explained below.

[0632] Support for medical professionals

[0633] Step 1:

[0634] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[0635] Step 2:

[0636] Terminal: Sends the entered patient data to the server.

[0637] Step 3:

[0638] Server: Stores the received patient data.

[0639] Step 4:

[0640] Server: Analyzes stored patient data using artificial intelligence algorithms.

[0641] Step 5:

[0642] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[0643] Step 6:

[0644] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[0645] Step 7:

[0646] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[0647] Prevention and health promotion

[0648] Step 1:

[0649] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[0650] Step 2:

[0651] Smartphone: Sends the entered health data to the server.

[0652] Step 3:

[0653] Server: Stores the received health data.

[0654] Step 4:

[0655] Server: Analyzes stored health data using artificial intelligence algorithms.

[0656] Step 5:

[0657] Server: Identifies health risks and areas for improvement based on the analysis results.

[0658] Step 6:

[0659] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[0660] Step 7:

[0661] Server: Sends the generated health advice and improvement guidance to a smartphone.

[0662] Step 8:

[0663] Smartphone: Provides health advice and guidance to users.

[0664] Utilizing medical data

[0665] Step 1:

[0666] Hospital: Provides medical records and treatment data to the server.

[0667] Step 2:

[0668] Server: Receives and stores the data provided.

[0669] Step 3:

[0670] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[0671] Step 4:

[0672] Server: Identify treatment effects and trends from analysis results.

[0673] Step 5:

[0674] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[0675] Step 6:

[0676] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[0677] Example 1

[0678] 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."

[0679] In the medical field, medical professionals are required to efficiently collect patient data and quickly provide diagnoses and treatment plans based on that data. It is also important to accurately collect and analyze health data from patients' daily lives and provide appropriate health advice. Furthermore, there is a need to effectively analyze medical records and treatment data collected from multiple hospitals and use the data for new research and the development of new treatments. To solve these challenges, a system is needed to efficiently and safely perform each process of data collection, analysis, and provision.

[0680] 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.

[0681] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including a terminal for transmitting the patient data to the server using a secure communication protocol; and means for encrypting and transmitting the candidate diagnoses and treatment plans from the server to the terminal, thereby enabling medical professionals to quickly and safely collect and analyze patient data and provide appropriate diagnoses and treatment plans.

[0682] In this invention, the server includes means for receiving daily health data entered by the user, means including an artificial intelligence algorithm for analyzing the health data and identifying health risks and areas for improvement, means for notifying the user of the generated health advice and improvement guidance, means for transmitting the user's input data from a smartphone app to the server, and means for notifying the smartphone of the analysis results, thereby enabling the user to easily collect and analyze health data from their daily lives and receive appropriate health advice.

[0683] Furthermore, in this invention, the server includes: means for receiving medical records and treatment data from multiple hospitals; means including an artificial intelligence algorithm for analyzing the received data and identifying treatment effects and trends; means for generating feedback for new research concepts and new drug development based on the analysis results and providing the feedback to research institutions and pharmaceutical companies; means for analyzing the data using distributed processing technology; and means for storing the analysis results in secure storage, encrypting them, and providing them. This enables effective analysis of medical data and makes it possible to use the data for new research and development of new treatments.

[0684] "Healthcare professionals" is a general term for people who work in medical institutions such as hospitals and clinics, examining, treating, and caring for patients.

[0685] "Patient Data" means any data related to a patient's diagnosis or treatment, including symptoms, vital signs, and medical records.

[0686] "Means of receiving" refers to the function of inputting data into a specific device or system using a communication protocol or network.

[0687] "Analysis" is the process of analyzing collected data using technologies such as artificial intelligence algorithms to identify potential diagnoses, treatment plans, and areas for improvement.

[0688] "Candidate diagnoses" are a list of possible diagnoses identified by an artificial intelligence algorithm based on patient data.

[0689] A "treatment plan" is a detailed treatment policy and specific treatment method formulated based on the diagnostic results.

[0690] An "artificial intelligence algorithm" is a computer program that uses techniques such as machine learning and deep learning to analyze data and make inferences.

[0691] "Presentation means" refers to the function of visually showing the analysis results, diagnostic candidates, and treatment plans to the user via a display device or terminal.

[0692] A "communications protocol" is a set of rules and procedures for data communication, and is a set of regulations for standardizing and safely transmitting and receiving data.

[0693] A "terminal" is an electronic device for inputting and displaying data, and refers to PCs, tablets, and smartphones used by medical professionals and users.

[0694] "Encryption" is the process of transforming original information into another form using a specific algorithm in order to protect the data.

[0695] A "smartphone app" is a software application that runs on a smartphone and provides health data input and notification functions.

[0696] "Distributed processing technology" is a technology that uses multiple computer resources to analyze and process data simultaneously and in parallel.

[0697] "Secure storage" refers to a data storage system in which data is stored securely and has data access control and encryption functions.

[0698] This system aims to enable medical professionals to efficiently collect and analyze patient data and provide appropriate diagnoses and treatment plans. It also aims to analyze health data from users' daily lives and provide appropriate health advice, as well as analyze medical records and treatment data collected from multiple hospitals to aid in new research and the development of new treatments. This system consists of three main components: a server, a terminal, and a user.

[0699] Hardware and Software

[0700] server

[0701] The server plays a central role in receiving, analyzing, and storing data. The software used includes artificial intelligence algorithms for analysis (e.g., TensorFlow and PyTorch). HTTPS and TLS protocols are used to securely receive and transmit data. Apache Spark is used for distributed data processing.

[0702] Terminal

[0703] A device is a device where a healthcare professional or user enters data, and can be a PC, tablet, or smartphone. The device runs an electronic medical record system (e.g., Epic or Cerner) or a health app (e.g., HealthKit or Google Fit). Secure communication protocols are used to transmit data from the device.

[0704] User

[0705] Users are responsible for inputting and collecting health data in their daily lives. The collected data is sent to a server via a smartphone app, and notifications are received from the server.

[0706] Data collection and analysis

[0707] Support for medical professionals

[0708] 1. Data Collection:

[0709] The device allows medical professionals to input a patient's symptoms, vital signs, and medical records into an electronic medical record. For example, a doctor inputs and saves a patient's temperature and blood pressure, and the data is then sent to a server.

[0710] The terminal transmits the input data to the server using a secure protocol.

[0711] 2. Data Analysis:

[0712] The server analyzes the received patient data using AI algorithms, and for example, the server lists possible diagnoses such as cold, flu, or COVID-19.

[0713] The server generates the analysis results and sends them to the terminal.

[0714] 3. Results presentation:

[0715] The device then displays the received diagnostic candidates and treatment plans to the medical professional, who can then review the diagnosis results and modify the treatment plan as necessary.

[0716] Prevention and health promotion

[0717] 1. Data Collection:

[0718] Users input their daily diet, exercise, and sleep data into a health app on their smartphone. For example, when a user inputs and saves their dietary information, it is automatically sent to the server.

[0719] The smartphone periodically synchronizes data with the server.

[0720] 2. Data Analysis:

[0721] The server then analyzes the received health data using AI algorithms, identifying, for example, nutritional deficiencies and areas for improvement in exercise habits.

[0722] The server generates health advice based on the analysis results and sends it to the smartphone.

[0723] 3. Result notification:

[0724] The smartphone will then notify the user of the health advice it has received, such as messages like "Eat more vegetables" or "We recommend walking 30 minutes a day."

[0725] Utilizing medical data

[0726] 1. Data Collection:

[0727] Multiple hospitals provide medical records and treatment data to the server, for example by exporting the data weekly and sending it to the server in a secure manner.

[0728] The server stores the received data and accumulates it in a data warehouse.

[0729] 2. Data Analysis:

[0730] The server then uses AI algorithms to analyze the large amounts of medical data it receives, for example by analyzing the data in detail to identify the effectiveness of new treatments.

[0731] The server identifies the analysis results as new research concepts and treatments and generates feedback.

[0732] 3. Results provided:

[0733] The server provides the analysis results to research institutions and pharmaceutical companies. The results are stored in secure storage and provided in encrypted form.

[0734] Examples of concrete examples and prompts

[0735] Specific examples include cases where a doctor enters data on a patient complaining of fever, cough, or fatigue into an electronic medical record, which is then analyzed by a server to suggest possible diagnoses, or where a user enters information about their diet and exercise into a health app, which then analyzes the information and provides health advice. Another example is the analysis of treatment data from hospitals across the country to help with new drug development.

[0736] Example prompt sentence:

[0737] 1. "Doctors enter fever, cough, and fatigue into patients' electronic medical records, and the server analyzes this data using AI to generate potential diagnoses."

[0738] 2. "Users enter their dietary information and exercise amount into the app, and the server analyzes that data using AI to generate health advice."

[0739] 3. "Please explain the process by which a server uses AI to analyze cancer treatment data provided by hospitals across the country, identify the effectiveness of new treatments, and provide the results to research institutions."

[0740] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0741] Support for medical professionals

[0742] Data collection

[0743] Step 1:

[0744] A medical professional opens the electronic medical record system using a terminal (PC or tablet). For example, a doctor operates the electronic medical record software on the hospital's local server and logs in.

[0745] Step 2:

[0746] Medical staff enter data such as patient information, symptoms, and vital signs, such as the patient's temperature, blood pressure, and symptoms (fever, cough, fatigue) using a keyboard or touchscreen.

[0747] Input: Patient's vital signs and symptoms, including temperature and blood pressure

[0748] Output: Dataset of input patient information

[0749] Step 3:

[0750] The terminal sends the entered data to the server using a secure communication protocol (HTTPS or TLS). For example, when a doctor clicks the "Save" button, the electronic medical record system encrypts the data and sends it to the server in real time.

[0751] Input: Dataset of entered patient information

[0752] Output: Securely transmitted patient information

[0753] Data analysis

[0754] Step 4:

[0755] The server then passes the received patient data to an artificial intelligence algorithm for analysis. For example, a patient's symptom data is fed into an AI model running on TensorFlow or PyTorch.

[0756] Input: Dataset of patient information

[0757] Output: Analysis request by AI algorithm

[0758] Step 5:

[0759] The server analyzes the data and matches symptoms with potential diagnoses. For example, an AI model could analyze a patient's symptom data and come up with a list of possibilities, such as cold, flu, or COVID-19.

[0760] Input: Analysis request by AI algorithm

[0761] Output: Diagnosis candidate list

[0762] Step 6:

[0763] The server formats the generated diagnostic candidates and treatment plans for the electronic medical record system, encrypts them, and transmits them to the terminal.

[0764] Input: Diagnosis candidate list

[0765] Output: Encrypted diagnosis candidate list and treatment plan

[0766] Results presentation

[0767] Step 7:

[0768] The terminal receives the diagnosis candidates and treatment plans from the server and presents them to the medical staff. For example, a list of diagnosis candidates is displayed on the electronic medical record screen.

[0769] Input: Encrypted diagnostic candidate list and treatment plan

[0770] Output: A list of diagnostic candidates and a treatment plan displayed on the screen

[0771] Prevention and health promotion

[0772] Data collection

[0773] Step 1:

[0774] The user opens a health app on their smartphone, for example, HealthKit or Google Fit.

[0775] Step 2:

[0776] Users input their daily diet, exercise, and sleep data. For example, they record their diet and exercise amount in the app by tapping or voice input.

[0777] Input: Daily diet, exercise, and sleep data

[0778] Output: A dataset of the input health data

[0779] Step 3:

[0780] The smartphone securely transmits collected data to the server, and it is assumed that data will be transmitted periodically using the automatic synchronization function.

[0781] Input: A dataset of input health data

[0782] Output: Securely transmitted health data

[0783] Data analysis

[0784] Step 4:

[0785] The server passes the received health data to an artificial intelligence algorithm for analysis. For example, the health data is input into an AI model.

[0786] Input: Health data dataset

[0787] Output: AI analysis request

[0788] Step 5:

[0789] The server analyzes the data and identifies health risks and areas for improvement. For example, AI models can identify nutrient deficiencies or lack of exercise.

[0790] Input: AI analysis request

[0791] Output: List of health risks and improvements

[0792] Step 6:

[0793] The server formats the generated health advice so that it can be sent to a smartphone, encrypts it, and sends it.

[0794] Input: List of health risks and improvements

[0795] Output: Encrypted health advice

[0796] Result notification

[0797] Step 7:

[0798] The smartphone notifies the user of the health advice received from the server. For example, a health message is displayed in the notification area of ​​the app.

[0799] Input: Encrypted health advice

[0800] Output: Notified health advice

[0801] Utilizing medical data

[0802] Data collection

[0803] Step 1:

[0804] Multiple hospitals provide medical records and treatment data to the server. For example, hospital information system personnel export the data and send it to the server using a secure file transfer protocol.

[0805] Input: Medical records and treatment data

[0806] Output: Transmitted medical data

[0807] Data analysis

[0808] Step 2:

[0809] The server stores the received data and accumulates it in a data warehouse.

[0810] Input: Transmitted medical data

[0811] Output: Stored medical data

[0812] Step 3:

[0813] The server inputs large amounts of medical data into an artificial intelligence algorithm for analysis, and the data is processed using distributed processing technology.

[0814] Input: Stored medical data

[0815] Output: AI analysis request

[0816] Step 4:

[0817] The server performs the analysis to identify treatment effects and trends. For example, data is analyzed in detail to identify the effects of new treatment A.

[0818] Input: AI analysis request

[0819] Output: Analysis results (treatment effects and trends)

[0820] Providing results

[0821] Step 5:

[0822] The server provides the analysis results to research institutions and pharmaceutical companies. The analysis results are stored in secure storage and provided in encrypted form.

[0823] Input: Analysis results (treatment effects and trends)

[0824] Output: Securely encrypted data provided

[0825] (Application example 1)

[0826] 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."

[0827] Currently, quality control is extremely important in the medical device manufacturing process, but conventional methods have issues such as delayed detection of defective products and the enormous effort and time required for overall product quality control. Furthermore, in medical settings, diagnoses and treatment plans must be made quickly and accurately, placing a heavy burden on medical professionals. Furthermore, to effectively utilize the large amounts of data collected in factories, real-time data analysis and quality control are required. To solve these issues, an advanced data analysis system utilizing AI technology and an efficient infrastructure to implement it are required.

[0828] 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.

[0829] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; data collection means for receiving manufacturing data acquired by machines used in a factory and performing quality evaluation; means including an artificial intelligence algorithm for analyzing the manufacturing data in real time and identifying potential defects and defective products; and means for displaying quality control information on the manufacturing line based on the analysis results. This enables the improvement of the accuracy of diagnoses and treatment plans in medical settings, as well as the efficiency of quality control on the manufacturing line in the factory and the reduction of defective products.

[0830] "Healthcare workers" is a general term for doctors, nurses, and other health care professionals who diagnose and treat patients in hospitals and clinics.

[0831] "Patient data" refers to information collected in medical settings, such as patient symptoms, vital signs, and medical records.

[0832] "Artificial intelligence algorithm" is a general term for computational methods and programs used to analyze large amounts of data and generate specific results.

[0833] "Candidate diagnoses" is a list of possible diagnostic results based on the input data.

[0834] A "treatment plan" refers to a set of proposed treatment methods or steps based on a particular diagnosis.

[0835] "Machinery used in factories" is a general term for all automated devices and machinery used in the manufacturing process.

[0836] "Manufacturing data" refers to process data and quality data acquired by machines in a factory.

[0837] "Data collection means" refers to a device or system for collecting patient data or manufacturing data.

[0838] "Quality evaluation" refers to the process of determining whether manufactured products meet standards.

