System

Abstract

To provide a system for improving treatment results of a patient.SOLUTION: Means for receiving, in real time, biological information and diagnosis results of a patient, storing the biological information and the diagnosis results in a cloud database, and centrally integrating the biological information and the diagnosis results with the cloud database, means for updating a patient profile in real time based on the integrated data, means for analyzing text data of an electronic medical record and extracting important medical information and patterns, means for adding an analysis result to a corresponding patient profile so that a medical professional can easily access the analysis result, and means for generating dashboard data based on information of the patient, A system comprising: means for transmitting to a terminal; means for visualizing dashboard data generated by the terminal and providing an interface for use by a medical professional; means for collecting up-to-date medical research and evidence from a cloud database; means for associating the collected medical information with patient data; and means for predicting future medical conditions and treatment effects based on historical data.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] In conventional medical data management systems, patients' vital signs and diagnostic results were scattered across multiple platforms, making it difficult to manage them centrally. Furthermore, it was difficult to extract and utilize important medical information from text data in electronic medical records, reducing the efficiency of diagnosis and treatment planning. Furthermore, quickly obtaining the latest medical research and evidence and linking it to patient data was also a challenge. These issues hindered medical professionals' ability to make quick and accurate decisions. [Means for solving the problem]

[0005] The present invention provides a system that receives patient biometric information and diagnostic results in real time and centrally integrates them into a cloud database. It also includes a means for using generative AI to analyze text data from electronic medical records and extract important medical information and patterns. The analysis results are added to patient profiles for easy access by medical professionals. It also provides an interface for generating dashboard data based on patient information and transmitting it to a terminal for visualization. It is also possible to collect the latest medical research and evidence from a cloud database and associate it with patient data. Finally, it provides a means for using generative AI to predict future disease conditions and treatment outcomes based on past data, generating a data report of the predicted results and displaying it to medical professionals. This enables medical professionals to make faster and more accurate diagnoses and treatment plans, improving patient outcomes.

[0006] "Patient's biological information" refers to medical data obtained from within the patient's body, such as heart rate, blood pressure, blood sugar level, and body temperature.

[0007] A "diagnosis" is a medical assessment or judgment made by a medical professional about a patient based on examination and observation.

[0008] A "cloud database" is a data storage system that stores data on a group of servers in remote locations and can be accessed via the Internet.

[0009] "Generative AI" refers to generative artificial intelligence used to analyze data and make predictions.

[0010] "Electronic medical record text data" refers to written data such as patient progress records, medical records, and test results recorded in the electronic medical record.

[0011] "Important medical information" refers to key data and findings that medical professionals need to make diagnoses and treatment decisions.

[0012] A "pattern" refers to a particular trend or regularity found in data or information.

[0013] "Dashboard data" is a set of information collected from multiple information sources and organized for visualization.

[0014] "Interface" refers to the operation screen and operation procedures used when inputting and outputting information between the system and the user.

[0015] "Latest medical research" refers to recent research findings, new technologies, and treatments related to medicine and healthcare.

[0016] "Evidence" refers to evidence and facts obtained based on medical or scientific grounds.

[0017] "Predictive analytics" is the act of extrapolating future events or outcomes based on past and current data.

[0018] A "data report" is a report that clearly organizes and describes the results of analysis and predictions. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The system of the present invention integrates various medical data and supports advanced medical analysis. The following describes embodiments of the present invention and specific examples thereof.

[0041] 1. Data Collection

[0042] The server receives real-time biological information from the patient's body (e.g., heart rate, blood pressure, blood glucose level, temperature, etc.) from IoT devices and medical institution systems. For example, when receiving data from a heart rate monitor or blood glucose level sensor, this data is sent through an API.

[0043] The server retrieves electronic medical record information from medical institutions' systems using HL7 or FHIR protocols, allowing it to centrally manage the necessary diagnostic results and case records in real time.

[0044] 2. Data Integration

[0045] The server integrates and stores the received vital signs and diagnostic results in a cloud database, which allows data in different formats to be organized and centralized based on patient IDs.

[0046] The server checks data integrity and updates existing patient profiles in real time, adding new data entries and linking them to historical data.

[0047] 3. Electronic Medical Record Analysis

[0048] The server uses generative AI to analyze the text data in the electronic medical records. For example, it uses natural language processing (NLP) technology to extract important information from the records, such as "the patient had diabetes in the past."

[0049] The server converts the analysis results into structured data and adds it to the corresponding patient profile, allowing medical professionals to quickly access the information they need.

[0050] 4. Dashboard display

[0051] The server generates dashboard data based on the patient's information and sends the compiled data set to the device, displaying, for example, the patient's real-time heart rate and past diagnostic data on a single screen.

[0052] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[0053] 5. Providing the latest medical information and evidence

[0054] The server collects the latest medical research and evidence from cloud databases, including accessing academic paper APIs and medical databases.

[0055] The server associates the collected medical information with the patient's data and presents applicable treatments and medical findings.

[0056] 6. Predictive analysis and reporting functions

[0057] The server uses generative AI based on past data to predict future disease conditions and treatment outcomes. For example, it analyzes blood glucose level data from the past year to predict future risk of diabetes complications.

[0058] The server generates a data report of the predicted results, sends it to the device, and displays it to medical professionals, who can use the predicted data to adjust treatment plans or intervene early.

[0059] A specific example would be a cardiologist simultaneously viewing information from a patient's heart rate monitor and electronic medical record to determine whether an abnormal heart rate is related to a previous diagnosis. Based on this information, the doctor can quickly make treatment decisions. Generative AI can also be used to predict future disease states and proactively plan patient care.

[0060] In this way, the present invention provides a system that greatly improves the efficiency and accuracy of medical care through medical data integration, real-time analysis, and intuitive information display.

[0061] The processing flow will be explained below.

[0062] Program processing flow

[0063] 1. Data collection and integration

[0064] Step 1:

[0065] The server receives the patient's vital signs (heart rate, blood sugar level, etc.) in real time from the IoT device.

[0066] The server connects to each device and uses an API or dedicated protocol to collect data.

[0067] Step 2:

[0068] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[0069] The server sends a request to the medical institution's system to obtain the required patient data.

[0070] Step 3:

[0071] The server stores the received data in a cloud database and centrally consolidates it.

[0072] The server unifies the data format and organizes each piece of data based on the patient ID.

[0073] 2. Electronic Medical Record Analysis

[0074] Step 1:

[0075] The server begins processing to analyze the text data in the electronic medical record using the generation AI.

[0076] The server preprocesses the text data and removes noise.

[0077] Step 2:

[0078] The server uses natural language processing (NLP) techniques to extract key information and convert it into structured data.

[0079] The server extracts information such as "past diabetes" from the electronic medical record and attaches appropriate tags.

[0080] Step 3:

[0081] The server adds and updates the patient profile with the analysis results.

[0082] The server integrates new medical information into existing profiles and maintains data integrity.

[0083] 3. Dashboard display

[0084] Step 1:

[0085] The server generates dashboard data based on real-time patient data and analysis results.

[0086] The server extracts the data sets and converts them into graphs and charts.

[0087] Step 2:

[0088] The server transmits the generated dashboard data to the terminal.

[0089] The server encrypts the data for transmission and ensures secure communication.

[0090] Step 3:

[0091] The terminal visually displays the received dashboard data.

[0092] The terminal provides an interface that allows the user to easily understand the data.

[0093] 4. Providing the latest medical information and evidence

[0094] Step 1:

[0095] The server accesses a cloud database to collect the latest medical research and evidence.

[0096] The server retrieves the latest information from academic paper APIs and databases.

[0097] Step 2:

[0098] The server integrates the collected information with relevant patient data.

[0099] The server updates patient profiles with the latest treatments and research findings.

[0100] Step 3:

[0101] The device will provide updates to medical professionals with this new information.

[0102] The terminal displays the latest evidence so that the user can easily refer to it.

[0103] 5. Predictive analysis and reporting functions

[0104] Step 1:

[0105] The server uses generative AI to perform predictive analysis based on historical data.

[0106] The server inputs time-series data into an AI model to predict future risks and treatment effects.

[0107] Step 2:

[0108] The server generates the prediction results as a data report.

[0109] The server generates a report containing the predicted results along with a risk assessment and recommended actions.

[0110] Step 3:

[0111] The server transmits the generated forecast report to the terminal.

[0112] The server encrypts and securely transmits the reports.

[0113] Step 4:

[0114] The terminal displays the received prediction report to the medical professional.