[0839] "Real-time" refers to instantaneous processing and response, meaning there is little to no delay.

[0840] A "latent defect" refers to a problem or defect that is likely to be present in a product but has not yet become apparent.

[0841] "Defective Product" means a product that does not meet standards and is not suitable for use or sale.

[0842] "Quality control information" refers to information on the quality status of a product and defect detection, and management and improvements are carried out based on this information.

[0843] "Cloud server" is a general term for a remote server where data is stored and processed via the Internet.

[0844] "Improvement proposals" refer to methods and measures for improving products or processes proposed based on the analysis results.

[0845] "Pharmaceutical company" is a general term for companies that research, develop, manufacture, and sell new drugs.

[0846] "Research institute" is a general term for organizations that conduct research activities with the aim of developing new knowledge and technology.

[0847] This invention is a system that reduces the burden on medical professionals, improves the quality of medical care, and streamlines quality control in the manufacturing industry. This system utilizes AI technology in both medical and manufacturing settings to perform data analysis and realize diagnostic support and quality control.

[0848] Support for medical professionals

[0849] The server receives patient data entered by medical professionals and analyzes it using AI algorithms. For example, when a medical professional enters a patient's symptoms and vital signs into an electronic medical record, the server receives this information and uses an AI model to generate potential diagnoses, such as cold, flu, or COVID-19. This information is then sent to the medical professional's device to help with detailed examinations.

[0850] Factory quality control

[0851] The server receives manufacturing data acquired by machines used in the factory and collects the data for quality evaluation. For example, a camera attached to a factory device takes a picture of a medical device being manufactured and sends the image data to the server. The server then analyzes the image using an AI algorithm to identify potential defects or defective products. The analysis results are displayed on the production line and provided as quality control information.

[0852] Data collection and analysis for health promotion

[0853] When users enter their daily health data into their smartphone, the server receives it and uses AI algorithms to identify health risks and areas for improvement. For example, when a user enters their daily diet and exercise amount into the app, the server analyzes any nutrient deficiencies and areas for improvement in exercise, and sends appropriate advice to the smartphone.

[0854] Hardware and software used

[0855] The hardware used includes medical staff tablets and PCs, cameras on the production line, and users' smartphones, and the software used is Python, OpenCV, TensorFlow / Keras, and the Requests library.

[0856] Data processing and calculation

[0857] 1. Data collection: Collecting patient and manufacturing data from terminals and machines.

[0858] 2. Data Preprocessing: The image data undergoes preprocessing such as resizing, normalization, and reshaping.

[0859] 3. AI analysis: Analyze the data using pre-trained AI models to generate candidate diagnoses and quality assessments.

[0860] 4. Notification: The analysis results are sent to devices and production lines for use in medical and manufacturing settings.

[0861] Examples and prompts

[0862] For example, if a manufacturing line is making surgical tools, the robot will take a picture of the part with a camera and pass the image to an AI model for analysis, which will determine if the part is defective and, if necessary, send the data to a server.

[0863] Example prompt sentence:

[0864] Analyze images taken from a production line today and list the parts that are likely to be defective. Also, describe in detail which parts are problematic.

[0865] This system will improve the accuracy of diagnosis and treatment planning in medical settings, while also making quality control more efficient and reducing defective products on factory production lines.

[0866] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0867] Step 1:

[0868] Users input data using devices (medical staff's tablets or PCs, or cameras on the manufacturing line). The input data includes patient symptoms, vital signs, and images of medical equipment being manufactured. This prepares the data to be sent to the server.

[0869] Step 2:

[0870] The device sends the input data to the server. The server checks the format of the received data and performs preprocessing as necessary. For example, if the data is image data, it resizes or normalizes it, and if it is text data, it checks the format. This ensures data consistency and makes it suitable for analysis.

[0871] Step 3:

[0872] The server inputs the preprocessed data into an AI algorithm, which analyzes the data based on a pre-trained model and generates a diagnosis candidate, a treatment plan, or a quality assessment. For example, for image data sent from a manufacturing line, it scores the likelihood of a defective product. This generates a data analysis result.

[0873] Step 4:

[0874] The server checks the generated analysis results and performs additional analysis as necessary. The analysis results are also sent to the cloud server and used for further analysis and feedback. For example, new treatments or quality improvement measures may be proposed based on the analysis results. This improves the reliability and usefulness of the analysis results.

[0875] Step 5:

[0876] The server notifies the terminal of the generated analysis results and suggestions, which are then displayed on the terminal to medical professionals and production line workers. Specifically, medical professionals are shown potential diagnoses and treatment plans, while production line workers are shown a list of defective products and suggestions for quality improvement. This enables the data to be put to practical use.

[0877] Step 6:

[0878] Users (healthcare professionals and production line workers) can then take action based on the displayed analysis results and recommendations: healthcare professionals adjust diagnoses and treatment plans, and production line workers implement quality improvement measures, leading to continuous improvement of the entire system.

[0879] 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.

[0880] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[0881] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[0882] Support for medical professionals

[0883] Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[0884] Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[0885] Result presentation: The server sends the generated diagnosis candidates and treatment plans to the terminal, which displays them to the medical professional.

[0886] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[0887] Prevention and health promotion

[0888] Data collection: Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The smartphone then sends the collected data to a server.

[0889] Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[0890] Result notification: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[0891] Emotion recognition: The emotion engine recognizes emotions from smartphone input data and user behavior.

[0892] Emotion-based advice adjustment: Based on the emotions recognized by the emotion engine, the server adjusts health advice and improvement guidance.

[0893] Example: When a user enters their daily diet and exercise amount into the app, the server analyzes this and points out any missing nutrients or areas for improvement in exercise. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), it adjusts the advice more flexibly. For example, if the user is feeling stressed, it will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[0894] Utilizing medical data

[0895] Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[0896] Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[0897] Result provision: Based on the analysis results, the server generates feedback for new research concepts and new drug development and provides it to research institutions and pharmaceutical companies.

[0898] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[0899] The system with these functions will be able to provide flexible advice that takes into account the user's psychological state by incorporating an emotion engine, further improving the quality of medical care and health management. The system's flexible structure will allow it to adapt to different medical environments and user needs.

[0900] The processing flow will be explained below.

[0901] Support for medical professionals

[0902] Step 1:

[0903] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[0904] Step 2:

[0905] Terminal: Sends the entered patient data to the server.

[0906] Step 3:

[0907] Server: Stores the received patient data.

[0908] Step 4:

[0909] Server: Analyzes stored patient data using artificial intelligence algorithms.

[0910] Step 5:

[0911] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[0912] Step 6:

[0913] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[0914] Step 7:

[0915] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[0916] Prevention and health promotion

[0917] Step 1:

[0918] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[0919] Step 2:

[0920] Smartphone: Sends the entered health data to the server.

[0921] Step 3:

[0922] Server: Stores the received health data.

[0923] Step 4:

[0924] Server: Analyzes stored health data using artificial intelligence algorithms.

[0925] Step 5:

[0926] Server: Identifies health risks and areas for improvement based on the analysis results.

[0927] Step 6:

[0928] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[0929] Step 7:

[0930] Server: Sends the generated health advice and improvement guidance to a smartphone.

[0931] Step 8:

[0932] Smartphone: Provides health advice and guidance to users.

[0933] Step 9:

[0934] Emotion Engine: Recognizes emotions from user input data and their behavior.

[0935] Step 10:

[0936] Emotion Engine: Sends instructions to the server based on the recognized emotion.

[0937] Step 11:

[0938] Server: Receives instructions from the emotion engine and adjusts health advice and improvement guidance.

[0939] Step 12:

[0940] Server: Resends tailored advice and improvement guidance to the smartphone.

[0941] Step 13:

[0942] Smartphone: Notify users with tailored advice and guidance.

[0943] Utilizing medical data

[0944] Step 1:

[0945] Hospital: Provides medical records and treatment data to the server.

[0946] Step 2:

[0947] Server: Receives and stores the data provided.

[0948] Step 3:

[0949] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[0950] Step 4:

[0951] Server: Identify treatment effects and trends from analysis results.

[0952] Step 5:

[0953] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[0954] Step 6:

[0955] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[0956] Example 2

[0957] 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."

[0958] Conventional medical support systems were able to analyze medical and daily health data to provide potential diagnoses, treatment plans, and health advice. However, it was difficult to provide flexible advice and treatment plans that took the user's emotional state into account, which sometimes resulted in insufficient support for medical professionals and users. This created a challenge: improving the quality of medical care while simultaneously reducing the psychological burden on patients and users.

[0959] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0960] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion recognition engine for analyzing the emotional state of the user; and means for adjusting the candidate diagnoses and treatment plans based on the emotional state obtained by the emotion recognition engine. This enables the provision of flexible advice and appropriate treatment plans that take the user's emotional state into consideration.

[0961] "Medical professionals" refer to professionals who perform medical procedures such as medical examinations, treatment, and nursing for patients at medical institutions.

[0962] "Patient data" refers to all information necessary for medical examination and treatment, such as a patient's symptoms, vital signs, and medical records.

[0963] An "artificial intelligence algorithm" refers to a program that uses techniques such as machine learning and deep learning to analyze large amounts of data and generate conclusions and predictions based on specific purposes.

[0964] "Candidate diagnoses" refers to a list of likely diseases or conditions based on a patient's symptoms and data.

[0965] A "treatment plan" is a plan that includes details of the treatment to be administered to a patient, based on the results of a diagnosis.

[0966] "User" refers to medical professionals and general individuals who use the system, and who input health data and check diagnosis results.

[0967] "Health data" refers to all information related to an individual's health status, such as diet, exercise, sleep, and physical condition.

[0968] An "emotion recognition engine" refers to a program that analyzes and identifies a user's emotional state (e.g., stress, joy, sadness, etc.) from input data and user behavior.

[0969] "Health advice" refers to suggestions and guidance for maintaining and improving health that are provided to users based on health data and analysis results.

[0970] A "research institution" refers to an organization or group that develops new medical technologies and drugs, researches treatment methods, etc.

[0971] "Drug development companies" refer to companies that research, develop, manufacture, and sell new drugs.

[0972] "Medical record" means any record relating to the examination, treatment, and follow-up of a patient.

[0973] "Treatment data" refers to information about the effectiveness, results, and patient response of a particular treatment.

[0974] "Analysis results" refers to output information such as conclusions, predictions, and findings obtained as a result of data analysis by AI algorithms.

[0975] "Feedback" refers to advice and suggestions for new research concepts, treatments, and new drug development that are generated based on the analysis results.

[0976] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[0977] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[0978] Support for medical professionals

[0979] Data collection

[0980] On the terminal (healthcare worker's PC or tablet), healthcare workers input the patient's symptoms, vital signs, and medical records into the electronic medical record. Specific hardware used is a standard PC or tablet. The terminal sends the input data to a server. The software used is an electronic medical record system.

[0981] Data analysis

[0982] The server then analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used. During the analysis process, potential diagnoses are listed based on the patient's symptoms and vital signs.

[0983] Results presentation

[0984] The server sends the generated diagnosis candidates and treatment plans to a terminal, which then displays them to the medical staff via an electronic medical record system or medical information system.

[0985] Examples:

[0986] When a patient visits the hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses TensorFlow to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional then conducts a detailed examination based on this list.

[0987] Prevention and health promotion

[0988] Data collection

[0989] Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The hardware used is a smartphone, and the specific software used is a health management app. The smartphone then sends the collected data to a server.

[0990] Data analysis

[0991] The server then analyzes the received health data using AI algorithms to identify health risks and areas for improvement, using machine learning frameworks such as Keras.

[0992] Result notification

[0993] The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[0994] Emotion recognition

[0995] The emotion engine recognizes emotions from smartphone input data and user behavior. The software used is an emotion recognition algorithm.

[0996] Emotion-based advice adjustment

[0997] Based on the emotions recognized by the emotion engine, the server tailors health advice and improvement guidance.

[0998] Examples:

[0999] When a user enters their daily diet and exercise amount into a health management app, the server analyzes the data and identifies any nutrient deficiencies or areas for improvement. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), the advice is adjusted more flexibly. For example, if the user is feeling stressed, the server will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[1000] Utilizing medical data

[1001] Data collection

[1002] Hospitals provide medical records and treatment data to the server, which receives and stores the data.

[1003] Data analysis

[1004] The server uses AI algorithms to analyze the large amounts of medical data it receives and identify treatment effects and trends, using big data analysis tools such as Apache Spark and H2O.ai.

[1005] Providing results

[1006] Based on the analysis results, the server generates feedback for new research concepts and new drug development, and provides it to research institutions and drug development companies.

[1007] Examples:

[1008] Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If new treatments are found to be significantly effective against specific types of cancer, the server can provide this information to research institutions and drug development companies to promote further research and new drug development.

[1009] Example prompt for a generative AI model:

[1010] "Please suggest what health advice should be given to users who are experiencing stress."

[1011] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1012] Support for medical professionals

[1013] Step 1: User (healthcare professional) enters patient data

[1014] Users (healthcare professionals) input patients' symptoms, vital signs, and medical records into the electronic medical record system using devices such as PCs and tablets.

[1015] Input: Patient symptoms, vital signs, medical records

[1016] Output: Data entered into the electronic medical record system

[1017] Specific action: A healthcare professional types text or clicks an option on a PC or tablet.

[1018] Step 2: The device sends the data to the server

[1019] The terminal transmits the input data to the server via the network.

[1020] Input: Data entered into the electronic medical record system

[1021] Output: Patient data sent to the server

[1022] What it does: The device encrypts the data and sends it to the server using the HTTPS protocol.

[1023] Step 3: The server parses the data

[1024] The server analyzes the received patient data using AI algorithms, specifically software such as TensorFlow and PyTorch.

[1025] Input: Patient data sent to the server

[1026] Output: A list of diagnostic candidates and a treatment plan as the analysis results

[1027] Specific operation: The server cleanses the data, supplies it to the AI ​​model, and executes a Python script to generate analysis results.

[1028] Step 4: The server sends the results to the device

[1029] The server sends the generated diagnosis candidates and treatment plans to the terminal.

[1030] Input: A list of diagnostic candidates and a treatment plan as the analysis results

[1031] Output: Result data sent to the terminal

[1032] Specific operation: The server encrypts the analysis results and sends them to the device through a secure channel.

[1033] Step 5: The terminal displays the results

[1034] The device displays the received diagnostic candidates and treatment plans to medical professionals.

[1035] Input: Result data sent to the terminal

[1036] Output: Possible diagnoses and treatment plans displayed to healthcare professionals

[1037] Specific operation: The terminal displays data on the screen of an electronic medical record system, etc.

[1038] Prevention and health promotion

[1039] Step 1: User enters health data

[1040] Users enter their daily health data (diet, exercise, sleep, physical condition, etc.) into a health management app on their smartphone.

[1041] Input: Daily health data (diet, exercise, sleep, physical condition)

[1042] Output: Data entered into the health management app

[1043] Specific action: A user taps and swipes on a smartphone to enter data.

[1044] Step 2: The device sends the data to the server

[1045] The smartphone sends the entered health data to a server.

[1046] Input: Data entered into the health management app

[1047] Output: Health data sent to the server

[1048] Specific operation: The smartphone sends data to the server via Wi-Fi or mobile data communication.

[1049] Step 3: The server parses the data

[1050] The server analyzes the received health data using an AI algorithm, specifically the software Keras.

[1051] Input: Health data sent to the server

[1052] Output: Health risks and improvements as a result of the analysis

[1053] Specific operation: The server supplies data to the AI ​​model, which then calculates risks and areas for improvement.

[1054] Step 4: The server analyzes the emotional state

[1055] An emotion recognition engine recognizes the user's emotional state from the received data.

[1056] Input: Health data and related data

[1057] Output: Emotional state as a result of analysis

[1058] Specific operation: The server identifies the emotion using an emotion recognition algorithm.

[1059] Step 5: Servers adjust advice

[1060] The server adjusts health advice and improvement guidance based on the emotional state obtained from the emotion recognition engine.

[1061] Input: Emotion recognition results and health analysis results

[1062] Output: Tailored health advice and guidance

[1063] Specific behavior: The server generates advice and modifies the content according to the emotional state.

[1064] Step 6: The server sends the results to the device

[1065] The server then sends the generated health advice and improvement guidance to a smartphone.

[1066] Input: Tailored health advice and guidance

[1067] Output: Advice and guidance sent to your smartphone

[1068] Specific operation: The server encrypts the notification data and sends it to the smartphone.

[1069] Step 7: Your device will notify you of the results

[1070] The smartphone notifies the user of the advice and guidance received.

[1071] Input: Advice and guidance sent to your smartphone

[1072] Output: Advice and guidance to be given to the user

[1073] Specific action: The smartphone notifies the user via push notification or in-app message.

[1074] Utilizing medical data

[1075] Step 1: The hospital provides medical records and treatment data to the server

[1076] Multiple medical institutions provide medical records and treatment data to the server.

[1077] Input: medical records and treatment data

[1078] Output: Medical data stored on the server

[1079] Specific operation: The medical record system automatically transfers data to the server.

[1080] Step 2: The server parses the data

[1081] The server analyzes the received medical data using AI algorithms to identify treatment effects and trends, using software such as Apache Spark and H2O.ai.

[1082] Input: Medical data stored on the server

[1083] Output: Treatment effects and trend information as analysis results

[1084] Specific operation: The server supplies data to the AI ​​model and performs large-scale data analysis.

[1085] Step 3: Server generates feedback

[1086] The server generates feedback for new research concepts and new drug development based on the analysis results.

[1087] Input: Treatment effects and trend information as analysis results

[1088] Output: Feedback on research concepts and new drug development

[1089] Specific operation: The server formats the analysis results into a report format and generates the report.

[1090] Step 4: The server serves the results

[1091] The server provides the generated feedback to research institutions and drug development companies.

[1092] Input: Feedback on research concepts and new drug development

[1093] Output: Feedback provided to research institutions and drug development companies

[1094] What it does: The server encrypts the feedback and sends it to the relevant authority over a secure channel.

[1095] (Application example 2)

[1096] 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."

[1097] Current medical and health management systems do not adequately consider the psychological state of medical professionals and users, resulting in a lack of reduction in stress and emotional burden, and suboptimal treatment effectiveness and quality of health care. Furthermore, data analysis results are often significantly influenced by emotional states, making it difficult to provide appropriate diagnoses and treatment plans. Therefore, a system that can provide high-quality diagnoses, treatments, and health care recommendations while taking into account individual emotional states is needed.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1099] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion engine for recognizing the emotional state of the user; and means for adjusting the generated candidate diagnoses and treatment plans based on the emotion recognized by the emotion engine. This enables more flexible and appropriate diagnosis, treatment, and health management proposals that take the emotional state into consideration.

[1100] A "healthcare professional" is someone whose occupation regularly provides health care services to patients.

[1101] "Patient data" refers to data that includes medical information such as a patient's symptoms, vital signs, and medical records.

[1102] "Artificial intelligence algorithms" are algorithms for analyzing data and generating predictive models in computers.

[1103] "Candidate diagnoses" are multiple disease names and pathological conditions that are presumed based on patient data.

[1104] A "treatment plan" is a specific treatment method or protocol proposed for a diagnosed disease or condition.

[1105] A "user" is an individual who uses the system, and in this context refers primarily to a person receiving health care or medical services.

[1106] "Health data" refers to data that includes information about daily health conditions such as diet, exercise, sleep, and physical condition.

[1107] An "emotion engine" is a system that recognizes the user's emotional state and provides feedback and advice based on that information.

[1108] "Drug development" is the process of developing new medicines and is based on research.

[1109] "Health advice" refers to specific guidance and suggestions aimed at reducing health risks and improving lifestyle habits.

[1110] "Treatment data" refers to medical records and data related to treatment behavior at hospitals and healthcare institutions.

[1111] To implement this invention, a medical support system incorporating an emotion engine is required. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1112] Support for medical professionals

[1113] Data collection

[1114] The terminal (a personal computer or tablet used by a healthcare professional) acts as a device where the healthcare professional inputs the patient's symptoms, vital signs, and medical records. This information is sent from the terminal to a server. The software used is an electronic medical record system, such as Epic or Cerner.

[1115] Data analysis

[1116] The server analyzes the received patient data using artificial intelligence algorithms (e.g., TensorFlow or PyTorch) to generate potential diagnoses and treatment plans. The emotion engine plays a part in this process, adjusting the diagnosis and treatment plan based on the patient's psychological state.

[1117] Results presentation

[1118] The server then sends the generated diagnosis candidates and treatment plans to a terminal, which displays them to the medical professional. For example, if a patient visits the hospital complaining of fever, cough, and fatigue, the medical professional enters these symptoms and the patient's vital signs into the electronic medical record and sends the data to the server. The server uses AI to list the most likely diagnoses, such as cold, flu, and COVID-19, and provides a treatment plan.

[1119] Prevention and health promotion

[1120] Data collection

[1121] Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The smartphone then sends the collected data to a server. Examples of such applications include Apple Health and Google Fit.

[1122] Data analysis

[1123] The server uses AI algorithms to analyze the received health data and identify health risks and areas for improvement. An emotion engine recognizes emotions from smartphone input data and user behavior. Software such as Emotion API and DeepFace is utilized.

[1124] Result notification

[1125] The server sends the generated health advice and guidance for improvement to the smartphone, which then notifies the user. The emotion engine flexibly adjusts the advice based on the user's emotional state. For example, if a user enters their daily diet and exercise amount into the app, the server will point out any nutrient deficiencies and areas for improvement in exercise, and if the user is feeling stressed, the server will notify them by saying, "Start with a short exercise session" or "We recommend a relaxing meal."

[1126] Example prompt sentence:

[1127] "How are you feeling today? For example, if you're feeling stressed, please enter that."

[1128] "We'll suggest the best menu for you based on your food preferences and mood. Just tell us your recent diet history."

[1129] Utilizing medical data

[1130] Data collection

[1131] Multiple healthcare institutions provide medical records and treatment data to the server, which is collected using a comprehensive electronic medical record system.

[1132] Data analysis

[1133] The server analyzes large amounts of medical data using AI algorithms to identify treatment effects and trends, and an emotion engine further analyzes the data based on the patient's psychological trends.

[1134] Providing results

[1135] Based on the analysis results, feedback for new research concepts and new drug development is generated and provided to research institutions and pharmaceutical companies. This will promote the discovery of new treatments and the development of new drugs. As a specific example, if cancer treatment data is collected from hospitals across the country and AI analyzes it, and it is found that new treatment A is showing significant effectiveness against a specific type of cancer, this information can be provided to research institutions and pharmaceutical companies to enable further research and new drug development.

[1136] This system will enable medical care and health management that takes emotional states into account, improving the quality of medical care and user satisfaction.

[1137] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1138] Step 1:

[1139] The device collects patient data (symptoms, vital signs, medical records) entered by medical professionals and sends the data to a server. The input data includes information such as fever, cough, and fatigue. This data is collected and sent using an electronic medical record system (e.g., Epic, Cerner).

[1140] Step 2:

[1141] The server analyzes the patient data it receives using an artificial intelligence algorithm (e.g., TensorFlow or PyTorch). Specifically, it preprocesses the data and generates appropriate diagnostic candidates (e.g., cold, flu, COVID-19, etc.). At this time, the AI ​​model lists the diagnostic candidates in descending order based on the input data (patient symptoms).

[1142] Step 3:

[1143] The generated diagnosis candidates and treatment plans are sent to a terminal, which displays them to medical professionals. Specifically, a list of diagnosis candidates and a treatment plan based on them are displayed on the screen, and medical professionals can evaluate and make decisions.

[1144] Step 4:

[1145] The emotion engine uses the smartphone's camera and voice input functions to recognize the user's emotional state. It uses image and voice data to analyze the user's emotions (e.g., tiredness, stress, optimism, etc.). This process utilizes the Emotion API and DeepFace.

[1146] Step 5:

[1147] The server takes the user's emotional state into account to adjust potential diagnoses and treatment plans. Specifically, it modifies the usual diagnosis and treatment plan based on the user's emotional state. For example, if stress is causing symptoms to worsen, the server generates a treatment plan that also addresses that.

[1148] Step 6:

[1149] Users enter their daily health data (food, exercise, sleep, physical condition) into a smartphone app, and this data is sent to a server via applications such as Apple Health and Google Fit.

[1150] Step 7:

[1151] The server analyzes the received health data and uses an artificial intelligence algorithm to identify health risks and areas for improvement. As a result of the analysis, it identifies areas for improvement such as nutrient deficiencies and exercise. Specific health advice is generated based on this data.

[1152] Step 8:

[1153] The emotion engine analyzes the user's emotional state and adjusts health advice and guidance accordingly. For example, a user feeling stressed may be given flexible advice such as "Start with a short workout" or "Recommend a relaxing diet."

[1154] Step 9:

[1155] The server then sends the generated health advice and guidance to the smartphone, which then notifies the user of the advice. Specifically, the information is displayed to the user via a pop-up notification or push notification.

[1156] Step 10:

[1157] Multiple healthcare institutions provide medical records and treatment data to the server, which is collected using a comprehensive electronic medical record system.

[1158] Step 11:

[1159] The server analyzes large amounts of medical data using AI algorithms to identify treatment effects and trends, and an emotion engine analyzes the data while taking into account the patient's psychological trends.

[1160] Step 12:

[1161] Based on the analysis results, feedback for new research concepts and new drug development will be generated and provided to research institutions and pharmaceutical companies, thereby accelerating the discovery of new treatments and the development of new drugs.

[1162] This provides a concrete explanation of the processing steps of the entire system, clarifying the data processing and calculations performed at each step, as well as the output based on these.

[1163] 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.

[1164] 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.

[1165] 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.

[1166] [Third embodiment]

[1167] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1168] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1169] 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).

[1170] 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.

[1171] 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.

[1172] 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).

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] 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.

[1178] 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."

[1179] The present invention provides a system that aims to reduce the burden on medical professionals, improve the quality of medical care, increase patient satisfaction, and effectively utilize medical data. This system is embodied in the following specific form.

[1180] The system consists of three main components: the server, the terminal, and the user.

[1181] Support for medical professionals

[1182] 1. Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[1183] 2. Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[1184] 3. Presentation of results: The server sends the generated diagnostic candidates and treatment plans to the terminal, which displays them to the medical professional.

[1185] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[1186] Prevention and health promotion

[1187] 1. Data collection: Users enter their daily health data, such as diet, exercise, sleep, and physical condition, into a smartphone app. The smartphone then sends the collected data to a server.

[1188] 2. Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[1189] 3. Notification of results: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[1190] Example: When a user enters their daily diet and exercise amount into an app, the server analyzes the information and identifies any nutrient deficiencies and areas for improvement in exercise. The app then notifies the user with messages such as "Eat more vegetables" or "We recommend walking 30 minutes every day."

[1191] Utilizing medical data

[1192] 1. Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[1193] 2. Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[1194] 3. Providing results: The server generates feedback for new research concepts and new drug development based on the analysis results and provides them to research institutions and pharmaceutical companies.

[1195] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[1196] A system with these functions will be able to comprehensively solve Japan's health issues through supporting medical professionals, prevention and health promotion, and effective use of medical data. In addition, the system's flexible structure allows it to adapt to different medical environments and user needs.

[1197] The processing flow will be explained below.

[1198] Support for medical professionals

[1199] Step 1:

[1200] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[1201] Step 2:

[1202] Terminal: Sends the entered patient data to the server.

[1203] Step 3:

[1204] Server: Stores the received patient data.

[1205] Step 4:

[1206] Server: Analyzes stored patient data using artificial intelligence algorithms.

[1207] Step 5:

[1208] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[1209] Step 6:

[1210] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[1211] Step 7:

[1212] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[1213] Prevention and health promotion

[1214] Step 1:

[1215] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[1216] Step 2:

[1217] Smartphone: Sends the entered health data to the server.

[1218] Step 3:

[1219] Server: Stores the received health data.

[1220] Step 4:

[1221] Server: Analyzes stored health data using artificial intelligence algorithms.

[1222] Step 5:

[1223] Server: Identifies health risks and areas for improvement based on the analysis results.

[1224] Step 6:

[1225] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[1226] Step 7:

[1227] Server: Sends the generated health advice and improvement guidance to a smartphone.

[1228] Step 8:

[1229] Smartphone: Provides health advice and guidance to users.

[1230] Utilizing medical data

[1231] Step 1:

[1232] Hospital: Provides medical records and treatment data to the server.

[1233] Step 2:

[1234] Server: Receives and stores the data provided.

[1235] Step 3:

[1236] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[1237] Step 4:

[1238] Server: Identify treatment effects and trends from analysis results.

[1239] Step 5:

[1240] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[1241] Step 6:

[1242] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[1243] Example 1

[1244] 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."

[1245] In the medical field, medical professionals are required to efficiently collect patient data and quickly provide diagnoses and treatment plans based on that data. It is also important to accurately collect and analyze health data from patients' daily lives and provide appropriate health advice. Furthermore, there is a need to effectively analyze medical records and treatment data collected from multiple hospitals and use the data for new research and the development of new treatments. To solve these challenges, a system is needed to efficiently and safely perform each process of data collection, analysis, and provision.

[1246] 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.

[1247] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including a terminal for transmitting the patient data to the server using a secure communication protocol; and means for encrypting and transmitting the candidate diagnoses and treatment plans from the server to the terminal, thereby enabling medical professionals to quickly and safely collect and analyze patient data and provide appropriate diagnoses and treatment plans.

[1248] In this invention, the server includes means for receiving daily health data entered by the user, means including an artificial intelligence algorithm for analyzing the health data and identifying health risks and areas for improvement, means for notifying the user of the generated health advice and improvement guidance, means for transmitting the user's input data from a smartphone app to the server, and means for notifying the smartphone of the analysis results, thereby enabling the user to easily collect and analyze health data from their daily lives and receive appropriate health advice.

[1249] Furthermore, in this invention, the server includes: means for receiving medical records and treatment data from multiple hospitals; means including an artificial intelligence algorithm for analyzing the received data and identifying treatment effects and trends; means for generating feedback for new research concepts and new drug development based on the analysis results and providing the feedback to research institutions and pharmaceutical companies; means for analyzing the data using distributed processing technology; and means for storing the analysis results in secure storage, encrypting them, and providing them. This enables effective analysis of medical data and makes it possible to use the data for new research and development of new treatments.

[1250] "Healthcare professionals" is a general term for people who work in medical institutions such as hospitals and clinics, examining, treating, and caring for patients.

[1251] "Patient Data" means any data related to a patient's diagnosis or treatment, including symptoms, vital signs, and medical records.

[1252] "Means of receiving" refers to the function of inputting data into a specific device or system using a communication protocol or network.

[1253] "Analysis" is the process of analyzing collected data using technologies such as artificial intelligence algorithms to identify potential diagnoses, treatment plans, and areas for improvement.

[1254] "Candidate diagnoses" are a list of possible diagnoses identified by an artificial intelligence algorithm based on patient data.