[0115] The terminal provides an interface for the user to adjust the treatment plan based on the predicted results.

[0116] Throughout the system, healthcare professionals can leverage real-time, integrated patient data to make more accurate decisions.

[0117] Example 1

[0118] 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."

[0119] Conventional medical data management systems have incomplete integration of patient biometric information and diagnostic results, making it difficult to update and analyze information in real time. Furthermore, important medical information cannot be quickly extracted when analyzing text data from electronic medical records, making it difficult for medical professionals to easily access the information they need. Furthermore, there are insufficient mechanisms for effectively utilizing the latest medical research and evidence in clinical settings, leading to inaccurate predictions of treatment effectiveness and future disease conditions. As a result, there are issues with delays in the formulation of treatment plans and early intervention.

[0120] 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.

[0121] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from the cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means for analyzing the medical information collected from the cloud database and suggesting treatments appropriate for the patient's condition; means for predicting trends in heart rate and blood sugar level based on past data; means for generating the prediction results as a data report and transmitting it to the terminal; and means for the terminal to visually display the data report so that it can be used by medical professionals. This will enable the integration of diverse medical data from different sources, updating and analyzing it in real time, and providing medical professionals with quick access to the information they need. It will also promote the use of the latest medical research and evidence, improving the accuracy of future disease predictions, allowing for the rapid development of treatment plans and early intervention.

[0122] "Biometric information" is data obtained directly from a patient's body, and examples include heart rate, blood pressure, blood sugar level, and body temperature.

[0123] "Diagnostic results" refers to the evaluations and findings obtained through examinations and medical treatment of patients by medical institutions, and specifically includes the contents of medical certificates and test reports.

[0124] A "cloud database" refers to a database service that can be accessed via the Internet and allows for the centralized management and storage of large amounts of data.

[0125] A "patient profile" is a data set that centrally manages individual information about a patient, including medical history, biometric information, and diagnostic results.

[0126] "Generative AI" refers to systems that use artificial intelligence techniques to generate and analyze data, and is particularly used for advanced pattern recognition and predictive analysis.

[0127] An "electronic medical record" refers to a system that electronically records and manages patient medical information at medical institutions, including medical records, prescriptions, test results, etc.

[0128] "Dashboard data" refers to a data set that integrates information obtained from multiple data sources and displays it visually.

[0129] An "interface" is a means of enabling interaction between a user and a system, and includes screens and operating means that users can use intuitively.

[0130] "Medical research" means scientific research activities in the field of medicine, including experiments and investigations aimed at developing new treatments and understanding disease states.

[0131] "Evidence" refers to scientific evidence supporting the effectiveness of a particular medical procedure or treatment.

[0132] "Trend forecasting" refers to an analytical method that predicts future fluctuations and patterns based on past data.

[0133] A "data report" is a report that includes analytical results and forecast information and provides a summary of data for a specific purpose.

[0134] The system of the present invention integrates various medical data and supports advanced medical analysis. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[0135] Data collection

[0136] First, the server has a means to receive patient biometric information and diagnostic results in real time. Specifically, biometric information such as the patient's heart rate, blood pressure, blood glucose level, and body temperature is obtained via an API from IoT devices such as heart rate monitors and blood glucose sensors. Electronic medical record information is also obtained from medical institution systems using the HL7 and FHIR protocols.

[0137] Example: A server receives data from a heart rate monitor every minute and stores it in a database. Electronic medical record data is retrieved periodically using the HL7 protocol.

[0138] Data Integration

[0139] The server stores the received vital signs and diagnostic results in a cloud database, centrally integrating them, organizing data in different formats while maintaining consistency based on patient IDs, and updating patient profiles in real time.

[0140] Example: The server integrates heart rate and blood glucose data into a cloud database and appends it to an existing patient profile.

[0141] Electronic medical record analysis

[0142] The server uses generative AI to analyze the text data in the electronic medical record. It uses natural language processing (NLP) techniques to extract important information and patterns from the records, convert them into structured data, and add them to the patient profile.

[0143] Example: The server inputs the prompt "Extract past diabetes history from the patient's electronic medical record data" into the generative AI model and adds the retrieved information to the patient profile.

[0144] Dashboard View

[0145] The server generates dashboard data based on the patient's information and sends it to the device, which displays a single screen that integrates the patient's real-time heart rate and past diagnostic data.

[0146] The terminal visually displays the received dashboard data and provides an interface for use by medical professionals.

[0147] Example: The server generates dashboard data that combines heart rate data and past diagnostic data and sends it to the device, which displays this data in a graph format, allowing medical professionals to understand the patient's condition at a glance.

[0148] Providing the latest medical information and evidence

[0149] The server collects the latest medical research and evidence from a cloud database, associates it with patient data, analyzes the collected medical information, and suggests treatments appropriate for the patient's condition.

[0150] Example: The server uses the academic journal API to collect the latest research data and associate it with patient profiles to suggest optimal treatment options.

[0151] Predictive analytics and reporting

[0152] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data. The prediction results are generated as a data report and sent to the device, which then visually displays the data report and makes it available to medical professionals.

[0153] Example: The server analyzes blood glucose data from the past year to predict future diabetes risk. A report of the prediction results is sent to the device, which medical professionals can use to adjust treatment plans.

[0154] Prompt Sentence Examples

[0155] "Extract past diabetes history from a patient's electronic medical record data."

[0156] "Based on your heart rate data from the past year, predict your heart rate trend for the next six months."

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1: Receiving data

[0159] The server receives patient biometric information (heart rate, blood pressure, blood glucose level, body temperature, etc.) from IoT devices via an API. The input is data from the heart rate monitor and blood glucose level sensor, and the output is biometric information stored in a cloud database.

[0160] As a specific example of operation, the server receives the patient's heart rate data every minute through the API and stores it in a cloud database.

[0161] Step 2: Obtain electronic medical record data

[0162] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. The input is HL7 or FHIR format data from the medical institution's system, and the output is electronic medical record information stored in a cloud database.

[0163] As a specific example of operation, the server periodically acquires electronic medical record data from medical institutions every day via a protocol and centrally manages it.

[0164] Step 3: Data Integration

[0165] The server integrates the received biometric information and diagnostic results into a cloud database. The input is the biometric information and electronic medical record information obtained in steps 1 and 2, and the output is unified patient profile data.

[0166] As a specific example of how it works, heart rate data and blood glucose data are integrated into a cloud database and organized based on patient ID.

[0167] Step 4: Data integrity check

[0168] The server checks the integrity of the data and adds new data entries to the existing patient profile. The input is the merged patient profile data and the output is the updated patient profile.

[0169] As a specific example of operation, new heart rate data and diagnostic results are compared with the existing profile, and consistency is confirmed before updating.

[0170] Step 5: Electronic medical record analysis

[0171] The server analyzes the text data of the electronic medical record using a generative AI model. The input is the text data of the electronic medical record, and the output is structured medical information.

[0172] As a specific example of operation, a prompt statement such as "Extract past diabetes history from the patient's electronic medical record data" is input into the generative AI model, and the extracted information is converted into structured data.

[0173] Step 6: Generate dashboard data

[0174] The server generates dashboard data based on the patient information and sends it to the terminal. The input is the updated patient profile data, and the output is the dashboard data for visualization.

[0175] As a specific example of operation, dashboard data that integrates heart rate data and past diagnostic data is generated and sent to the terminal.

[0176] Step 7: View the dashboard

[0177] The terminal visually displays the received dashboard data. The input is the dashboard data sent from the server, and the output is the visualized data as a user interface.

[0178] As a specific example of how it works, the device displays heart rate and past diagnostic data at a glance through graphs and charts.

[0179] Step 8: Providing the latest medical information and evidence

[0180] The server collects the latest medical research and evidence from a cloud database and associates it with patient data. The input is the latest medical research data and patient information, and the output is the associated treatment and medical knowledge.

[0181] As a specific example of how it works, the server uses an academic paper API to collect the latest research data, associates it with patient profiles, and presents applicable treatments.

[0182] Step 9: Predictive analytics

[0183] The server uses a generative AI model based on past data to predict future disease conditions and treatment outcomes. The input is past heart rate and blood sugar data, and the output is a data report of the predicted disease conditions and treatment outcomes.

[0184] As a specific example of how it works, it analyzes blood glucose data from the past year and predicts the risk of future diabetic complications.

[0185] Step 10: Generate and view data reports

[0186] The server generates a data report based on the prediction results and sends it to the terminal, which visually displays the data report and makes it available to medical professionals. The input is the prediction result data, and the output is the visualized data report.

[0187] In a specific example of operation, the server compiles the predicted data into a report and sends it to the device, which then visually displays the report in graphs and text format and allows medical professionals to adjust the treatment plan.

[0188] (Application example 1)

[0189] 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."

[0190] Conventional medical systems have difficulty receiving, integrating, and analyzing patients' vital signs and diagnostic results in real time. Furthermore, there are insufficient means to use generative AI to analyze text data from electronic medical records, extract important medical information, and provide it to medical professionals. In particular, brick-and-mortar stores lack real-time data acquisition and analysis methods for managing customers' health and recommending appropriate treatments. This makes it difficult to provide personalized health advice to customers.

[0191] 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.

[0192] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and sending the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from a cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means, which is installed in smart glasses, for acquiring a customer's biometric information in real time and displaying the analysis results; means for acquiring electronic medical record information using HL7 or FHIR protocols; means for displaying appropriate treatments and health management suggestions on the display of the smart glasses; and means for providing advice based on the latest medical research and evidence. This will enable physical stores to provide personalized health advice to customers in real time.

[0193] "Patient's biological information" refers to physiological data obtained from within the patient's body, such as heart rate, blood pressure, blood sugar level, and body temperature.

[0194] "Diagnosis results" are the results of professional diagnoses or tests conducted by a doctor or medical institution regarding a patient's medical condition or health status.

[0195] A "cloud database" is a database service provided by a remote server that allows data to be stored, managed, and accessed over the Internet.

[0196] A "patient profile" is a set of information that represents the health status of an individual patient, constructed based on medical data such as the patient's biometric information, diagnosis results, and electronic medical records.

[0197] "Generative AI" is an artificial intelligence technique that can generate new information and insights using large datasets and machine learning algorithms.

[0198] An "electronic medical record" is a system that electronically records and manages a patient's medical history, prescriptions, test results, etc.

[0199] "Dashboard data" is a data set that visually organizes patient biometric information and diagnostic results, and displays them in a way that can be understood at a glance.

[0200] A "terminal" is a device that a user operates, and in this case refers to a PC, smartphone, tablet, etc.

[0201] An "interface" is a software or hardware component that provides a screen or means of operation for a user to interact with a system.

[0202] "Medical research" is scientific research conducted with the goal of advancing medical care, understanding disease, and developing treatments.

[0203] "Evidence" refers to data and research results that provide scientific evidence used in the medical field.

[0204] "Predicting future disease states and treatment outcomes" is the process of using past data and generative AI to predict a patient's future health condition and treatment outcomes.

[0205] "Smart glasses" are a wearable eyeglass-type device equipped with a display that can display data in real time and provide information to users.

[0206] The "HL7 and FHIR protocols" are standards for electronically exchanging medical information and are formats and communication protocols that ensure interoperability of medical data.

[0207] "Health management suggestions" involve providing specific advice and recommendations on lifestyle changes, treatment options, etc. to improve a patient's health.

[0208] The system according to the present invention integrates various medical data and realizes advanced medical analysis. Specific embodiments of the present invention will be described below.

[0209] 1. Hardware Configuration

[0210] The system includes the following hardware:

[0211] Server: The central component responsible for data collection, integration, analysis, and cloud database management.

[0212] Smart glasses: A wearable device that allows users to check data in real time and receive appropriate health advice.

[0213] IoT devices: These devices collect patients' vital signs, such as heart rate, blood pressure, and blood sugar levels, in real time.

[0214] Device: The device that provides the data visualization or interface, including computers, smartphones, tablets, etc.

[0215] 2. Software Configuration

[0216] The system uses the following software:

[0217] Python: The language on which the program is based.

[0218] OpenAI® API: Generative AI models (e.g., GPT-4®) used for natural language processing (NLP).

[0219] Requests (Python library): A library for retrieving data from APIs.

[0220] HL7 / FHIR API: A standard protocol for obtaining electronic medical record information.

[0221] 3. Data Collection and Integration

[0222] The server receives patient biometric information from IoT devices in real time and retrieves electronic medical record information from medical institutions using HL7 and FHIR protocols. These data are integrated and stored in a cloud database, and patient profiles are updated in real time.

[0223] 4. Data Analysis

[0224] The server uses generative AI to parse the text data in the electronic medical record to extract important medical information and patterns, which are then added to the corresponding patient profile and made easily accessible to medical professionals.

[0225] 5. Dashboard generation and display

[0226] The server generates dashboard data based on the patient's information and sends it to the device. The device visualizes the dashboard data and provides an interface for medical professionals to use. The smart glasses collect the patient's biometric information in real time and display the analysis results to provide appropriate health advice to the patient.

[0227] 6. Providing the latest medical information and evidence

[0228] The server collects the latest medical research and evidence from a cloud database and associates the collected medical information with patient data, thereby suggesting applicable treatments and medical findings.

[0229] 7. Predictive Analytics and Reporting

[0230] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data, and the results are generated as a data report, which is sent to the device and displayed to medical professionals.

[0231] Specific examples

[0232] For example, when a customer visits a pharmacy, the smart glasses can be used to check their heart rate and past diagnostic information, and provide them with on-the-spot medication and health advice.

[0233] Prompt Sentence Examples

[0234] Patient data: {"physiological_data": {"heart_rate": 85, "blood_pressure": "120 / 80", "blood_sugar": 110}, "medical_records": {"condition": "hypertension", "medication": ["Drug A", "Drug B"]}}.

[0235] Provide a summary and recommendations.

[0236] This will enable physical stores to provide personalized health advice to customers in real time.

[0237] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0238] Step 1:

[0239] Collecting patient vital signs in real time

[0240] The server receives real-time biometric information such as heart rate, blood pressure, and blood sugar levels from IoT devices. Specifically, it periodically acquires data sent from IoT devices using an API and stores it in a cloud database.

[0241] Input: Biometric data from IoT devices

[0242] Output: Biometric information stored in a cloud database

[0243] Step 2:

[0244] Obtain electronic medical record information

[0245] The server retrieves electronic medical record information from medical institutions' systems using the HL7 or FHIR protocol. Specifically, based on the specified protocol, it extracts information such as patient diagnosis results and past medical history from the medical institution's database and integrates it into a cloud database.

[0246] Input: Electronic medical record information from medical institutions

[0247] Output: Electronic medical record information stored in a cloud database

[0248] Step 3:

[0249] Data integration and profile updates

[0250] The server integrates the received vital signs and electronic medical records into a cloud database and updates patient profiles in real time. Specifically, it organizes different types of data for each patient and adds them to the existing data profile.

[0251] Input: Biometric information and electronic medical record information

[0252] Output: Updated patient profile

[0253] Step 4:

[0254] Using generative AI to analyze text data from electronic medical records

[0255] The server uses generative AI (e.g., OpenAI's GPT-4) to analyze the text data of the electronic medical record and extract important medical information and patterns. Specifically, the server supplies the text data of the electronic medical record and obtains the extracted important information as the output of the AI ​​model.

[0256] Input: Text data from electronic medical records

[0257] Output: Extracted important medical information

[0258] Step 5:

[0259] Adding analysis results to patient profiles

[0260] The server adds the key medical information extracted by the generative AI to the corresponding patient profile, making it easily accessible to medical professionals.

[0261] Input: Extracted vital medical information

[0262] Output: Updated patient profile

[0263] Step 6:

[0264] Generate dashboard data and send it to the device

[0265] The server generates dashboard data based on the patient's information and sends it to the terminal. Specifically, it extracts the necessary data from the patient profile, converts it into a visually easy-to-understand format, and generates the dashboard.

[0266] Input: Patient Profile

[0267] Output: Generated dashboard data

[0268] Step 7:

[0269] The device visualizes the dashboard data and provides it as an interface.

[0270] The device visualizes the transmitted dashboard data and provides a user-friendly interface for medical professionals, displaying key patient information in the form of graphs and charts.

[0271] Input: Submitted dashboard data

[0272] Output: Visualized dashboard

[0273] Step 8:

[0274] Collect the latest medical research and evidence and link it to patient data

[0275] The server collects the latest medical research and evidence from a cloud database and associates it with patient data, specifically retrieving the latest information from academic paper databases and medical information platforms, and reflecting it in patient profiles.

[0276] Input: Latest medical research and evidence

[0277] Output: Updated patient profile

[0278] Step 9:

[0279] Using generative AI to predict future disease states and treatment outcomes

[0280] The server uses generative AI based on past data to predict future medical conditions and treatment outcomes. Specifically, it analyzes past biometric information and diagnostic result data to predict future health risks and treatment outcomes.