[1255] A "treatment plan" is a detailed treatment policy and specific treatment method formulated based on the diagnostic results.

[1256] An "artificial intelligence algorithm" is a computer program that uses techniques such as machine learning and deep learning to analyze data and make inferences.

[1257] "Presentation means" refers to the function of visually showing the analysis results, diagnostic candidates, and treatment plans to the user via a display device or terminal.

[1258] A "communications protocol" is a set of rules and procedures for data communication, and is a set of regulations for standardizing and safely transmitting and receiving data.

[1259] A "terminal" is an electronic device for inputting and displaying data, and refers to PCs, tablets, and smartphones used by medical professionals and users.

[1260] "Encryption" is the process of transforming original information into another form using a specific algorithm in order to protect the data.

[1261] A "smartphone app" is a software application that runs on a smartphone and provides health data input and notification functions.

[1262] "Distributed processing technology" is a technology that uses multiple computer resources to analyze and process data simultaneously and in parallel.

[1263] "Secure storage" refers to a data storage system in which data is stored securely and has data access control and encryption functions.

[1264] This system aims to enable medical professionals to efficiently collect and analyze patient data and provide appropriate diagnoses and treatment plans. It also aims to analyze health data from users' daily lives and provide appropriate health advice, as well as analyze medical records and treatment data collected from multiple hospitals to aid in new research and the development of new treatments. This system consists of three main components: a server, a terminal, and a user.

[1265] Hardware and Software

[1266] server

[1267] The server plays a central role in receiving, analyzing, and storing data. The software used includes artificial intelligence algorithms for analysis (e.g., TensorFlow and PyTorch). HTTPS and TLS protocols are used to securely receive and transmit data. Apache Spark is used for distributed data processing.

[1268] Terminal

[1269] A device is a device where a healthcare professional or user enters data, and can be a PC, tablet, or smartphone. The device runs an electronic medical record system (e.g., Epic or Cerner) or a health app (e.g., HealthKit or Google Fit). Secure communication protocols are used to transmit data from the device.

[1270] User

[1271] Users are responsible for inputting and collecting health data in their daily lives. The collected data is sent to a server via a smartphone app, and notifications are received from the server.

[1272] Data collection and analysis

[1273] Support for medical professionals

[1274] 1. Data Collection:

[1275] The device allows medical professionals to input a patient's symptoms, vital signs, and medical records into an electronic medical record. For example, a doctor inputs and saves a patient's temperature and blood pressure, and the data is then sent to a server.

[1276] The terminal transmits the input data to the server using a secure protocol.

[1277] 2. Data Analysis:

[1278] The server analyzes the received patient data using AI algorithms, and for example, the server lists possible diagnoses such as cold, flu, or COVID-19.

[1279] The server generates the analysis results and sends them to the terminal.

[1280] 3. Results presentation:

[1281] The device then displays the received diagnostic candidates and treatment plans to the medical professional, who can then review the diagnosis results and modify the treatment plan as necessary.

[1282] Prevention and health promotion

[1283] 1. Data Collection:

[1284] Users input their daily diet, exercise, and sleep data into a health app on their smartphone. For example, when a user inputs and saves their dietary information, it is automatically sent to the server.

[1285] The smartphone periodically synchronizes data with the server.

[1286] 2. Data Analysis:

[1287] The server then analyzes the received health data using AI algorithms, identifying, for example, nutritional deficiencies and areas for improvement in exercise habits.

[1288] The server generates health advice based on the analysis results and sends it to the smartphone.

[1289] 3. Result notification:

[1290] The smartphone will then notify the user of the health advice it has received, such as messages like "Eat more vegetables" or "We recommend walking 30 minutes a day."

[1291] Utilizing medical data

[1292] 1. Data Collection:

[1293] Multiple hospitals provide medical records and treatment data to the server, for example by exporting the data weekly and sending it to the server in a secure manner.

[1294] The server stores the received data and accumulates it in a data warehouse.

[1295] 2. Data Analysis:

[1296] The server then uses AI algorithms to analyze the large amounts of medical data it receives, for example by analyzing the data in detail to identify the effectiveness of new treatments.

[1297] The server identifies the analysis results as new research concepts and treatments and generates feedback.

[1298] 3. Results provided:

[1299] The server provides the analysis results to research institutions and pharmaceutical companies. The results are stored in secure storage and provided in encrypted form.

[1300] Examples of concrete examples and prompts

[1301] Specific examples include cases where a doctor enters data on a patient complaining of fever, cough, or fatigue into an electronic medical record, which is then analyzed by a server to suggest possible diagnoses, or where a user enters information about their diet and exercise into a health app, which then analyzes the information and provides health advice. Another example is the analysis of treatment data from hospitals across the country to help with new drug development.

[1302] Example prompt sentence:

[1303] 1. "Doctors enter fever, cough, and fatigue into patients' electronic medical records, and the server analyzes this data using AI to generate potential diagnoses."

[1304] 2. "Users enter their dietary information and exercise amount into the app, and the server analyzes that data using AI to generate health advice."

[1305] 3. "Please explain the process by which a server uses AI to analyze cancer treatment data provided by hospitals across the country, identify the effectiveness of new treatments, and provide the results to research institutions."

[1306] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1307] Support for medical professionals

[1308] Data collection

[1309] Step 1:

[1310] A medical professional opens the electronic medical record system using a terminal (PC or tablet). For example, a doctor operates the electronic medical record software on the hospital's local server and logs in.

[1311] Step 2:

[1312] Medical staff enter data such as patient information, symptoms, and vital signs, such as the patient's temperature, blood pressure, and symptoms (fever, cough, fatigue) using a keyboard or touchscreen.

[1313] Input: Patient's vital signs and symptoms, including temperature and blood pressure

[1314] Output: Dataset of input patient information

[1315] Step 3:

[1316] The terminal sends the entered data to the server using a secure communication protocol (HTTPS or TLS). For example, when a doctor clicks the "Save" button, the electronic medical record system encrypts the data and sends it to the server in real time.

[1317] Input: Dataset of entered patient information

[1318] Output: Securely transmitted patient information

[1319] Data analysis

[1320] Step 4:

[1321] The server then passes the received patient data to an artificial intelligence algorithm for analysis. For example, a patient's symptom data is fed into an AI model running on TensorFlow or PyTorch.

[1322] Input: Dataset of patient information

[1323] Output: Analysis request by AI algorithm

[1324] Step 5:

[1325] The server analyzes the data and matches symptoms with potential diagnoses. For example, an AI model could analyze a patient's symptom data and come up with a list of possibilities, such as cold, flu, or COVID-19.

[1326] Input: Analysis request by AI algorithm

[1327] Output: Diagnosis candidate list

[1328] Step 6:

[1329] The server formats the generated diagnostic candidates and treatment plans for the electronic medical record system, encrypts them, and transmits them to the terminal.

[1330] Input: Diagnosis candidate list

[1331] Output: Encrypted diagnosis candidate list and treatment plan

[1332] Results presentation

[1333] Step 7:

[1334] The terminal receives the diagnosis candidates and treatment plans from the server and presents them to the medical staff. For example, a list of diagnosis candidates is displayed on the electronic medical record screen.

[1335] Input: Encrypted diagnostic candidate list and treatment plan

[1336] Output: A list of diagnostic candidates and a treatment plan displayed on the screen

[1337] Prevention and health promotion

[1338] Data collection

[1339] Step 1:

[1340] The user opens a health app on their smartphone, for example, HealthKit or Google Fit.

[1341] Step 2:

[1342] Users input their daily diet, exercise, and sleep data. For example, they record their diet and exercise amount in the app by tapping or voice input.

[1343] Input: Daily diet, exercise, and sleep data

[1344] Output: A dataset of the input health data

[1345] Step 3:

[1346] The smartphone securely transmits collected data to the server, and it is assumed that data will be transmitted periodically using the automatic synchronization function.

[1347] Input: A dataset of input health data

[1348] Output: Securely transmitted health data

[1349] Data analysis

[1350] Step 4:

[1351] The server passes the received health data to an artificial intelligence algorithm for analysis. For example, the health data is input into an AI model.

[1352] Input: Health data dataset

[1353] Output: AI analysis request

[1354] Step 5:

[1355] The server analyzes the data and identifies health risks and areas for improvement. For example, AI models can identify nutrient deficiencies or lack of exercise.

[1356] Input: AI analysis request

[1357] Output: List of health risks and improvements

[1358] Step 6:

[1359] The server formats the generated health advice so that it can be sent to a smartphone, encrypts it, and sends it.

[1360] Input: List of health risks and improvements

[1361] Output: Encrypted health advice

[1362] Result notification

[1363] Step 7:

[1364] The smartphone notifies the user of the health advice received from the server. For example, a health message is displayed in the notification area of ​​the app.

[1365] Input: Encrypted health advice

[1366] Output: Notified health advice

[1367] Utilizing medical data

[1368] Data collection

[1369] Step 1:

[1370] Multiple hospitals provide medical records and treatment data to the server. For example, hospital information system personnel export the data and send it to the server using a secure file transfer protocol.

[1371] Input: Medical records and treatment data

[1372] Output: Transmitted medical data

[1373] Data analysis

[1374] Step 2:

[1375] The server stores the received data and accumulates it in a data warehouse.

[1376] Input: Transmitted medical data

[1377] Output: Stored medical data

[1378] Step 3:

[1379] The server inputs large amounts of medical data into an artificial intelligence algorithm for analysis, and the data is processed using distributed processing technology.

[1380] Input: Stored medical data

[1381] Output: AI analysis request

[1382] Step 4:

[1383] The server performs the analysis to identify treatment effects and trends. For example, data is analyzed in detail to identify the effects of new treatment A.

[1384] Input: AI analysis request

[1385] Output: Analysis results (treatment effects and trends)

[1386] Providing results

[1387] Step 5:

[1388] The server provides the analysis results to research institutions and pharmaceutical companies. The analysis results are stored in secure storage and provided in encrypted form.

[1389] Input: Analysis results (treatment effects and trends)

[1390] Output: Securely encrypted data provided

[1391] (Application example 1)

[1392] 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."

[1393] Currently, quality control is extremely important in the medical device manufacturing process, but conventional methods have issues such as delayed detection of defective products and the enormous effort and time required for overall product quality control. Furthermore, in medical settings, diagnoses and treatment plans must be made quickly and accurately, placing a heavy burden on medical professionals. Furthermore, to effectively utilize the large amounts of data collected in factories, real-time data analysis and quality control are required. To solve these issues, an advanced data analysis system utilizing AI technology and an efficient infrastructure to implement it are required.

[1394] 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.

[1395] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; data collection means for receiving manufacturing data acquired by machines used in a factory and performing quality evaluation; means including an artificial intelligence algorithm for analyzing the manufacturing data in real time and identifying potential defects and defective products; and means for displaying quality control information on the manufacturing line based on the analysis results. This enables the improvement of the accuracy of diagnoses and treatment plans in medical settings, as well as the efficiency of quality control on the manufacturing line in the factory and the reduction of defective products.

[1396] "Healthcare workers" is a general term for doctors, nurses, and other health care professionals who diagnose and treat patients in hospitals and clinics.

[1397] "Patient data" refers to information collected in medical settings, such as patient symptoms, vital signs, and medical records.

[1398] "Artificial intelligence algorithm" is a general term for computational methods and programs used to analyze large amounts of data and generate specific results.

[1399] "Candidate diagnoses" is a list of possible diagnostic results based on the input data.

[1400] A "treatment plan" refers to a set of proposed treatment methods or steps based on a particular diagnosis.

[1401] "Machinery used in factories" is a general term for all automated devices and machinery used in the manufacturing process.

[1402] "Manufacturing data" refers to process data and quality data acquired by machines in a factory.

[1403] "Data collection means" refers to a device or system for collecting patient data or manufacturing data.

[1404] "Quality evaluation" refers to the process of determining whether manufactured products meet standards.

[1405] "Real-time" refers to instantaneous processing and response, meaning there is little to no delay.

[1406] A "latent defect" refers to a problem or defect that is likely to be present in a product but has not yet become apparent.

[1407] "Defective Product" means a product that does not meet standards and is not suitable for use or sale.

[1408] "Quality control information" refers to information on the quality status of a product and defect detection, and management and improvements are carried out based on this information.

[1409] "Cloud server" is a general term for a remote server where data is stored and processed via the Internet.

[1410] "Improvement proposals" refer to methods and measures for improving products or processes proposed based on the analysis results.

[1411] "Pharmaceutical company" is a general term for companies that research, develop, manufacture, and sell new drugs.

[1412] "Research institute" is a general term for organizations that conduct research activities with the aim of developing new knowledge and technology.

[1413] This invention is a system that reduces the burden on medical professionals, improves the quality of medical care, and streamlines quality control in the manufacturing industry. This system utilizes AI technology in both medical and manufacturing settings to perform data analysis and realize diagnostic support and quality control.

[1414] Support for medical professionals

[1415] The server receives patient data entered by medical professionals and analyzes it using AI algorithms. For example, when a medical professional enters a patient's symptoms and vital signs into an electronic medical record, the server receives this information and uses an AI model to generate potential diagnoses, such as cold, flu, or COVID-19. This information is then sent to the medical professional's device to help with detailed examinations.

[1416] Factory quality control

[1417] The server receives manufacturing data acquired by machines used in the factory and collects the data for quality evaluation. For example, a camera attached to a factory device takes a picture of a medical device being manufactured and sends the image data to the server. The server then analyzes the image using an AI algorithm to identify potential defects or defective products. The analysis results are displayed on the production line and provided as quality control information.

[1418] Data collection and analysis for health promotion

[1419] When users enter their daily health data into their smartphone, the server receives it and uses AI algorithms to identify health risks and areas for improvement. For example, when a user enters their daily diet and exercise amount into the app, the server analyzes any nutrient deficiencies and areas for improvement in exercise, and sends appropriate advice to the smartphone.

[1420] Hardware and software used

[1421] The hardware used includes medical staff tablets and PCs, cameras on the production line, and users' smartphones, and the software used is Python, OpenCV, TensorFlow / Keras, and the Requests library.

[1422] Data processing and calculation

[1423] 1. Data collection: Collecting patient and manufacturing data from terminals and machines.

[1424] 2. Data Preprocessing: The image data undergoes preprocessing such as resizing, normalization, and reshaping.

[1425] 3. AI analysis: Analyze the data using pre-trained AI models to generate candidate diagnoses and quality assessments.

[1426] 4. Notification: The analysis results are sent to devices and production lines for use in medical and manufacturing settings.

[1427] Examples and prompts

[1428] For example, if a manufacturing line is making surgical tools, the robot will take a picture of the part with a camera and pass the image to an AI model for analysis, which will determine if the part is defective and, if necessary, send the data to a server.

[1429] Example prompt sentence:

[1430] Analyze images taken from a production line today and list the parts that are likely to be defective. Also, describe in detail which parts are problematic.

[1431] This system will improve the accuracy of diagnosis and treatment planning in medical settings, while also making quality control more efficient and reducing defective products on factory production lines.

[1432] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1433] Step 1:

[1434] Users input data using devices (medical staff's tablets or PCs, or cameras on the manufacturing line). The input data includes patient symptoms, vital signs, and images of medical equipment being manufactured. This prepares the data to be sent to the server.

[1435] Step 2:

[1436] The device sends the input data to the server. The server checks the format of the received data and performs preprocessing as necessary. For example, if the data is image data, it resizes or normalizes it, and if it is text data, it checks the format. This ensures data consistency and makes it suitable for analysis.