[0281] Input: Past vital signs and diagnostic results data

[0282] Output: Predicted future disease status and treatment effects

[0283] Step 10:

[0284] The application installed on the smart glasses collects the customer's biometric information in real time and displays the analysis results.

[0285] The application installed on the smart glasses collects the customer's biometric information in real time and displays the results analyzed by the generative AI. Specifically, the glasses display shows treatment and health management suggestions, providing appropriate advice to the user.

[0286] Input: Customer's biometric information and the analysis results of the generated AI

[0287] Output: Health advice displayed on smart glasses

[0288] Step 11:

[0289] Displaying appropriate treatment and health management suggestions on the smart glasses display

[0290] The smart glasses will then display appropriate treatment and health management suggestions based on the analysis results, allowing users to receive specific advice in real time.

[0291] Input: Analysis results

[0292] Output: Displayed treatment and health management suggestions

[0293] Step 12:

[0294] Providing the latest medical research and evidence-based advice

[0295] The server provides users with appropriate advice based on the latest medical research and evidence collected, specifically suggesting optimal treatments and health management based on the latest medical information linked to patient data.

[0296] Input: Latest medical research and evidence

[0297] Output: Advice provided

[0298] 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.

[0299] The system of the present invention not only integrates, analyzes, and visualizes medical data, but also recognizes the user's emotions and adjusts the interface based on those emotions to provide more optimal medical support. The following describes embodiments of the present invention and specific examples thereof.

[0300] 1. Data Collection

[0301] The server receives patient vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time from IoT devices, which transmit data using APIs or dedicated protocols.

[0302] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol and obtains the necessary diagnostic results and case notes.

[0303] 2. Data Integration

[0304] The server integrates and stores the received biometric information and diagnostic results in a cloud database, standardizing the data format and organizing each piece of data based on patient ID.

[0305] The server checks the integrity of the data and updates existing patient profiles in real time.

[0306] 3. Electronic Medical Record Analysis

[0307] The server uses generative AI to analyze the text data in the electronic medical records and extract important information, such as "past diabetes," using natural language processing (NLP) technology to extract information and convert it into structured data.

[0308] The server adds and updates the patient profile with the analysis results, allowing medical professionals to quickly access the information they need.

[0309] 4. Dashboard display

[0310] The server generates dashboard data based on the patient's information and sends the compiled data set to the terminal.

[0311] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[0312] 5. Providing the latest medical information and evidence

[0313] The server collects the latest medical research and evidence from a cloud database, obtains the latest information from academic paper APIs and databases, and reflects it in patient data.

[0314] The device provides medical professionals with the latest collected information to aid in diagnosis and treatment planning.

[0315] 6. Predictive analysis and reporting functions

[0316] The server uses generative AI to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes, and generates a data report of the results, which is sent to the device and displayed to medical professionals.

[0317] The device provides an interface for adjusting treatment plans and conducting early intervention based on the received predictive report.

[0318] 7. Incorporating an Emotional Engine

[0319] The server incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state, for example, recognizing emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis.

[0320] The server then reflects the emotional data obtained from the emotion engine in the dashboard data, allowing medical professionals to make comprehensive judgments that take into account their own emotional state.

[0321] The device adjusts the interface display and operation based on the user's emotions: for example, if a medical professional is feeling highly stressed, the system will automatically change the screen layout and highlight important information.

[0322] Examples:

[0323] The server receives data in real time from heart rate monitors and blood glucose sensors, stores it in a cloud database, and consolidates it.

[0324] The server analyzes electronic medical records to determine whether the patient has had diabetes in the past and adds this information to the patient profile.

[0325] The device generates a dashboard that visually displays the patient's overall health status and diagnostic results.

[0326] The server uses an emotion engine to analyze the emotional state of the medical professional as they view the dashboard: for example, if the professional is feeling anxious, the system will highlight important information more prominently.

[0327] The device adjusts the interface display based on the patient's emotional state, helping medical professionals make efficient decisions.

[0328] The entire system empowers healthcare professionals with real-time, integrated patient data for fast and accurate decision-making in an interface optimized for the user's emotional state.

[0329] The processing flow will be explained below.

[0330] Program processing flow

[0331] 1. Data collection and integration

[0332] Step 1:

[0333] The server receives the patient's vital signs (heart rate, blood pressure, blood sugar level, etc.) in real time from the IoT device.

[0334] The server collects data from each device through an API and checks the integrity of the data received.

[0335] Step 2:

[0336] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[0337] The server sends the request, extracts the corresponding data, and converts the format.

[0338] Step 3:

[0339] The server integrates and stores the received biometric information and electronic medical record data in a cloud database.

[0340] The server organizes each piece of data based on the patient ID and creates a database entry for centralized management.

[0341] 2. Electronic Medical Record Analysis

[0342] Step 1:

[0343] The server analyzes the text data in the electronic medical records using generative AI (natural language processing technology).

[0344] The server preprocesses the text data of the electronic medical records, removes noise, and performs morphological analysis.

[0345] Step 2:

[0346] The server uses generative AI to extract important medical information and patterns.

[0347] The server detects important information, such as "past diabetes," and tags and converts that information into structured data.

[0348] Step 3:

[0349] The server adds the analysis results to the patient profile and integrates them with existing data.

[0350] The server updates the database and adds the extracted medical information.

[0351] 3. Dashboard display

[0352] Step 1:

[0353] The server creates dashboard data based on the patient's real-time biometric information and analysis results.

[0354] The server transforms the data into graphs and charts and generates a data set for the dashboard.

[0355] Step 2:

[0356] The server transmits the generated dashboard data to the terminal.

[0357] The server encrypts the data to ensure secure transmission and transmits it using HTTPS.

[0358] Step 3:

[0359] The terminal visually displays the received dashboard data.

[0360] The device uses graphs and charts to make the information easy for medical professionals to understand.

[0361] 4. Providing the latest medical information and evidence

[0362] Step 1:

[0363] The server accesses a cloud database to collect the latest medical research and evidence.

[0364] The server sends requests to retrieve information from academic paper APIs and medical databases.

[0365] Step 2:

[0366] The server integrates the collected medical information with the patient's data.

[0367] The server adds the latest evidence to the patient's profile and suggests applicable treatments.

[0368] Step 3:

[0369] The terminal displays an interface that provides the medical professional with the latest collected information.

[0370] The terminal provides visualization options where appropriate to allow the user to easily view the new information.

[0371] 5. Predictive analysis and reporting functions

[0372] Step 1:

[0373] The server uses generative AI to perform predictive analysis based on past data.

[0374] The server inputs time-series data into an AI model to predict future disease conditions and treatment outcomes.

[0375] Step 2:

[0376] The server generates the prediction results as a data report.

[0377] The server generates a report containing the predicted results, risk assessment, and recommended actions.

[0378] Step 3:

[0379] The server transmits the generated data report to the terminal.

[0380] The server encrypts the data reports and transmits them over a secure channel.

[0381] Step 4:

[0382] The terminal displays the received prediction report to the medical professional.

[0383] The terminal provides an interface that allows the user to review predicted results and adjust the treatment plan.

[0384] 6. Use of Emotion Engines

[0385] Step 1:

[0386] The terminal activates an emotion engine to recognize the emotions of the user (medical professional).

[0387] The device recognizes the user's facial expressions and analyzes their voice to determine their emotional state.

[0388] Step 2:

[0389] The server receives the emotion data obtained from the emotion engine and reflects it in the dashboard data.

[0390] The server analyzes and prepares the necessary data to adjust the interface according to the user's emotional state.

[0391] Step 3:

[0392] The device adjusts the interface display and operation method based on the emotional state.

[0393] If the user is feeling stressed, the device will highlight important information or change the screen layout.

[0394] Examples:

[0395] The server receives data in real time from the heart rate monitor and blood glucose sensor, stores it in a cloud database, and consolidates it.

[0396] The server adds information extracted from the electronic medical record, such as "past diabetes," to the patient profile and updates the database.

[0397] The device generates a dashboard that visually displays the patient's overall health status and diagnostic results.

[0398] The server uses an emotion engine to analyze the emotional state of the medical professional as he or she reviews the dashboard.

[0399] If the user feels anxious, the device will automatically highlight important information and change the screen layout to optimize the user experience.

[0400] This will enable healthcare professionals to make faster and more accurate decisions through integrated medical data and an optimized user interface.

[0401] Example 2

[0402] 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."

[0403] Traditional medical systems do not integrate patients' vital signs and diagnostic results in real time, making it difficult for medical professionals to access information quickly. They also do not take into account the patient's emotional state, potentially resulting in a decline in the quality of medical care. Furthermore, it is difficult to predict future disease conditions and treatment outcomes, limiting diagnostic and treatment planning.

[0404] 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.

[0405] In this invention, the server includes: means for receiving patient biometric information and diagnostic results in real time; means for storing and centrally integrating the patient biometric information and diagnostic results in a cloud database; means for updating patient profiles in real time based on the integrated data; means for analyzing text data from electronic medical records using a generative AI to extract important medical information and patterns; means for adding the analysis results to the corresponding patient profile for easy access by medical professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from a cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment outcomes based on past data using a generative AI; means for recognizing and analyzing a user's emotional state and reflecting the emotional data in the interface; and means for adjusting the interface based on the user's emotional state. This enables centralized management of patient biometric information and diagnostic results, real-time information updates, and predictive analysis based on patient data. Furthermore, adjusting the interface to take the user's emotional state into account is expected to improve the quality of medical care.

[0406] "Patient's vital signs" refers to data that indicates the patient's physical condition, such as heart rate, blood pressure, and blood sugar level.

[0407] "Diagnosis" means the result of a diagnosis made by a medical professional and is information related to a patient's medical condition and treatment plan.

[0408] "Cloud database" refers to a database stored on a remote server accessible via the Internet.

[0409] "Integrating" refers to the process of combining data collected from different sources into one database.

[0410] A "patient profile" refers to a data set that compiles medical information about an individual patient, such as biometric information, diagnostic results, and treatment history.

[0411] "Generative AI" refers to artificial intelligence technology that uses machine learning and deep learning algorithms to analyze data and generate new information and predictions.

[0412] "Electronic medical record text data" refers to the text information of an electronically recorded medical record.

[0413] "Dashboard Data" refers to data that has been processed to visually display consolidated patient information.

[0414] "Terminal" refers to a device, such as a text editor, with computer graphics used by a healthcare professional to view and manipulate information.

[0415] "Interface" refers to the screen and operation method used by users to operate software or hardware.

[0416] "The latest medical research and evidence" refers to medical information and evidence obtained through recent scientific research and clinical trials.

[0417] "Predictive analytics" refers to the process of predicting and analyzing future disease conditions and treatment outcomes based on past data.

[0418] "Emotion engine" refers to software technology for recognizing and analyzing a user's emotional state from their facial expressions and voice.

[0419] "Interface adjustment" refers to the process of changing the operating screen and display content based on the user's emotional state.

[0420] The system of the present invention receives, integrates, analyzes, and visualizes the patient's vital signs and diagnostic results in real time, and also recognizes the user's emotions and adjusts the interface to provide more optimal medical support. Specific embodiments of the present invention are described below.

[0421] Data collection

[0422] The server receives the patient's vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time. This data is sent from IoT devices using APIs or dedicated protocols. For example, when receiving data from a heart rate monitor or blood glucose sensor, the server obtains heart rate data of 70 bpm via an HTTP request and stores it in a cloud database.

[0423] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. This allows it to collect diagnosis results and case records. For example, it retrieves information such as "Diabetes: positive" from "Patient ID: 1234" via the FHIR protocol.

[0424] Data Integration

[0425] The server integrates the collected vital signs and diagnostic results into a cloud database. The data format is standardized and each data item is organized based on the patient ID. For example, the data is stored in the database in a standardized JSON format as "Patient ID: 1234, heart_rate: 70 bpm, blood_pressure: 120 / 80, diabetes_history: positive."

[0426] The server checks the data for consistency and updates the patient profile in real time: for example, if the heart rate is an unrealistic value (such as 0 bpm or 300 bpm), the data is invalidated.

[0427] Electronic medical record analysis

[0428] The server uses a generative AI model to analyze the text data in the electronic medical record and extract important information. It uses natural language processing (NLP) technology to extract information such as "past diabetes" and convert it into structured data. For example, text such as "The patient had diabetes in the past" is converted into structured data as "diabetes_history: positive."

[0429] The server adds the extracted information to and updates the patient profile, allowing medical professionals to quickly access the information they need.

[0430] Dashboard View

[0431] The server generates dashboard data based on the patient information and sends it to the terminal in a format such as "Patient ID: 1234, chart_data: ...".

[0432] The device visually displays the received dashboard data, allowing medical professionals to see important information at a glance through graphs and charts. For example, it generates graphs such as "Heart Rate Trend" and "Blood Glucose Chart" and updates the dashboard.

[0433] Providing the latest medical information and evidence

[0434] The server collects the latest medical research and evidence from a cloud database. It retrieves the latest information from academic paper APIs and databases and reflects it in patient data. For example, it searches the database with the query "latest diabetes treatments" to retrieve the latest paper information.

[0435] The device then provides medical professionals with the latest information it has collected to aid in diagnosis and treatment planning, for example by notifying them that "five new diabetes treatments have been discovered."

[0436] Predictive analytics and reporting

[0437] The server uses the generative AI model to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes. For example, it sends a query to the generative AI model, such as "Predict blood glucose fluctuations over the next six months for patient ID: 1234," and obtains the predicted results.

[0438] The server generates a data report of the prediction results and sends it to the device. Medical professionals can use this information to adjust their diagnosis and treatment plan. For example, a "blood glucose prediction report for the next six months" can be generated in PDF format and sent to the device.

[0439] Incorporating an emotion engine

[0440] The server uses an emotion engine to analyze the user's emotional state. For example, it recognizes emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis. It analyzes facial expression data and voice data acquired through a camera and microphone and determines the user's "stress level: high."

[0441] The server reflects the emotional data in the dashboard data, which enables comprehensive judgment. For example, data such as "emotional state: high stress level" can be integrated into the dashboard data.

[0442] The device adjusts the interface display based on the user's emotions. For example, if a medical professional is feeling highly stressed, important information will be highlighted. Based on the emotional data, important information will be highlighted with a red frame.

[0443] Prompt Sentence Examples

[0444] Use the following parameters to generate dashboard content that can be easily understood by healthcare professionals.

[0445] Parameters: Patient ID, heart rate, blood pressure, blood glucose, past medical history, latest diagnosis

[0446] Generative AI models should use natural language processing to extract key information, such as "past diabetes," and provide it as structured data, and also adapt the interface based on the user's emotional state.

[0447] The entire system empowers healthcare professionals with real-time, integrated patient data to make fast and accurate decisions with an interface optimized for the user's emotional state.

[0448] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0449] Step 1: Data collection

[0450] The server receives real-time patient vital signs from IoT devices such as heart rate monitors and blood glucose sensors, which are transmitted using APIs and proprietary protocols.

[0451] Input: Biometric information such as heart rate, blood pressure, and blood sugar level

[0452] Data processing: The server converts the received data into an appropriate format and stores it in a cloud database.

[0453] Output: Formatted biometric data

[0454] Specific operation:

[0455] The server receives an HTTP request from the heart rate monitor and stores the heart rate of 70 bpm in a cloud database in JSON format.

[0456] Step 2: Obtaining electronic medical record information

[0457] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[0458] Input: Patient ID, electronic medical record information

[0459] Data processing: The server analyzes the acquired medical record information, extracts diagnostic results and case records, and stores them in a database.

[0460] Output: Analyzed medical record information

[0461] Specific operation:

[0462] The server queries the diagnosis results for "Patient ID: 1234" using the FHIR protocol and integrates the obtained "Diabetes: positive" information into the database.

[0463] Step 3: Data Integration

[0464] The server integrates the biometric information and diagnostic results into a cloud database.

[0465] Input: Biometric information, diagnosis results

[0466] Data processing: The server standardizes the data format and organizes each data based on the patient ID.

[0467] Output: Unified patient data

[0468] Specific operation:

[0469] The server stores the data in a database in the format "Patient ID: 1234, heart_rate: 70 bpm, blood_pressure: 120 / 80, diabetes_history: positive".

[0470] Step 4: Check data integrity

[0471] The server checks the integrity of the merged data and eliminates inconsistent data.

[0472] Input: Unified patient data

[0473] Data calculation: The server checks the data format and outliers.

[0474] Output: consistent data

[0475] Specific operation:

[0476] The server detects unrealistic heart rate data such as 0 bpm or 300 bpm and rejects it as inconsistent data.

[0477] Step 5: Electronic medical record analysis

[0478] The server uses a generative AI model to analyze the text data in the electronic medical record and extract key information.