[1437] Step 3:

[1438] The server inputs the preprocessed data into an AI algorithm, which analyzes the data based on a pre-trained model and generates a diagnosis candidate, a treatment plan, or a quality assessment. For example, for image data sent from a manufacturing line, it scores the likelihood of a defective product. This generates a data analysis result.

[1439] Step 4:

[1440] The server checks the generated analysis results and performs additional analysis as necessary. The analysis results are also sent to the cloud server and used for further analysis and feedback. For example, new treatments or quality improvement measures may be proposed based on the analysis results. This improves the reliability and usefulness of the analysis results.

[1441] Step 5:

[1442] The server notifies the terminal of the generated analysis results and suggestions, which are then displayed on the terminal to medical professionals and production line workers. Specifically, medical professionals are shown potential diagnoses and treatment plans, while production line workers are shown a list of defective products and suggestions for quality improvement. This enables the data to be put to practical use.

[1443] Step 6:

[1444] Users (healthcare professionals and production line workers) can then take action based on the displayed analysis results and recommendations: healthcare professionals adjust diagnoses and treatment plans, and production line workers implement quality improvement measures, leading to continuous improvement of the entire system.

[1445] 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.

[1446] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[1447] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[1448] Support for medical professionals

[1449] Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[1450] Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[1451] Result presentation: The server sends the generated diagnosis candidates and treatment plans to the terminal, which displays them to the medical professional.

[1452] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[1453] Prevention and health promotion

[1454] Data collection: Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The smartphone then sends the collected data to a server.

[1455] Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[1456] Result notification: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[1457] Emotion recognition: The emotion engine recognizes emotions from smartphone input data and user behavior.

[1458] Emotion-based advice adjustment: Based on the emotions recognized by the emotion engine, the server adjusts health advice and improvement guidance.

[1459] Example: When a user enters their daily diet and exercise amount into the app, the server analyzes this and points out any missing nutrients or areas for improvement in exercise. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), it adjusts the advice more flexibly. For example, if the user is feeling stressed, it will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[1460] Utilizing medical data

[1461] Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[1462] Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[1463] Result provision: Based on the analysis results, the server generates feedback for new research concepts and new drug development and provides it to research institutions and pharmaceutical companies.

[1464] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[1465] The system with these functions will be able to provide flexible advice that takes into account the user's psychological state by incorporating an emotion engine, further improving the quality of medical care and health management. The system's flexible structure will allow it to adapt to different medical environments and user needs.

[1466] The processing flow will be explained below.

[1467] Support for medical professionals

[1468] Step 1:

[1469] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[1470] Step 2:

[1471] Terminal: Sends the entered patient data to the server.

[1472] Step 3:

[1473] Server: Stores the received patient data.

[1474] Step 4:

[1475] Server: Analyzes stored patient data using artificial intelligence algorithms.

[1476] Step 5:

[1477] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[1478] Step 6:

[1479] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[1480] Step 7:

[1481] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[1482] Prevention and health promotion

[1483] Step 1:

[1484] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[1485] Step 2:

[1486] Smartphone: Sends the entered health data to the server.

[1487] Step 3:

[1488] Server: Stores the received health data.

[1489] Step 4:

[1490] Server: Analyzes stored health data using artificial intelligence algorithms.

[1491] Step 5:

[1492] Server: Identifies health risks and areas for improvement based on the analysis results.

[1493] Step 6:

[1494] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[1495] Step 7:

[1496] Server: Sends the generated health advice and improvement guidance to a smartphone.

[1497] Step 8:

[1498] Smartphone: Provides health advice and guidance to users.

[1499] Step 9:

[1500] Emotion Engine: Recognizes emotions from user input data and their behavior.

[1501] Step 10:

[1502] Emotion Engine: Sends instructions to the server based on the recognized emotion.

[1503] Step 11:

[1504] Server: Receives instructions from the emotion engine and adjusts health advice and improvement guidance.

[1505] Step 12:

[1506] Server: Resends tailored advice and improvement guidance to the smartphone.

[1507] Step 13:

[1508] Smartphone: Notify users with tailored advice and guidance.

[1509] Utilizing medical data

[1510] Step 1:

[1511] Hospital: Provides medical records and treatment data to the server.

[1512] Step 2:

[1513] Server: Receives and stores the data provided.

[1514] Step 3:

[1515] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[1516] Step 4:

[1517] Server: Identify treatment effects and trends from analysis results.

[1518] Step 5:

[1519] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[1520] Step 6:

[1521] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[1522] Example 2

[1523] 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."

[1524] Conventional medical support systems were able to analyze medical and daily health data to provide potential diagnoses, treatment plans, and health advice. However, it was difficult to provide flexible advice and treatment plans that took the user's emotional state into account, which sometimes resulted in insufficient support for medical professionals and users. This created a challenge: improving the quality of medical care while simultaneously reducing the psychological burden on patients and users.

[1525] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1526] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion recognition engine for analyzing the emotional state of the user; and means for adjusting the candidate diagnoses and treatment plans based on the emotional state obtained by the emotion recognition engine. This enables the provision of flexible advice and appropriate treatment plans that take the user's emotional state into consideration.

[1527] "Medical professionals" refer to professionals who perform medical procedures such as medical examinations, treatment, and nursing for patients at medical institutions.

[1528] "Patient data" refers to all information necessary for medical examination and treatment, such as a patient's symptoms, vital signs, and medical records.

[1529] An "artificial intelligence algorithm" refers to a program that uses techniques such as machine learning and deep learning to analyze large amounts of data and generate conclusions and predictions based on specific purposes.

[1530] "Candidate diagnoses" refers to a list of likely diseases or conditions based on a patient's symptoms and data.

[1531] A "treatment plan" is a plan that includes details of the treatment to be administered to a patient, based on the results of a diagnosis.

[1532] "User" refers to medical professionals and general individuals who use the system, and who input health data and check diagnosis results.

[1533] "Health data" refers to all information related to an individual's health status, such as diet, exercise, sleep, and physical condition.

[1534] An "emotion recognition engine" refers to a program that analyzes and identifies a user's emotional state (e.g., stress, joy, sadness, etc.) from input data and user behavior.

[1535] "Health advice" refers to suggestions and guidance for maintaining and improving health that are provided to users based on health data and analysis results.

[1536] A "research institution" refers to an organization or group that develops new medical technologies and drugs, researches treatment methods, etc.

[1537] "Drug development companies" refer to companies that research, develop, manufacture, and sell new drugs.

[1538] "Medical record" means any record relating to the examination, treatment, and follow-up of a patient.

[1539] "Treatment data" refers to information about the effectiveness, results, and patient response of a particular treatment.

[1540] "Analysis results" refers to output information such as conclusions, predictions, and findings obtained as a result of data analysis by AI algorithms.

[1541] "Feedback" refers to advice and suggestions for new research concepts, treatments, and new drug development that are generated based on the analysis results.

[1542] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[1543] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[1544] Support for medical professionals

[1545] Data collection

[1546] On the terminal (healthcare worker's PC or tablet), healthcare workers input the patient's symptoms, vital signs, and medical records into the electronic medical record. Specific hardware used is a standard PC or tablet. The terminal sends the input data to a server. The software used is an electronic medical record system.

[1547] Data analysis

[1548] The server then analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used. During the analysis process, potential diagnoses are listed based on the patient's symptoms and vital signs.

[1549] Results presentation

[1550] The server sends the generated diagnosis candidates and treatment plans to a terminal, which then displays them to the medical staff via an electronic medical record system or medical information system.

[1551] Examples:

[1552] When a patient visits the hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses TensorFlow to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional then conducts a detailed examination based on this list.

[1553] Prevention and health promotion

[1554] Data collection

[1555] Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The hardware used is a smartphone, and the specific software used is a health management app. The smartphone then sends the collected data to a server.

[1556] Data analysis

[1557] The server then analyzes the received health data using AI algorithms to identify health risks and areas for improvement, using machine learning frameworks such as Keras.

[1558] Result notification

[1559] The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[1560] Emotion recognition

[1561] The emotion engine recognizes emotions from smartphone input data and user behavior. The software used is an emotion recognition algorithm.

[1562] Emotion-based advice adjustment

[1563] Based on the emotions recognized by the emotion engine, the server tailors health advice and improvement guidance.

[1564] Examples:

[1565] When a user enters their daily diet and exercise amount into a health management app, the server analyzes the data and identifies any nutrient deficiencies or areas for improvement. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), the advice is adjusted more flexibly. For example, if the user is feeling stressed, the server will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[1566] Utilizing medical data

[1567] Data collection

[1568] Hospitals provide medical records and treatment data to the server, which receives and stores the data.

[1569] Data analysis

[1570] The server uses AI algorithms to analyze the large amounts of medical data it receives and identify treatment effects and trends, using big data analysis tools such as Apache Spark and H2O.ai.

[1571] Providing results

[1572] Based on the analysis results, the server generates feedback for new research concepts and new drug development, and provides it to research institutions and drug development companies.

[1573] Examples:

[1574] Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If new treatments are found to be significantly effective against specific types of cancer, the server can provide this information to research institutions and drug development companies to promote further research and new drug development.

[1575] Example prompt for a generative AI model:

[1576] "Please suggest what health advice should be given to users who are experiencing stress."

[1577] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1578] Support for medical professionals

[1579] Step 1: User (healthcare professional) enters patient data

[1580] Users (healthcare professionals) input patients' symptoms, vital signs, and medical records into the electronic medical record system using devices such as PCs and tablets.

[1581] Input: Patient symptoms, vital signs, medical records

[1582] Output: Data entered into the electronic medical record system

[1583] Specific action: A healthcare professional types text or clicks an option on a PC or tablet.

[1584] Step 2: The device sends the data to the server

[1585] The terminal transmits the input data to the server via the network.

[1586] Input: Data entered into the electronic medical record system

[1587] Output: Patient data sent to the server

[1588] What it does: The device encrypts the data and sends it to the server using the HTTPS protocol.

[1589] Step 3: The server parses the data

[1590] The server analyzes the received patient data using AI algorithms, specifically software such as TensorFlow and PyTorch.

[1591] Input: Patient data sent to the server

[1592] Output: A list of diagnostic candidates and a treatment plan as the analysis results

[1593] Specific operation: The server cleanses the data, supplies it to the AI ​​model, and executes a Python script to generate analysis results.

[1594] Step 4: The server sends the results to the device

[1595] The server sends the generated diagnosis candidates and treatment plans to the terminal.

[1596] Input: A list of diagnostic candidates and a treatment plan as the analysis results

[1597] Output: Result data sent to the terminal

[1598] Specific operation: The server encrypts the analysis results and sends them to the device through a secure channel.

[1599] Step 5: The terminal displays the results

[1600] The device displays the received diagnostic candidates and treatment plans to medical professionals.

[1601] Input: Result data sent to the terminal

[1602] Output: Possible diagnoses and treatment plans displayed to healthcare professionals

[1603] Specific operation: The terminal displays data on the screen of an electronic medical record system, etc.

[1604] Prevention and health promotion

[1605] Step 1: User enters health data

[1606] Users enter their daily health data (diet, exercise, sleep, physical condition, etc.) into a health management app on their smartphone.

[1607] Input: Daily health data (diet, exercise, sleep, physical condition)

[1608] Output: Data entered into the health management app

[1609] Specific action: A user taps and swipes on a smartphone to enter data.

[1610] Step 2: The device sends the data to the server

[1611] The smartphone sends the entered health data to a server.

[1612] Input: Data entered into the health management app

[1613] Output: Health data sent to the server

[1614] Specific operation: The smartphone sends data to the server via Wi-Fi or mobile data communication.

[1615] Step 3: The server parses the data

[1616] The server analyzes the received health data using an AI algorithm, specifically the software Keras.

[1617] Input: Health data sent to the server

[1618] Output: Health risks and improvements as a result of the analysis

[1619] Specific operation: The server supplies data to the AI ​​model, which then calculates risks and areas for improvement.

[1620] Step 4: The server analyzes the emotional state

[1621] An emotion recognition engine recognizes the user's emotional state from the received data.

[1622] Input: Health data and related data

[1623] Output: Emotional state as a result of analysis

[1624] Specific operation: The server identifies the emotion using an emotion recognition algorithm.

[1625] Step 5: Servers adjust advice

[1626] The server adjusts health advice and improvement guidance based on the emotional state obtained from the emotion recognition engine.

[1627] Input: Emotion recognition results and health analysis results

[1628] Output: Tailored health advice and guidance

[1629] Specific behavior: The server generates advice and modifies the content according to the emotional state.

[1630] Step 6: The server sends the results to the device

[1631] The server then sends the generated health advice and improvement guidance to a smartphone.

[1632] Input: Tailored health advice and guidance

[1633] Output: Advice and guidance sent to your smartphone

[1634] Specific operation: The server encrypts the notification data and sends it to the smartphone.

[1635] Step 7: Your device will notify you of the results

[1636] The smartphone notifies the user of the advice and guidance received.

[1637] Input: Advice and guidance sent to your smartphone

[1638] Output: Advice and guidance to be given to the user

[1639] Specific action: The smartphone notifies the user via push notification or in-app message.

[1640] Utilizing medical data

[1641] Step 1: The hospital provides medical records and treatment data to the server

[1642] Multiple medical institutions provide medical records and treatment data to the server.

[1643] Input: medical records and treatment data

[1644] Output: Medical data stored on the server

[1645] Specific operation: The medical record system automatically transfers data to the server.

[1646] Step 2: The server parses the data

[1647] The server analyzes the received medical data using AI algorithms to identify treatment effects and trends, using software such as Apache Spark and H2O.ai.

[1648] Input: Medical data stored on the server

[1649] Output: Treatment effects and trend information as analysis results

[1650] Specific operation: The server supplies data to the AI ​​model and performs large-scale data analysis.

[1651] Step 3: Server generates feedback

[1652] The server generates feedback for new research concepts and new drug development based on the analysis results.

[1653] Input: Treatment effects and trend information as analysis results

[1654] Output: Feedback on research concepts and new drug development

[1655] Specific operation: The server formats the analysis results into a report format and generates the report.

[1656] Step 4: The server serves the results

[1657] The server provides the generated feedback to research institutions and drug development companies.

[1658] Input: Feedback on research concepts and new drug development

[1659] Output: Feedback provided to research institutions and drug development companies

[1660] What it does: The server encrypts the feedback and sends it to the relevant authority over a secure channel.

[1661] (Application example 2)

[1662] 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."

[1663] Current medical and health management systems do not adequately consider the psychological state of medical professionals and users, resulting in a lack of reduction in stress and emotional burden, and suboptimal treatment effectiveness and quality of health care. Furthermore, data analysis results are often significantly influenced by emotional states, making it difficult to provide appropriate diagnoses and treatment plans. Therefore, a system that can provide high-quality diagnoses, treatments, and health care recommendations while taking into account individual emotional states is needed.

[1664] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1665] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion engine for recognizing the emotional state of the user; and means for adjusting the generated candidate diagnoses and treatment plans based on the emotion recognized by the emotion engine. This enables more flexible and appropriate diagnosis, treatment, and health management proposals that take the emotional state into consideration.

[1666] A "healthcare professional" is someone whose occupation regularly provides health care services to patients.

[1667] "Patient data" refers to data that includes medical information such as a patient's symptoms, vital signs, and medical records.

[1668] "Artificial intelligence algorithms" are algorithms for analyzing data and generating predictive models in computers.

[1669] "Candidate diagnoses" are multiple disease names and pathological conditions that are presumed based on patient data.

[1670] A "treatment plan" is a specific treatment method or protocol proposed for a diagnosed disease or condition.