[0479] Input: Electronic medical record text data

[0480] Data calculation: Using natural language processing technology, information such as "past diabetes" is extracted from text and converted into structured data.

[0481] Output: Structured important information

[0482] Specific operation:

[0483] The server converts text such as "The patient had diabetes in the past" as "diabetes_history: positive".

[0484] Step 6: Update the patient profile

[0485] The server adds and updates the patient profile with the analysis results.

[0486] Input: Structured critical information

[0487] Data calculations: Add new information to an existing patient profile.

[0488] Output: Updated patient profile

[0489] Specific operation:

[0490] The server adds the "Past History of Diabetes" data to the profile and updates it as "Patient ID: 1234, diabetes_history: positive".

[0491] Step 7: Generate dashboard data

[0492] The server generates dashboard data based on the patient's information and sends it to the terminal.

[0493] Input: Patient profile data

[0494] Data processing: Converting data into a visualizable format.

[0495] Output: Dashboard data

[0496] Specific operation:

[0497] The server sends the dashboard data to the terminal in the format "Patient ID: 1234, chart_data: ...".

[0498] Step 8: View the Dashboard

[0499] The terminal visually displays the received dashboard data.

[0500] Input: Dashboard data

[0501] Data processing: Display the data using visualization tools.

[0502] Output: Visualized information

[0503] Specific operation:

[0504] The device generates graphs such as "heart rate trend" and "blood glucose chart" and updates the dashboard.

[0505] Step 9: Gather the latest medical information

[0506] The server collects the latest medical research and evidence from a cloud database.

[0507] Input: Query, medical information database

[0508] Data Calculation: The server uses the specified query to extract the latest information.

[0509] Output: Latest medical information

[0510] Specific operation:

[0511] The server searches the database using the keyword "latest diabetes treatments" to obtain new paper information.

[0512] Step 10: Provide medical information

[0513] The device displays the latest collected medical information to medical professionals to aid in diagnosis and treatment planning.

[0514] Input: Latest medical information

[0515] Data processing: Converting information into a user-friendly format for display.

[0516] Output: Medical information displayed

[0517] Specific operation:

[0518] The device notifies the user that "five new diabetes treatments have been discovered" and displays details.

[0519] Step 11: Perform predictive analysis

[0520] The server uses a generative AI model to perform predictive analysis based on historical data.

[0521] Input: Historical Patient Data

[0522] Data calculation: Predicting future disease conditions and treatment outcomes from past data.

[0523] Output: Prediction result data

[0524] Specific operation:

[0525] The server sends a query to the generative AI model saying, "Predict blood glucose fluctuations for the next 6 months for patient ID: 1234" and obtains the prediction results.

[0526] Step 12: Generate forecast data reports

[0527] The server generates a data report based on the prediction results and sends it to the terminal.

[0528] Input: Prediction result data

[0529] Data processing: Compile the prediction results into a report format.

[0530] Output: Data report

[0531] Specific operation:

[0532] The server generates a "blood glucose prediction report for the next six months" in PDF format and sends it to the terminal.

[0533] Step 13: Emotion Engine Analysis

[0534] The server uses an emotion engine to analyze the user's emotional state.

[0535] Input: facial expression and voice data from camera and microphone

[0536] Data Computation: Analyze emotional states using an emotion engine.

[0537] Output: Emotion data

[0538] Specific operation:

[0539] The server analyzes facial expression and voice data acquired through the camera and microphone and determines the "stress level: high."

[0540] Step 14: Reflecting Emotional Data

[0541] The server reflects the emotion data on the dashboard.

[0542] Input: Emotion data

[0543] Data processing: Integrating sentiment data into dashboard data.

[0544] Output: Dashboard data after reflecting emotions

[0545] Specific operation:

[0546] The server consolidates and displays data such as "Emotional state: High stress level" on a dashboard.

[0547] Step 15: Adjusting the Interface

[0548] The terminal adjusts the display content of the interface based on the user's emotional state.

[0549] Input: Dashboard data after reflecting emotions

[0550] Data processing: Adjusting the interface, such as highlighting important information.

[0551] Output: Adjusted interface

[0552] Specific operation:

[0553] If the device determines that your stress level is high, it will highlight important information in a red frame.

[0554] (Application example 2)

[0555] 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."

[0556] Current medical support systems lack the ability to not only integrate and analyze patients' biometric information and diagnostic results, but also adjust their interfaces based on the user's emotional state. This makes it difficult for medical professionals to make quick and accurate decisions, even in stressful situations. Furthermore, there is a need for an efficient way to display important information in emergency situations. To solve these issues, a mechanism is needed to collect user emotional data in real time and adjust the interface appropriately.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving patient biometric information and diagnostic results in real time, means for storing and centrally integrating the patient biometric information and diagnostic results in a cloud database, means for updating the patient profile in real time based on the integrated data, means for analyzing text data in the electronic medical record using a generating AI to extract important medical information and patterns, means for adding the analysis results to the corresponding patient profile so that medical professionals can easily access it, means for generating dashboard data based on the patient information and transmitting the dashboard data to a terminal, means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals, means for collecting the latest medical research and evidence from a cloud database, means for associating the collected medical information with patient data, means for predicting future medical conditions and treatment effects based on past data using a generating AI, means for collecting user emotional data in real time, and means for adjusting the interface based on the collected emotional data. This enables appropriate information display and interface adjustment according to the user's emotional state, enabling medical professionals to make quick and accurate decisions even in stressful situations.

[0558] "Biometric information" refers to data on a patient's physical condition, such as heart rate, blood pressure, and blood sugar level, obtained in real time.

[0559] "Diagnosis results" are data obtained as a result of a diagnosis made to a patient by a medical institution, and are information recorded in an electronic medical record.

[0560] A "cloud database" refers to data stored on remote servers accessible over the internet, and is often used to store medical information.

[0561] A "patient profile" is an integrated data set that includes a patient's biometric information, diagnostic results, and medical history.

[0562] "Generative AI" is a type of artificial intelligence technology that refers to algorithms that analyze data and make predictions using models trained for specific purposes.

[0563] An "electronic medical record" is a patient's medical record stored in digital format, and refers to a record of diagnosis and treatment within a medical institution.

[0564] "Dashboard data" is summary data configured to visually display information aggregated from multiple data sources.

[0565] A "terminal" is a device that a user uses to check data or information, and includes a PC, tablet, smartphone, etc.

[0566] "State-of-the-art medical research" refers to ongoing or recently completed research and results in the field of medicine.

[0567] "Evidence" refers to scientific evidence that serves as the basis for medical treatment and diagnosis in the medical field.

[0568] "Emotion data" is information about the emotional state extracted from the user's facial expressions, voice, behavior, etc.

[0569] "Interface adjustment" refers to changing the display and operation method of the system used by the user based on the user's emotional state.

[0570] To implement this invention, the following system configuration is required: This system integrates the patient's biometric information and diagnostic results, and incorporates the user's emotional data to assist medical professionals in making quick and effective decisions.

[0571] 1. Data collection and integration

[0572] The server receives patient vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time from IoT devices, which transmit data using APIs or dedicated protocols.

[0573] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol and receives the necessary diagnostic results and case notes.

[0574] The server integrates and stores the received biometric information and diagnostic results in a cloud database, standardizing the data format and organizing each piece of data based on patient ID.

[0575] 2. Electronic Medical Record Analysis

[0576] The server uses generative AI to analyze the text data in the electronic medical records and extract important information, such as "past diabetes," using natural language processing (NLP) technology to extract information and convert it into structured data.

[0577] 3. Dashboard display

[0578] The server generates dashboard data based on the patient's information and sends the compiled data set to the terminal.

[0579] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[0580] 4. Providing the latest medical information and evidence

[0581] The server collects the latest medical research and evidence from a cloud database, obtains the latest information from academic paper APIs and databases, and reflects it in patient data.

[0582] The device provides medical professionals with the latest collected information to aid in diagnosis and treatment planning.

[0583] 5. Predictive analytics and reporting

[0584] The server uses generative AI to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes, and generates a data report of the results, which is sent to the device and displayed to medical professionals.

[0585] 6. Incorporating an Emotional Engine

[0586] The server incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state, for example, recognizing emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis.

[0587] The device adjusts the interface and controls based on the user's emotions: if a medical professional is feeling stressed, the system automatically changes the screen layout and highlights important information.

[0588] Specific examples

[0589] For example, if a medical professional is stressed during an emergency, the displayed dashboard data will automatically highlight important information, allowing for a quicker response, while if the medical professional remains calm, the normal interface will be displayed.

[0590] Prompt Sentence Examples

[0591] Please provide a concrete example of a system that collects user sentiment data in real time and adjusts the interface accordingly. Also explain how the data is stored with a timestamp and used to generate dashboard data.

[0592] This system configuration allows healthcare professionals to make fast and accurate decisions using real-time integrated patient data and an interface that adapts to the user's emotional state.

[0593] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0594] Step 1:

[0595] Data collection

[0596] The server receives the patient's vital signs (heart rate, blood pressure, blood glucose level, etc.) from the IoT device in real time. The data is sent via API or dedicated communication protocol. The input is the vital signs from the IoT device, and the output is the raw data for integration.

[0597] Step 2:

[0598] Acquisition of electronic medical record information

[0599] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. The input is diagnosis results and case notes from the medical institution's system, and the output is raw data for storing this information.

[0600] Step 3:

[0601] Data Integration and Storage

[0602] The server integrates and stores the received biometric information and diagnostic results in a cloud database. The data format is standardized and each data item is organized based on the patient ID. The input is raw data of biometric information and diagnostic results, and the output is integrated patient profile data.

[0603] Step 4:

[0604] Electronic medical record analysis

[0605] The server uses generative AI to analyze the text data in the electronic medical record. It uses natural language processing (NLP) technology to extract information such as "past diabetes" and convert it into structured data. The input is the text data of the raw medical record, and the output is the analyzed structured data.

[0606] Step 5:

[0607] Generate dashboard data

[0608] The server generates dashboard data based on patient information. The generated data is sent to the terminal. The input is the integrated patient profile data and analysis results, and the output is the dashboard data for visualization.

[0609] Step 6:

[0610] Dashboard View

[0611] The terminal visually displays the received dashboard data, allowing medical professionals to see important information at a glance through graphs and charts. The input is the dashboard data sent from the server, and the output is the visualized data.

[0612] Step 7:

[0613] Obtaining the latest medical information

[0614] The server collects the latest medical research and evidence from a cloud database. It obtains the latest information from academic paper APIs and databases and reflects this information in patient data. The input is the latest information from academic paper APIs and databases, and the output is an updated patient profile.

[0615] Step 8:

[0616] Predictive Analytics and Reporting

[0617] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data. The prediction results are generated as a data report and sent to the device. The input is the past data and the generative AI model, and the output is a data report containing the prediction results.

[0618] Step 9:

[0619] Collecting Emotional Data

[0620] The server uses an emotion engine to collect user emotion data in real time. For example, it recognizes emotions from facial expressions and voice when a medical professional confirms diagnostic information. The input is the user's facial expression data and voice data, and the output is data indicating the user's emotional state.

[0621] Step 10:

[0622] Interface adjustments

[0623] The device adjusts the interface display and operation based on the collected emotional data. If the medical professional is feeling stressed, the system automatically changes the screen layout and highlights important information. The input is data indicating the emotional state, and the output is an adjusted interface.

[0624] In this way, the object of the invention is achieved by collecting, analyzing, and integrating data at each processing step, and performing a series of processes that provide information in the most optimal form for the user.

[0625] 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.

[0626] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0627] 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.

[0628] [Second embodiment]

[0629] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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).

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0640] 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."

[0641] The system of the present invention integrates various medical data and supports advanced medical analysis. The following describes embodiments of the present invention and specific examples thereof.

[0642] 1. Data Collection

[0643] The server receives real-time biological information from the patient's body (e.g., heart rate, blood pressure, blood glucose level, temperature, etc.) from IoT devices and medical institution systems. For example, when receiving data from a heart rate monitor or blood glucose level sensor, this data is sent through an API.

[0644] The server retrieves electronic medical record information from medical institutions' systems using HL7 or FHIR protocols, allowing it to centrally manage the necessary diagnostic results and case records in real time.

[0645] 2. Data Integration

[0646] The server integrates and stores the received vital signs and diagnostic results in a cloud database, which allows data in different formats to be organized and centralized based on patient IDs.

[0647] The server checks data integrity and updates existing patient profiles in real time, adding new data entries and linking them to historical data.

[0648] 3. Electronic Medical Record Analysis

[0649] The server uses generative AI to analyze the text data in the electronic medical records. For example, it uses natural language processing (NLP) technology to extract important information from the records, such as "the patient had diabetes in the past."

[0650] The server converts the analysis results into structured data and adds it to the corresponding patient profile, allowing medical professionals to quickly access the information they need.

[0651] 4. Dashboard display

[0652] The server generates dashboard data based on the patient's information and sends the compiled data set to the device, displaying, for example, the patient's real-time heart rate and past diagnostic data on a single screen.

[0653] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[0654] 5. Providing the latest medical information and evidence

[0655] The server collects the latest medical research and evidence from cloud databases, including accessing academic paper APIs and medical databases.

[0656] The server associates the collected medical information with the patient's data and presents applicable treatments and medical findings.

[0657] 6. Predictive analysis and reporting functions

[0658] The server uses generative AI based on past data to predict future disease conditions and treatment outcomes. For example, it analyzes blood glucose level data from the past year to predict future risk of diabetes complications.

[0659] The server generates a data report of the predicted results, sends it to the device, and displays it to medical professionals, who can use the predicted data to adjust treatment plans or intervene early.

[0660] A specific example would be a cardiologist simultaneously viewing information from a patient's heart rate monitor and electronic medical record to determine whether an abnormal heart rate is related to a previous diagnosis. Based on this information, the doctor can quickly make treatment decisions. Generative AI can also be used to predict future disease states and proactively plan patient care.

[0661] In this way, the present invention provides a system that greatly improves the efficiency and accuracy of medical care through medical data integration, real-time analysis, and intuitive information display.

[0662] The processing flow will be explained below.

[0663] Program processing flow

[0664] 1. Data collection and integration

[0665] Step 1:

[0666] The server receives the patient's vital signs (heart rate, blood sugar level, etc.) in real time from the IoT device.

[0667] The server connects to each device and uses an API or dedicated protocol to collect data.

[0668] Step 2:

[0669] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[0670] The server sends a request to the medical institution's system to obtain the required patient data.

[0671] Step 3:

[0672] The server stores the received data in a cloud database and centrally consolidates it.

[0673] The server unifies the data format and organizes each piece of data based on the patient ID.

[0674] 2. Electronic Medical Record Analysis

[0675] Step 1:

[0676] The server begins processing to analyze the text data in the electronic medical record using the generation AI.

[0677] The server preprocesses the text data and removes noise.

[0678] Step 2:

[0679] The server uses natural language processing (NLP) techniques to extract key information and convert it into structured data.

[0680] The server extracts information such as "past diabetes" from the electronic medical record and attaches appropriate tags.

[0681] Step 3:

[0682] The server adds and updates the patient profile with the analysis results.

[0683] The server integrates new medical information into existing profiles and maintains data integrity.

[0684] 3. Dashboard display

[0685] Step 1:

[0686] The server generates dashboard data based on real-time patient data and analysis results.

[0687] The server extracts the data sets and converts them into graphs and charts.

[0688] Step 2:

[0689] The server transmits the generated dashboard data to the terminal.

[0690] The server encrypts the data for transmission and ensures secure communication.

[0691] Step 3:

[0692] The terminal visually displays the received dashboard data.

[0693] The terminal provides an interface that allows the user to easily understand the data.

[0694] 4. Providing the latest medical information and evidence

[0695] Step 1:

[0696] The server accesses a cloud database to collect the latest medical research and evidence.

[0697] The server retrieves the latest information from academic paper APIs and databases.

[0698] Step 2:

[0699] The server integrates the collected information with relevant patient data.

[0700] The server updates patient profiles with the latest treatments and research findings.

[0701] Step 3:

[0702] The device will provide updates to medical professionals with this new information.

[0703] The terminal displays the latest evidence so that the user can easily refer to it.

[0704] 5. Predictive analysis and reporting functions

[0705] Step 1:

[0706] The server uses generative AI to perform predictive analysis based on historical data.

[0707] The server inputs time-series data into an AI model to predict future risks and treatment effects.

[0708] Step 2:

[0709] The server generates the prediction results as a data report.

[0710] The server generates a report containing the predicted results along with a risk assessment and recommended actions.

[0711] Step 3:

[0712] The server transmits the generated forecast report to the terminal.

[0713] The server encrypts and securely transmits the reports.

[0714] Step 4:

[0715] The terminal displays the received prediction report to the medical professional.