[1671] A "user" is an individual who uses the system, and in this context refers primarily to a person receiving health care or medical services.

[1672] "Health data" refers to data that includes information about daily health conditions such as diet, exercise, sleep, and physical condition.

[1673] An "emotion engine" is a system that recognizes the user's emotional state and provides feedback and advice based on that information.

[1674] "Drug development" is the process of developing new medicines and is based on research.

[1675] "Health advice" refers to specific guidance and suggestions aimed at reducing health risks and improving lifestyle habits.

[1676] "Treatment data" refers to medical records and data related to treatment behavior at hospitals and healthcare institutions.

[1677] To implement this invention, a medical support system incorporating an emotion engine is required. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1678] Support for medical professionals

[1679] Data collection

[1680] The terminal (a personal computer or tablet used by a healthcare professional) acts as a device where the healthcare professional inputs the patient's symptoms, vital signs, and medical records. This information is sent from the terminal to a server. The software used is an electronic medical record system, such as Epic or Cerner.

[1681] Data analysis

[1682] The server analyzes the received patient data using artificial intelligence algorithms (e.g., TensorFlow or PyTorch) to generate potential diagnoses and treatment plans. The emotion engine plays a part in this process, adjusting the diagnosis and treatment plan based on the patient's psychological state.

[1683] Results presentation

[1684] The server then sends the generated diagnosis candidates and treatment plans to a terminal, which displays them to the medical professional. For example, if a patient visits the hospital complaining of fever, cough, and fatigue, the medical professional enters these symptoms and the patient's vital signs into the electronic medical record and sends the data to the server. The server uses AI to list the most likely diagnoses, such as cold, flu, and COVID-19, and provides a treatment plan.

[1685] Prevention and health promotion

[1686] Data collection

[1687] Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The smartphone then sends the collected data to a server. Examples of such applications include Apple Health and Google Fit.

[1688] Data analysis

[1689] The server uses AI algorithms to analyze the received health data and identify health risks and areas for improvement. An emotion engine recognizes emotions from smartphone input data and user behavior. Software such as Emotion API and DeepFace is utilized.

[1690] Result notification

[1691] The server sends the generated health advice and guidance for improvement to the smartphone, which then notifies the user. The emotion engine flexibly adjusts the advice based on the user's emotional state. For example, if a user enters their daily diet and exercise amount into the app, the server will point out any nutrient deficiencies and areas for improvement in exercise, and if the user is feeling stressed, the server will notify them by saying, "Start with a short exercise session" or "We recommend a relaxing meal."

[1692] Example prompt sentence:

[1693] "How are you feeling today? For example, if you're feeling stressed, please enter that."

[1694] "We'll suggest the best menu for you based on your food preferences and mood. Just tell us your recent diet history."

[1695] Utilizing medical data

[1696] Data collection

[1697] Multiple healthcare institutions provide medical records and treatment data to the server, which is collected using a comprehensive electronic medical record system.

[1698] Data analysis

[1699] The server analyzes large amounts of medical data using AI algorithms to identify treatment effects and trends, and an emotion engine further analyzes the data based on the patient's psychological trends.

[1700] Providing results

[1701] Based on the analysis results, feedback for new research concepts and new drug development is generated and provided to research institutions and pharmaceutical companies. This will promote the discovery of new treatments and the development of new drugs. As a specific example, if cancer treatment data is collected from hospitals across the country and AI analyzes it, and it is found that new treatment A is showing significant effectiveness against a specific type of cancer, this information can be provided to research institutions and pharmaceutical companies to enable further research and new drug development.

[1702] This system will enable medical care and health management that takes emotional states into account, improving the quality of medical care and user satisfaction.

[1703] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1704] Step 1:

[1705] The device collects patient data (symptoms, vital signs, medical records) entered by medical professionals and sends the data to a server. The input data includes information such as fever, cough, and fatigue. This data is collected and sent using an electronic medical record system (e.g., Epic, Cerner).

[1706] Step 2:

[1707] The server analyzes the patient data it receives using an artificial intelligence algorithm (e.g., TensorFlow or PyTorch). Specifically, it preprocesses the data and generates appropriate diagnostic candidates (e.g., cold, flu, COVID-19, etc.). At this time, the AI ​​model lists the diagnostic candidates in descending order based on the input data (patient symptoms).

[1708] Step 3:

[1709] The generated diagnosis candidates and treatment plans are sent to a terminal, which displays them to medical professionals. Specifically, a list of diagnosis candidates and a treatment plan based on them are displayed on the screen, and medical professionals can evaluate and make decisions.

[1710] Step 4:

[1711] The emotion engine uses the smartphone's camera and voice input functions to recognize the user's emotional state. It uses image and voice data to analyze the user's emotions (e.g., tiredness, stress, optimism, etc.). This process utilizes the Emotion API and DeepFace.

[1712] Step 5:

[1713] The server takes the user's emotional state into account to adjust potential diagnoses and treatment plans. Specifically, it modifies the usual diagnosis and treatment plan based on the user's emotional state. For example, if stress is causing symptoms to worsen, the server generates a treatment plan that also addresses that.

[1714] Step 6:

[1715] Users enter their daily health data (food, exercise, sleep, physical condition) into a smartphone app, and this data is sent to a server via applications such as Apple Health and Google Fit.

[1716] Step 7:

[1717] The server analyzes the received health data and uses an artificial intelligence algorithm to identify health risks and areas for improvement. As a result of the analysis, it identifies areas for improvement such as nutrient deficiencies and exercise. Specific health advice is generated based on this data.

[1718] Step 8:

[1719] The emotion engine analyzes the user's emotional state and adjusts health advice and guidance accordingly. For example, a user feeling stressed may be given flexible advice such as "Start with a short workout" or "Recommend a relaxing diet."

[1720] Step 9:

[1721] The server then sends the generated health advice and guidance to the smartphone, which then notifies the user of the advice. Specifically, the information is displayed to the user via a pop-up notification or push notification.

[1722] Step 10:

[1723] Multiple healthcare institutions provide medical records and treatment data to the server, which is collected using a comprehensive electronic medical record system.

[1724] Step 11:

[1725] The server analyzes large amounts of medical data using AI algorithms to identify treatment effects and trends, and an emotion engine analyzes the data while taking into account the patient's psychological trends.

[1726] Step 12:

[1727] Based on the analysis results, feedback for new research concepts and new drug development will be generated and provided to research institutions and pharmaceutical companies, thereby accelerating the discovery of new treatments and the development of new drugs.

[1728] This provides a concrete explanation of the processing steps of the entire system, clarifying the data processing and calculations performed at each step, as well as the output based on these.

[1729] 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.

[1730] 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.

[1731] 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.

[1732] [Fourth embodiment]

[1733] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1734] 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.

[1735] 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).

[1736] 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.

[1737] 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.

[1738] 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).

[1739] 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.

[1740] 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.

[1741] 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.

[1742] 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.

[1743] 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.

[1744] 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.

[1745] 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."

[1746] The present invention provides a system that aims to reduce the burden on medical professionals, improve the quality of medical care, increase patient satisfaction, and effectively utilize medical data. This system is embodied in the following specific form.

[1747] The system consists of three main components: the server, the terminal, and the user.

[1748] Support for medical professionals

[1749] 1. Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[1750] 2. Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[1751] 3. Presentation of results: The server sends the generated diagnostic candidates and treatment plans to the terminal, which displays them to the medical professional.

[1752] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[1753] Prevention and health promotion

[1754] 1. Data collection: Users enter their daily health data, such as diet, exercise, sleep, and physical condition, into a smartphone app. The smartphone then sends the collected data to a server.

[1755] 2. Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[1756] 3. Notification of results: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[1757] Example: When a user enters their daily diet and exercise amount into an app, the server analyzes the information and identifies any nutrient deficiencies and areas for improvement in exercise. The app then notifies the user with messages such as "Eat more vegetables" or "We recommend walking 30 minutes every day."

[1758] Utilizing medical data

[1759] 1. Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[1760] 2. Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[1761] 3. Providing results: The server generates feedback for new research concepts and new drug development based on the analysis results and provides them to research institutions and pharmaceutical companies.

[1762] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[1763] A system with these functions will be able to comprehensively solve Japan's health issues through supporting medical professionals, prevention and health promotion, and effective use of medical data. In addition, the system's flexible structure allows it to adapt to different medical environments and user needs.

[1764] The processing flow will be explained below.

[1765] Support for medical professionals

[1766] Step 1:

[1767] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[1768] Step 2:

[1769] Terminal: Sends the entered patient data to the server.

[1770] Step 3:

[1771] Server: Stores the received patient data.

[1772] Step 4:

[1773] Server: Analyzes stored patient data using artificial intelligence algorithms.

[1774] Step 5:

[1775] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[1776] Step 6:

[1777] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[1778] Step 7:

[1779] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[1780] Prevention and health promotion

[1781] Step 1:

[1782] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[1783] Step 2:

[1784] Smartphone: Sends the entered health data to the server.

[1785] Step 3:

[1786] Server: Stores the received health data.

[1787] Step 4:

[1788] Server: Analyzes stored health data using artificial intelligence algorithms.

[1789] Step 5:

[1790] Server: Identifies health risks and areas for improvement based on the analysis results.

[1791] Step 6:

[1792] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[1793] Step 7:

[1794] Server: Sends the generated health advice and improvement guidance to a smartphone.

[1795] Step 8:

[1796] Smartphone: Provides health advice and guidance to users.

[1797] Utilizing medical data

[1798] Step 1:

[1799] Hospital: Provides medical records and treatment data to the server.

[1800] Step 2:

[1801] Server: Receives and stores the data provided.

[1802] Step 3:

[1803] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[1804] Step 4:

[1805] Server: Identify treatment effects and trends from analysis results.

[1806] Step 5:

[1807] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[1808] Step 6:

[1809] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[1810] Example 1

[1811] 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."

[1812] In the medical field, medical professionals are required to efficiently collect patient data and quickly provide diagnoses and treatment plans based on that data. It is also important to accurately collect and analyze health data from patients' daily lives and provide appropriate health advice. Furthermore, there is a need to effectively analyze medical records and treatment data collected from multiple hospitals and use the data for new research and the development of new treatments. To solve these challenges, a system is needed to efficiently and safely perform each process of data collection, analysis, and provision.

[1813] 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.

[1814] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including a terminal for transmitting the patient data to the server using a secure communication protocol; and means for encrypting and transmitting the candidate diagnoses and treatment plans from the server to the terminal, thereby enabling medical professionals to quickly and safely collect and analyze patient data and provide appropriate diagnoses and treatment plans.

[1815] In this invention, the server includes means for receiving daily health data entered by the user, means including an artificial intelligence algorithm for analyzing the health data and identifying health risks and areas for improvement, means for notifying the user of the generated health advice and improvement guidance, means for transmitting the user's input data from a smartphone app to the server, and means for notifying the smartphone of the analysis results, thereby enabling the user to easily collect and analyze health data from their daily lives and receive appropriate health advice.

[1816] Furthermore, in this invention, the server includes: means for receiving medical records and treatment data from multiple hospitals; means including an artificial intelligence algorithm for analyzing the received data and identifying treatment effects and trends; means for generating feedback for new research concepts and new drug development based on the analysis results and providing the feedback to research institutions and pharmaceutical companies; means for analyzing the data using distributed processing technology; and means for storing the analysis results in secure storage, encrypting them, and providing them. This enables effective analysis of medical data and makes it possible to use the data for new research and development of new treatments.

[1817] "Healthcare professionals" is a general term for people who work in medical institutions such as hospitals and clinics, examining, treating, and caring for patients.

[1818] "Patient Data" means any data related to a patient's diagnosis or treatment, including symptoms, vital signs, and medical records.

[1819] "Means of receiving" refers to the function of inputting data into a specific device or system using a communication protocol or network.

[1820] "Analysis" is the process of analyzing collected data using technologies such as artificial intelligence algorithms to identify potential diagnoses, treatment plans, and areas for improvement.

[1821] "Candidate diagnoses" are a list of possible diagnoses identified by an artificial intelligence algorithm based on patient data.

[1822] A "treatment plan" is a detailed treatment policy and specific treatment method formulated based on the diagnostic results.

[1823] An "artificial intelligence algorithm" is a computer program that uses techniques such as machine learning and deep learning to analyze data and make inferences.

[1824] "Presentation means" refers to the function of visually showing the analysis results, diagnostic candidates, and treatment plans to the user via a display device or terminal.

[1825] A "communications protocol" is a set of rules and procedures for data communication, and is a set of regulations for standardizing and safely transmitting and receiving data.

[1826] A "terminal" is an electronic device for inputting and displaying data, and refers to PCs, tablets, and smartphones used by medical professionals and users.

[1827] "Encryption" is the process of transforming original information into another form using a specific algorithm in order to protect the data.

[1828] A "smartphone app" is a software application that runs on a smartphone and provides health data input and notification functions.

[1829] "Distributed processing technology" is a technology that uses multiple computer resources to analyze and process data simultaneously and in parallel.

[1830] "Secure storage" refers to a data storage system in which data is stored securely and has data access control and encryption functions.

[1831] This system aims to enable medical professionals to efficiently collect and analyze patient data and provide appropriate diagnoses and treatment plans. It also aims to analyze health data from users' daily lives and provide appropriate health advice, as well as analyze medical records and treatment data collected from multiple hospitals to aid in new research and the development of new treatments. This system consists of three main components: a server, a terminal, and a user.

[1832] Hardware and Software

[1833] server

[1834] The server plays a central role in receiving, analyzing, and storing data. The software used includes artificial intelligence algorithms for analysis (e.g., TensorFlow and PyTorch). HTTPS and TLS protocols are used to securely receive and transmit data. Apache Spark is used for distributed data processing.

[1835] Terminal

[1836] A device is a device where a healthcare professional or user enters data, and can be a PC, tablet, or smartphone. The device runs an electronic medical record system (e.g., Epic or Cerner) or a health app (e.g., HealthKit or Google Fit). Secure communication protocols are used to transmit data from the device.

[1837] User

[1838] Users are responsible for inputting and collecting health data in their daily lives. The collected data is sent to a server via a smartphone app, and notifications are received from the server.

[1839] Data collection and analysis

[1840] Support for medical professionals

[1841] 1. Data Collection:

[1842] The device allows medical professionals to input a patient's symptoms, vital signs, and medical records into an electronic medical record. For example, a doctor inputs and saves a patient's temperature and blood pressure, and the data is then sent to a server.

[1843] The terminal transmits the input data to the server using a secure protocol.

[1844] 2. Data Analysis:

[1845] The server analyzes the received patient data using AI algorithms, and for example, the server lists possible diagnoses such as cold, flu, or COVID-19.

[1846] The server generates the analysis results and sends them to the terminal.

[1847] 3. Results presentation:

[1848] The device then displays the received diagnostic candidates and treatment plans to the medical professional, who can then review the diagnosis results and modify the treatment plan as necessary.

[1849] Prevention and health promotion

[1850] 1. Data Collection:

[1851] Users input their daily diet, exercise, and sleep data into a health app on their smartphone. For example, when a user inputs and saves their dietary information, it is automatically sent to the server.

[1852] The smartphone periodically synchronizes data with the server.

[1853] 2. Data Analysis:

[1854] The server then analyzes the received health data using AI algorithms, identifying, for example, nutritional deficiencies and areas for improvement in exercise habits.

[1855] The server generates health advice based on the analysis results and sends it to the smartphone.

[1856] 3. Result notification:

[1857] The smartphone will then notify the user of the health advice it has received, such as messages like "Eat more vegetables" or "We recommend walking 30 minutes a day."

[1858] Utilizing medical data

[1859] 1. Data Collection:

[1860] Multiple hospitals provide medical records and treatment data to the server, for example by exporting the data weekly and sending it to the server in a secure manner.

[1861] The server stores the received data and accumulates it in a data warehouse.

[1862] 2. Data Analysis:

[1863] The server then uses AI algorithms to analyze the large amounts of medical data it receives, for example by analyzing the data in detail to identify the effectiveness of new treatments.

[1864] The server identifies the analysis results as new research concepts and treatments and generates feedback.

[1865] 3. Results provided:

[1866] The server provides the analysis results to research institutions and pharmaceutical companies. The results are stored in secure storage and provided in encrypted form.

[1867] Examples of concrete examples and prompts

[1868] Specific examples include cases where a doctor enters data on a patient complaining of fever, cough, or fatigue into an electronic medical record, which is then analyzed by a server to suggest possible diagnoses, or where a user enters information about their diet and exercise into a health app, which then analyzes the information and provides health advice. Another example is the analysis of treatment data from hospitals across the country to help with new drug development.

[1869] Example prompt sentence:

[1870] 1. "Doctors enter fever, cough, and fatigue into patients' electronic medical records, and the server analyzes this data using AI to generate potential diagnoses."

[1871] 2. "Users enter their dietary information and exercise amount into the app, and the server analyzes that data using AI to generate health advice."

[1872] 3. "Please explain the process by which a server uses AI to analyze cancer treatment data provided by hospitals across the country, identify the effectiveness of new treatments, and provide the results to research institutions."

[1873] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1874] Support for medical professionals

[1875] Data collection

[1876] Step 1:

[1877] A medical professional opens the electronic medical record system using a terminal (PC or tablet). For example, a doctor operates the electronic medical record software on the hospital's local server and logs in.

[1878] Step 2:

[1879] Medical staff enter data such as patient information, symptoms, and vital signs, such as the patient's temperature, blood pressure, and symptoms (fever, cough, fatigue) using a keyboard or touchscreen.

[1880] Input: Patient's vital signs and symptoms, including temperature and blood pressure

[1881] Output: Dataset of input patient information

[1882] Step 3:

[1883] The terminal sends the entered data to the server using a secure communication protocol (HTTPS or TLS). For example, when a doctor clicks the "Save" button, the electronic medical record system encrypts the data and sends it to the server in real time.

[1884] Input: Dataset of entered patient information

[1885] Output: Securely transmitted patient information

[1886] Data analysis

[1887] Step 4:

[1888] The server then passes the received patient data to an artificial intelligence algorithm for analysis. For example, a patient's symptom data is fed into an AI model running on TensorFlow or PyTorch.

[1889] Input: Dataset of patient information

[1890] Output: Analysis request by AI algorithm

[1891] Step 5:

[1892] The server analyzes the data and matches symptoms with potential diagnoses. For example, an AI model could analyze a patient's symptom data and come up with a list of possibilities, such as cold, flu, or COVID-19.

[1893] Input: Analysis request by AI algorithm

[1894] Output: Diagnosis candidate list

[1895] Step 6:

[1896] The server formats the generated diagnostic candidates and treatment plans for the electronic medical record system, encrypts them, and transmits them to the terminal.

[1897] Input: Diagnosis candidate list

[1898] Output: Encrypted diagnosis candidate list and treatment plan

[1899] Results presentation

[1900] Step 7:

[1901] The terminal receives the diagnosis candidates and treatment plans from the server and presents them to the medical staff. For example, a list of diagnosis candidates is displayed on the electronic medical record screen.

[1902] Input: Encrypted diagnostic candidate list and treatment plan

[1903] Output: A list of diagnostic candidates and a treatment plan displayed on the screen

[1904] Prevention and health promotion

[1905] Data collection

[1906] Step 1:

[1907] The user opens a health app on their smartphone, for example, HealthKit or Google Fit.

[1908] Step 2:

[1909] Users input their daily diet, exercise, and sleep data. For example, they record their diet and exercise amount in the app by tapping or voice input.

[1910] Input: Daily diet, exercise, and sleep data

[1911] Output: A dataset of the input health data

[1912] Step 3:

[1913] The smartphone securely transmits collected data to the server, and it is assumed that data will be transmitted periodically using the automatic synchronization function.

[1914] Input: A dataset of input health data

[1915] Output: Securely transmitted health data

[1916] Data analysis

[1917] Step 4:

[1918] The server passes the received health data to an artificial intelligence algorithm for analysis. For example, the health data is input into an AI model.

[1919] Input: Health data dataset

[1920] Output: AI analysis request

[1921] Step 5:

[1922] The server analyzes the data and identifies health risks and areas for improvement. For example, AI models can identify nutrient deficiencies or lack of exercise.

[1923] Input: AI analysis request

[1924] Output: List of health risks and improvements

[1925] Step 6:

[1926] The server formats the generated health advice so that it can be sent to a smartphone, encrypts it, and sends it.

[1927] Input: List of health risks and improvements

[1928] Output: Encrypted health advice

[1929] Result notification

[1930] Step 7:

[1931] The smartphone notifies the user of the health advice received from the server. For example, a health message is displayed in the notification area of ​​the app.

[1932] Input: Encrypted health advice

[1933] Output: Notified health advice

[1934] Utilizing medical data

[1935] Data collection

[1936] Step 1:

[1937] Multiple hospitals provide medical records and treatment data to the server. For example, hospital information system personnel export the data and send it to the server using a secure file transfer protocol.

[1938] Input: Medical records and treatment data

[1939] Output: Transmitted medical data

[1940] Data analysis

[1941] Step 2:

[1942] The server stores the received data and accumulates it in a data warehouse.

[1943] Input: Transmitted medical data

[1944] Output: Stored medical data

[1945] Step 3:

[1946] The server inputs large amounts of medical data into an artificial intelligence algorithm for analysis, and the data is processed using distributed processing technology.

[1947] Input: Stored medical data

[1948] Output: AI analysis request

[1949] Step 4:

[1950] The server performs the analysis to identify treatment effects and trends. For example, data is analyzed in detail to identify the effects of new treatment A.

[1951] Input: AI analysis request

[1952] Output: Analysis results (treatment effects and trends)

[1953] Providing results

[1954] Step 5:

[1955] The server provides the analysis results to research institutions and pharmaceutical companies. The analysis results are stored in secure storage and provided in encrypted form.

[1956] Input: Analysis results (treatment effects and trends)

[1957] Output: Securely encrypted data provided

[1958] (Application example 1)

[1959] 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."

[1960] Currently, quality control is extremely important in the medical device manufacturing process, but conventional methods have issues such as delayed detection of defective products and the enormous effort and time required for overall product quality control. Furthermore, in medical settings, diagnoses and treatment plans must be made quickly and accurately, placing a heavy burden on medical professionals. Furthermore, to effectively utilize the large amounts of data collected in factories, real-time data analysis and quality control are required. To solve these issues, an advanced data analysis system utilizing AI technology and an efficient infrastructure to implement it are required.

[1961] 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.

[1962] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; data collection means for receiving manufacturing data acquired by machines used in a factory and performing quality evaluation; means including an artificial intelligence algorithm for analyzing the manufacturing data in real time and identifying potential defects and defective products; and means for displaying quality control information on the manufacturing line based on the analysis results. This enables the improvement of the accuracy of diagnoses and treatment plans in medical settings, as well as the efficiency of quality control on the manufacturing line in the factory and the reduction of defective products.

[1963] "Healthcare workers" is a general term for doctors, nurses, and other health care professionals who diagnose and treat patients in hospitals and clinics.

[1964] "Patient data" refers to information collected in medical settings, such as patient symptoms, vital signs, and medical records.

[1965] "Artificial intelligence algorithm" is a general term for computational methods and programs used to analyze large amounts of data and generate specific results.

[1966] "Candidate diagnoses" is a list of possible diagnostic results based on the input data.

[1967] A "treatment plan" refers to a set of proposed treatment methods or steps based on a particular diagnosis.

[1968] "Machinery used in factories" is a general term for all automated devices and machinery used in the manufacturing process.

[1969] "Manufacturing data" refers to process data and quality data acquired by machines in a factory.

[1970] "Data collection means" refers to a device or system for collecting patient data or manufacturing data.

[1971] "Quality evaluation" refers to the process of determining whether manufactured products meet standards.

[1972] "Real-time" refers to instantaneous processing and response, meaning there is little to no delay.

[1973] A "latent defect" refers to a problem or defect that is likely to be present in a product but has not yet become apparent.

[1974] "Defective Product" means a product that does not meet standards and is not suitable for use or sale.

[1975] "Quality control information" refers to information on the quality status of a product and defect detection, and management and improvements are carried out based on this information.

[1976] "Cloud server" is a general term for a remote server where data is stored and processed via the Internet.

[1977] "Improvement proposals" refer to methods and measures for improving products or processes proposed based on the analysis results.

[1978] "Pharmaceutical company" is a general term for companies that research, develop, manufacture, and sell new drugs.

[1979] "Research institute" is a general term for organizations that conduct research activities with the aim of developing new knowledge and technology.

[1980] This invention is a system that reduces the burden on medical professionals, improves the quality of medical care, and streamlines quality control in the manufacturing industry. This system utilizes AI technology in both medical and manufacturing settings to perform data analysis and realize diagnostic support and quality control.

[1981] Support for medical professionals

[1982] The server receives patient data entered by medical professionals and analyzes it using AI algorithms. For example, when a medical professional enters a patient's symptoms and vital signs into an electronic medical record, the server receives this information and uses an AI model to generate potential diagnoses, such as cold, flu, or COVID-19. This information is then sent to the medical professional's device to help with detailed examinations.

[1983] Factory quality control

[1984] The server receives manufacturing data acquired by machines used in the factory and collects the data for quality evaluation. For example, a camera attached to a factory device takes a picture of a medical device being manufactured and sends the image data to the server. The server then analyzes the image using an AI algorithm to identify potential defects or defective products. The analysis results are displayed on the production line and provided as quality control information.

[1985] Data collection and analysis for health promotion

[1986] When users enter their daily health data into their smartphone, the server receives it and uses AI algorithms to identify health risks and areas for improvement. For example, when a user enters their daily diet and exercise amount into the app, the server analyzes any nutrient deficiencies and areas for improvement in exercise, and sends appropriate advice to the smartphone.

[1987] Hardware and software used

[1988] The hardware used includes medical staff tablets and PCs, cameras on the production line, and users' smartphones, and the software used is Python, OpenCV, TensorFlow / Keras, and the Requests library.

[1989] Data processing and calculation

[1990] 1. Data collection: Collecting patient and manufacturing data from terminals and machines.

[1991] 2. Data Preprocessing: The image data undergoes preprocessing such as resizing, normalization, and reshaping.

[1992] 3. AI analysis: Analyze the data using pre-trained AI models to generate candidate diagnoses and quality assessments.

[1993] 4. Notification: The analysis results are sent to devices and production lines for use in medical and manufacturing settings.

[1994] Examples and prompts

[1995] For example, if a manufacturing line is making surgical tools, the robot will take a picture of the part with a camera and pass the image to an AI model for analysis, which will determine if the part is defective and, if necessary, send the data to a server.

[1996] Example prompt sentence:

[1997] Analyze images taken from a production line today and list the parts that are likely to be defective. Also, describe in detail which parts are problematic.

[1998] This system will improve the accuracy of diagnosis and treatment planning in medical settings, while also making quality control more efficient and reducing defective products on factory production lines.

[1999] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2000] Step 1:

[2001] Users input data using devices (medical staff's tablets or PCs, or cameras on the manufacturing line). The input data includes patient symptoms, vital signs, and images of medical equipment being manufactured. This prepares the data to be sent to the server.

[2002] Step 2:

[2003] The device sends the input data to the server. The server checks the format of the received data and performs preprocessing as necessary. For example, if the data is image data, it resizes or normalizes it, and if it is text data, it checks the format. This ensures data consistency and makes it suitable for analysis.

[2004] Step 3:

[2005] The server inputs the preprocessed data into an AI algorithm, which analyzes the data based on a pre-trained model and generates a diagnosis candidate, a treatment plan, or a quality assessment. For example, for image data sent from a manufacturing line, it scores the likelihood of a defective product. This generates a data analysis result.

[2006] Step 4:

[2007] The server checks the generated analysis results and performs additional analysis as necessary. The analysis results are also sent to the cloud server and used for further analysis and feedback. For example, new treatments or quality improvement measures may be proposed based on the analysis results. This improves the reliability and usefulness of the analysis results.

[2008] Step 5:

[2009] The server notifies the terminal of the generated analysis results and suggestions, which are then displayed on the terminal to medical professionals and production line workers. Specifically, medical professionals are shown potential diagnoses and treatment plans, while production line workers are shown a list of defective products and suggestions for quality improvement. This enables the data to be put to practical use.

[2010] Step 6:

[2011] Users (healthcare professionals and production line workers) can then take action based on the displayed analysis results and recommendations: healthcare professionals adjust diagnoses and treatment plans, and production line workers implement quality improvement measures, leading to continuous improvement of the entire system.

[2012] 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.

[2013] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[2014] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[2015] Support for medical professionals

[2016] Data collection: On the terminal (healthcare worker's PC or tablet), the healthcare worker inputs the patient's symptoms, vital signs, and medical records into the electronic medical record. The terminal sends the input data to the server.

[2017] Data analysis: The server analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans.

[2018] Result presentation: The server sends the generated diagnosis candidates and treatment plans to the terminal, which displays them to the medical professional.

[2019] Example: When a patient visits a hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses AI to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional uses this information to conduct a detailed examination.

[2020] Prevention and health promotion

[2021] Data collection: Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The smartphone then sends the collected data to a server.

[2022] Data analysis: The server analyzes the received health data using AI algorithms to identify health risks and areas for improvement.

[2023] Result notification: The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[2024] Emotion recognition: The emotion engine recognizes emotions from smartphone input data and user behavior.

[2025] Emotion-based advice adjustment: Based on the emotions recognized by the emotion engine, the server adjusts health advice and improvement guidance.

[2026] Example: When a user enters their daily diet and exercise amount into the app, the server analyzes this and points out any missing nutrients or areas for improvement in exercise. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), it adjusts the advice more flexibly. For example, if the user is feeling stressed, it will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[2027] Utilizing medical data

[2028] Data collection: Hospitals provide medical records and treatment data to the server. The server receives and stores the provided data.

[2029] Data analysis: The server uses AI algorithms to analyze the large amount of medical data it receives and identify treatment effects and trends.

[2030] Result provision: Based on the analysis results, the server generates feedback for new research concepts and new drug development and provides it to research institutions and pharmaceutical companies.

[2031] Example: Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If it turns out that new treatment A is showing remarkable effectiveness against a specific type of cancer, the server can provide this information to research institutions and pharmaceutical companies to promote further research and new drug development.

[2032] The system with these functions will be able to provide flexible advice that takes into account the user's psychological state by incorporating an emotion engine, further improving the quality of medical care and health management. The system's flexible structure will allow it to adapt to different medical environments and user needs.

[2033] The processing flow will be explained below.

[2034] Support for medical professionals

[2035] Step 1:

[2036] Terminal: Medical professionals enter the patient's symptoms, vital signs, and medical records into the electronic medical record.

[2037] Step 2:

[2038] Terminal: Sends the entered patient data to the server.

[2039] Step 3:

[2040] Server: Stores the received patient data.

[2041] Step 4:

[2042] Server: Analyzes stored patient data using artificial intelligence algorithms.

[2043] Step 5:

[2044] Server: Generates diagnostic candidates and treatment plans from the analysis results.

[2045] Step 6:

[2046] Server: Sends the generated diagnosis candidates and treatment plans to the terminal.

[2047] Step 7:

[2048] Terminal: Displays possible diagnoses and treatment plans to medical professionals.

[2049] Prevention and health promotion

[2050] Step 1:

[2051] User: Enters daily health data (diet, exercise, sleep, physical condition, etc.) into a smartphone app.

[2052] Step 2:

[2053] Smartphone: Sends the entered health data to the server.

[2054] Step 3:

[2055] Server: Stores the received health data.

[2056] Step 4:

[2057] Server: Analyzes stored health data using artificial intelligence algorithms.

[2058] Step 5:

[2059] Server: Identifies health risks and areas for improvement based on the analysis results.

[2060] Step 6:

[2061] Server: Generates specific health advice and improvement guidance based on identified health risks and areas for improvement.

[2062] Step 7:

[2063] Server: Sends the generated health advice and improvement guidance to a smartphone.

[2064] Step 8:

[2065] Smartphone: Provides health advice and guidance to users.

[2066] Step 9:

[2067] Emotion Engine: Recognizes emotions from user input data and their behavior.

[2068] Step 10:

[2069] Emotion Engine: Sends instructions to the server based on the recognized emotion.

[2070] Step 11:

[2071] Server: Receives instructions from the emotion engine and adjusts health advice and improvement guidance.

[2072] Step 12:

[2073] Server: Resends tailored advice and improvement guidance to the smartphone.

[2074] Step 13:

[2075] Smartphone: Notify users with tailored advice and guidance.

[2076] Utilizing medical data

[2077] Step 1:

[2078] Hospital: Provides medical records and treatment data to the server.

[2079] Step 2:

[2080] Server: Receives and stores the data provided.

[2081] Step 3:

[2082] Server: Analyzes large amounts of stored medical data using artificial intelligence algorithms.

[2083] Step 4:

[2084] Server: Identify treatment effects and trends from analysis results.

[2085] Step 5:

[2086] Server: Generates feedback for new research concepts and drug development based on identified treatment effects and trends.

[2087] Step 6:

[2088] Server: Provides generated feedback to research institutions and pharmaceutical companies.

[2089] Example 2

[2090] 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."

[2091] Conventional medical support systems were able to analyze medical and daily health data to provide potential diagnoses, treatment plans, and health advice. However, it was difficult to provide flexible advice and treatment plans that took the user's emotional state into account, which sometimes resulted in insufficient support for medical professionals and users. This created a challenge: improving the quality of medical care while simultaneously reducing the psychological burden on patients and users.

[2092] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2093] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion recognition engine for analyzing the emotional state of the user; and means for adjusting the candidate diagnoses and treatment plans based on the emotional state obtained by the emotion recognition engine. This enables the provision of flexible advice and appropriate treatment plans that take the user's emotional state into consideration.

[2094] "Medical professionals" refer to professionals who perform medical procedures such as medical examinations, treatment, and nursing for patients at medical institutions.

[2095] "Patient data" refers to all information necessary for medical examination and treatment, such as a patient's symptoms, vital signs, and medical records.

[2096] An "artificial intelligence algorithm" refers to a program that uses techniques such as machine learning and deep learning to analyze large amounts of data and generate conclusions and predictions based on specific purposes.

[2097] "Candidate diagnoses" refers to a list of likely diseases or conditions based on a patient's symptoms and data.

[2098] A "treatment plan" is a plan that includes details of the treatment to be administered to a patient, based on the results of a diagnosis.

[2099] "User" refers to medical professionals and general individuals who use the system, and who input health data and check diagnosis results.

[2100] "Health data" refers to all information related to an individual's health status, such as diet, exercise, sleep, and physical condition.

[2101] An "emotion recognition engine" refers to a program that analyzes and identifies a user's emotional state (e.g., stress, joy, sadness, etc.) from input data and user behavior.

[2102] "Health advice" refers to suggestions and guidance for maintaining and improving health that are provided to users based on health data and analysis results.

[2103] A "research institution" refers to an organization or group that develops new medical technologies and drugs, researches treatment methods, etc.

[2104] "Drug development companies" refer to companies that research, develop, manufacture, and sell new drugs.

[2105] "Medical record" means any record relating to the examination, treatment, and follow-up of a patient.

[2106] "Treatment data" refers to information about the effectiveness, results, and patient response of a particular treatment.

[2107] "Analysis results" refers to output information such as conclusions, predictions, and findings obtained as a result of data analysis by AI algorithms.

[2108] "Feedback" refers to advice and suggestions for new research concepts, treatments, and new drug development that are generated based on the analysis results.

[2109] This invention combines an emotion engine with a system to reduce the burden on medical professionals, improve the quality of medical care, and increase patient satisfaction. In addition to analyzing medical data, this system aims to recognize the user's emotional state and provide appropriate feedback and advice.

[2110] The system consists of four main components: the server, the terminal, the user, and the emotion engine.

[2111] Support for medical professionals

[2112] Data collection

[2113] On the terminal (healthcare worker's PC or tablet), healthcare workers input the patient's symptoms, vital signs, and medical records into the electronic medical record. Specific hardware used is a standard PC or tablet. The terminal sends the input data to a server. The software used is an electronic medical record system.

[2114] Data analysis

[2115] The server then analyzes the received data using AI algorithms to generate potential diagnoses and treatment plans. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used. During the analysis process, potential diagnoses are listed based on the patient's symptoms and vital signs.

[2116] Results presentation

[2117] The server sends the generated diagnosis candidates and treatment plans to a terminal, which then displays them to the medical staff via an electronic medical record system or medical information system.

[2118] Examples:

[2119] When a patient visits the hospital complaining of fever, cough, and fatigue, a medical professional enters these symptoms and the patient's vital signs into an electronic medical record and sends the data to a server. The server uses TensorFlow to list the most likely causes, such as cold, flu, or COVID-19, and provides a treatment plan. The medical professional then conducts a detailed examination based on this list.

[2120] Prevention and health promotion

[2121] Data collection

[2122] Users enter their daily health data (food, exercise, sleep, physical condition, etc.) into a smartphone app. The hardware used is a smartphone, and the specific software used is a health management app. The smartphone then sends the collected data to a server.

[2123] Data analysis

[2124] The server then analyzes the received health data using AI algorithms to identify health risks and areas for improvement, using machine learning frameworks such as Keras.

[2125] Result notification

[2126] The server sends the generated health advice and improvement guidance to the smartphone, which then notifies the user.

[2127] Emotion recognition

[2128] The emotion engine recognizes emotions from smartphone input data and user behavior. The software used is an emotion recognition algorithm.

[2129] Emotion-based advice adjustment

[2130] Based on the emotions recognized by the emotion engine, the server tailors health advice and improvement guidance.

[2131] Examples:

[2132] When a user enters their daily diet and exercise amount into a health management app, the server analyzes the data and identifies any nutrient deficiencies or areas for improvement. If the emotion engine recognizes the user's emotional state (e.g., stress level or low motivation), the advice is adjusted more flexibly. For example, if the user is feeling stressed, the server will notify them with messages such as "Start with a short workout" or "We recommend a relaxing meal."

[2133] Utilizing medical data

[2134] Data collection

[2135] Hospitals provide medical records and treatment data to the server, which receives and stores the data.

[2136] Data analysis

[2137] The server uses AI algorithms to analyze the large amounts of medical data it receives and identify treatment effects and trends, using big data analysis tools such as Apache Spark and H2O.ai.

[2138] Providing results

[2139] Based on the analysis results, the server generates feedback for new research concepts and new drug development, and provides it to research institutions and drug development companies.

[2140] Examples:

[2141] Cancer treatment data from hospitals across the country is collected on a server and analyzed by AI. If new treatments are found to be significantly effective against specific types of cancer, the server can provide this information to research institutions and drug development companies to promote further research and new drug development.

[2142] Example prompt for a generative AI model:

[2143] "Please suggest what health advice should be given to users who are experiencing stress."

[2144] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2145] Support for medical professionals

[2146] Step 1: User (healthcare professional) enters patient data

[2147] Users (healthcare professionals) input patients' symptoms, vital signs, and medical records into the electronic medical record system using devices such as PCs and tablets.

[2148] Input: Patient symptoms, vital signs, medical records

[2149] Output: Data entered into the electronic medical record system

[2150] Specific action: A healthcare professional types text or clicks an option on a PC or tablet.

[2151] Step 2: The device sends the data to the server

[2152] The terminal transmits the input data to the server via the network.

[2153] Input: Data entered into the electronic medical record system

[2154] Output: Patient data sent to the server

[2155] What it does: The device encrypts the data and sends it to the server using the HTTPS protocol.

[2156] Step 3: The server parses the data

[2157] The server analyzes the received patient data using AI algorithms, specifically software such as TensorFlow and PyTorch.

[2158] Input: Patient data sent to the server

[2159] Output: A list of diagnostic candidates and a treatment plan as the analysis results

[2160] Specific operation: The server cleanses the data, supplies it to the AI ​​model, and executes a Python script to generate analysis results.

[2161] Step 4: The server sends the results to the device

[2162] The server sends the generated diagnosis candidates and treatment plans to the terminal.

[2163] Input: A list of diagnostic candidates and a treatment plan as the analysis results

[2164] Output: Result data sent to the terminal

[2165] Specific operation: The server encrypts the analysis results and sends them to the device through a secure channel.

[2166] Step 5: The terminal displays the results

[2167] The device displays the received diagnostic candidates and treatment plans to medical professionals.

[2168] Input: Result data sent to the terminal

[2169] Output: Possible diagnoses and treatment plans displayed to healthcare professionals

[2170] Specific operation: The terminal displays data on the screen of an electronic medical record system, etc.

[2171] Prevention and health promotion

[2172] Step 1: User enters health data

[2173] Users enter their daily health data (diet, exercise, sleep, physical condition, etc.) into a health management app on their smartphone.

[2174] Input: Daily health data (diet, exercise, sleep, physical condition)

[2175] Output: Data entered into the health management app

[2176] Specific action: A user taps and swipes on a smartphone to enter data.

[2177] Step 2: The device sends the data to the server

[2178] The smartphone sends the entered health data to a server.

[2179] Input: Data entered into the health management app

[2180] Output: Health data sent to the server

[2181] Specific operation: The smartphone sends data to the server via Wi-Fi or mobile data communication.

[2182] Step 3: The server parses the data

[2183] The server analyzes the received health data using an AI algorithm, specifically the software Keras.

[2184] Input: Health data sent to the server

[2185] Output: Health risks and improvements as a result of the analysis

[2186] Specific operation: The server supplies data to the AI ​​model, which then calculates risks and areas for improvement.

[2187] Step 4: The server analyzes the emotional state

[2188] An emotion recognition engine recognizes the user's emotional state from the received data.

[2189] Input: Health data and related data

[2190] Output: Emotional state as a result of analysis

[2191] Specific operation: The server identifies the emotion using an emotion recognition algorithm.

[2192] Step 5: Servers adjust advice

[2193] The server adjusts health advice and improvement guidance based on the emotional state obtained from the emotion recognition engine.

[2194] Input: Emotion recognition results and health analysis results

[2195] Output: Tailored health advice and guidance

[2196] Specific behavior: The server generates advice and modifies the content according to the emotional state.

[2197] Step 6: The server sends the results to the device

[2198] The server then sends the generated health advice and improvement guidance to a smartphone.

[2199] Input: Tailored health advice and guidance

[2200] Output: Advice and guidance sent to your smartphone

[2201] Specific operation: The server encrypts the notification data and sends it to the smartphone.

[2202] Step 7: Your device will notify you of the results

[2203] The smartphone notifies the user of the advice and guidance received.

[2204] Input: Advice and guidance sent to your smartphone

[2205] Output: Advice and guidance to be given to the user

[2206] Specific action: The smartphone notifies the user via push notification or in-app message.

[2207] Utilizing medical data

[2208] Step 1: The hospital provides medical records and treatment data to the server

[2209] Multiple medical institutions provide medical records and treatment data to the server.

[2210] Input: medical records and treatment data

[2211] Output: Medical data stored on the server

[2212] Specific operation: The medical record system automatically transfers data to the server.

[2213] Step 2: The server parses the data

[2214] The server analyzes the received medical data using AI algorithms to identify treatment effects and trends, using software such as Apache Spark and H2O.ai.

[2215] Input: Medical data stored on the server

[2216] Output: Treatment effects and trend information as analysis results

[2217] Specific operation: The server supplies data to the AI ​​model and performs large-scale data analysis.

[2218] Step 3: Server generates feedback

[2219] The server generates feedback for new research concepts and new drug development based on the analysis results.

[2220] Input: Treatment effects and trend information as analysis results

[2221] Output: Feedback on research concepts and new drug development

[2222] Specific operation: The server formats the analysis results into a report format and generates the report.

[2223] Step 4: The server serves the results

[2224] The server provides the generated feedback to research institutions and drug development companies.

[2225] Input: Feedback on research concepts and new drug development

[2226] Output: Feedback provided to research institutions and drug development companies

[2227] What it does: The server encrypts the feedback and sends it to the relevant authority over a secure channel.

[2228] (Application example 2)

[2229] 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."

[2230] Current medical and health management systems do not adequately consider the psychological state of medical professionals and users, resulting in a lack of reduction in stress and emotional burden, and suboptimal treatment effectiveness and quality of health care. Furthermore, data analysis results are often significantly influenced by emotional states, making it difficult to provide appropriate diagnoses and treatment plans. Therefore, a system that can provide high-quality diagnoses, treatments, and health care recommendations while taking into account individual emotional states is needed.

[2231] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2232] In this invention, the server includes: means for receiving patient data entered by a medical professional; means including an artificial intelligence algorithm for analyzing the patient data and generating candidate diagnoses and treatment plans; means for presenting the generated candidate diagnoses and treatment plans to the medical professional; means including an emotion engine for recognizing the emotional state of the user; and means for adjusting the generated candidate diagnoses and treatment plans based on the emotion recognized by the emotion engine. This enables more flexible and appropriate diagnosis, treatment, and health management proposals that take the emotional state into consideration.

[2233] A "healthcare professional" is someone whose occupation regularly provides health care services to patients.

[2234] "Patient data" refers to data that includes medical information such as a patient's symptoms, vital signs, and medical records.

[2235] "Artificial intelligence algorithms" are algorithms for analyzing data and generating predictive models in computers.

[2236] "Candidate diagnoses" are multiple disease names and pathological conditions that are presumed based on patient data.

[2237] A "treatment plan" is a specific treatment method or protocol proposed for a diagnosed disease or condition.

[2238] A "user" is an individual who uses the system, and in this context refers primarily to a person receiving health care or medical services.

[2239] "Health data" refers to data that includes information about daily h...

Claims

1. means for receiving patient data entered by a healthcare professional; means including artificial intelligence algorithms for analyzing said patient data and generating candidate diagnoses and treatment plans; a means for presenting the generated candidate diagnoses and treatment plans to a medical professional; A system including:

2. means for receiving daily health data entered by a user; means for analyzing the health data and identifying health risks and areas for improvement, the means including an artificial intelligence algorithm; a means for notifying the user of the generated health advice or improvement guidance; The system of claim 1 , comprising:

3. a means for receiving medical records and treatment data from multiple hospitals; means including an artificial intelligence algorithm for analyzing the received data and identifying treatment effects and trends; A method to generate new research concepts and feedback for new drug development based on the analysis results and provide them to research institutions and pharmaceutical companies. The system of claim 1 , comprising:

Images