[0716] The terminal provides an interface for the user to adjust the treatment plan based on the predicted results.

[0717] Throughout the system, healthcare professionals can leverage real-time, integrated patient data to make more accurate decisions.

[0718] Example 1

[0719] 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."

[0720] Conventional medical data management systems have incomplete integration of patient biometric information and diagnostic results, making it difficult to update and analyze information in real time. Furthermore, important medical information cannot be quickly extracted when analyzing text data from electronic medical records, making it difficult for medical professionals to easily access the information they need. Furthermore, there are insufficient mechanisms for effectively utilizing the latest medical research and evidence in clinical settings, leading to inaccurate predictions of treatment effectiveness and future disease conditions. As a result, there are issues with delays in the formulation of treatment plans and early intervention.

[0721] 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.

[0722] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from the cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means for analyzing the medical information collected from the cloud database and suggesting treatments appropriate for the patient's condition; means for predicting trends in heart rate and blood sugar level based on past data; means for generating the prediction results as a data report and transmitting it to the terminal; and means for the terminal to visually display the data report so that it can be used by medical professionals. This will enable the integration of diverse medical data from different sources, updating and analyzing it in real time, and providing medical professionals with quick access to the information they need. It will also promote the use of the latest medical research and evidence, improving the accuracy of future disease predictions, allowing for the rapid development of treatment plans and early intervention.

[0723] "Biometric information" is data obtained directly from a patient's body, and examples include heart rate, blood pressure, blood sugar level, and body temperature.

[0724] "Diagnostic results" refers to the evaluations and findings obtained through examinations and medical treatment of patients by medical institutions, and specifically includes the contents of medical certificates and test reports.

[0725] A "cloud database" refers to a database service that can be accessed via the Internet and allows for the centralized management and storage of large amounts of data.

[0726] A "patient profile" is a data set that centrally manages individual information about a patient, including medical history, biometric information, and diagnostic results.

[0727] "Generative AI" refers to systems that use artificial intelligence techniques to generate and analyze data, and is particularly used for advanced pattern recognition and predictive analysis.

[0728] An "electronic medical record" refers to a system that electronically records and manages patient medical information at medical institutions, including medical records, prescriptions, test results, etc.

[0729] "Dashboard data" refers to a data set that integrates information obtained from multiple data sources and displays it visually.

[0730] An "interface" is a means of enabling interaction between a user and a system, and includes screens and operating means that users can use intuitively.

[0731] "Medical research" means scientific research activities in the field of medicine, including experiments and investigations aimed at developing new treatments and understanding disease states.

[0732] "Evidence" refers to scientific evidence supporting the effectiveness of a particular medical procedure or treatment.

[0733] "Trend forecasting" refers to an analytical method that predicts future fluctuations and patterns based on past data.

[0734] A "data report" is a report that includes analytical results and forecast information and provides a summary of data for a specific purpose.

[0735] The system of the present invention integrates various medical data and supports advanced medical analysis. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[0736] Data collection

[0737] First, the server has a means to receive patient biometric information and diagnostic results in real time. Specifically, biometric information such as the patient's heart rate, blood pressure, blood glucose level, and body temperature is obtained via an API from IoT devices such as heart rate monitors and blood glucose sensors. Electronic medical record information is also obtained from medical institution systems using the HL7 and FHIR protocols.

[0738] Example: A server receives data from a heart rate monitor every minute and stores it in a database. Electronic medical record data is retrieved periodically using the HL7 protocol.

[0739] Data Integration

[0740] The server stores the received vital signs and diagnostic results in a cloud database, centrally integrating them, organizing data in different formats while maintaining consistency based on patient IDs, and updating patient profiles in real time.

[0741] Example: The server integrates heart rate and blood glucose data into a cloud database and appends it to an existing patient profile.

[0742] Electronic medical record analysis

[0743] The server uses generative AI to analyze the text data in the electronic medical record. It uses natural language processing (NLP) techniques to extract important information and patterns from the records, convert them into structured data, and add them to the patient profile.

[0744] Example: The server inputs the prompt "Extract past diabetes history from the patient's electronic medical record data" into the generative AI model and adds the retrieved information to the patient profile.

[0745] Dashboard View

[0746] The server generates dashboard data based on the patient's information and sends it to the device, which displays a single screen that integrates the patient's real-time heart rate and past diagnostic data.

[0747] The terminal visually displays the received dashboard data and provides an interface for use by medical professionals.

[0748] Example: The server generates dashboard data that combines heart rate data and past diagnostic data and sends it to the device, which displays this data in a graph format, allowing medical professionals to understand the patient's condition at a glance.

[0749] Providing the latest medical information and evidence

[0750] The server collects the latest medical research and evidence from a cloud database, associates it with patient data, analyzes the collected medical information, and suggests treatments appropriate for the patient's condition.

[0751] Example: The server uses the academic journal API to collect the latest research data and associate it with patient profiles to suggest optimal treatment options.

[0752] Predictive analytics and reporting

[0753] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data. The prediction results are generated as a data report and sent to the device, which then visually displays the data report and makes it available to medical professionals.

[0754] Example: The server analyzes blood glucose data from the past year to predict future diabetes risk. A report of the prediction results is sent to the device, which medical professionals can use to adjust treatment plans.

[0755] Prompt Sentence Examples

[0756] "Extract past diabetes history from a patient's electronic medical record data."

[0757] "Based on your heart rate data from the past year, predict your heart rate trend for the next six months."

[0758] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0759] Step 1: Receiving data

[0760] The server receives patient biometric information (heart rate, blood pressure, blood glucose level, body temperature, etc.) from IoT devices via an API. The input is data from the heart rate monitor and blood glucose level sensor, and the output is biometric information stored in a cloud database.

[0761] As a specific example of operation, the server receives the patient's heart rate data every minute through the API and stores it in a cloud database.

[0762] Step 2: Obtain electronic medical record data

[0763] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. The input is HL7 or FHIR format data from the medical institution's system, and the output is electronic medical record information stored in a cloud database.

[0764] As a specific example of operation, the server periodically acquires electronic medical record data from medical institutions every day via a protocol and centrally manages it.

[0765] Step 3: Data Integration

[0766] The server integrates the received biometric information and diagnostic results into a cloud database. The input is the biometric information and electronic medical record information obtained in steps 1 and 2, and the output is unified patient profile data.

[0767] As a specific example of how it works, heart rate data and blood glucose data are integrated into a cloud database and organized based on patient ID.

[0768] Step 4: Data integrity check

[0769] The server checks the integrity of the data and adds new data entries to the existing patient profile. The input is the merged patient profile data and the output is the updated patient profile.

[0770] As a specific example of operation, new heart rate data and diagnostic results are compared with the existing profile, and consistency is confirmed before updating.

[0771] Step 5: Electronic medical record analysis

[0772] The server analyzes the text data of the electronic medical record using a generative AI model. The input is the text data of the electronic medical record, and the output is structured medical information.

[0773] As a specific example of operation, a prompt statement such as "Extract past diabetes history from the patient's electronic medical record data" is input into the generative AI model, and the extracted information is converted into structured data.

[0774] Step 6: Generate dashboard data

[0775] The server generates dashboard data based on the patient information and sends it to the terminal. The input is the updated patient profile data, and the output is the dashboard data for visualization.

[0776] As a specific example of operation, dashboard data that integrates heart rate data and past diagnostic data is generated and sent to the terminal.

[0777] Step 7: View the dashboard

[0778] The terminal visually displays the received dashboard data. The input is the dashboard data sent from the server, and the output is the visualized data as a user interface.

[0779] As a specific example of how it works, the device displays heart rate and past diagnostic data at a glance through graphs and charts.

[0780] Step 8: Providing the latest medical information and evidence

[0781] The server collects the latest medical research and evidence from a cloud database and associates it with patient data. The input is the latest medical research data and patient information, and the output is the associated treatment and medical knowledge.

[0782] As a specific example of how it works, the server uses an academic paper API to collect the latest research data, associates it with patient profiles, and presents applicable treatments.

[0783] Step 9: Predictive analytics

[0784] The server uses a generative AI model based on past data to predict future disease conditions and treatment outcomes. The input is past heart rate and blood sugar data, and the output is a data report of the predicted disease conditions and treatment outcomes.

[0785] As a specific example of how it works, it analyzes blood glucose data from the past year and predicts the risk of future diabetic complications.

[0786] Step 10: Generate and view data reports

[0787] The server generates a data report based on the prediction results and sends it to the terminal, which visually displays the data report and makes it available to medical professionals. The input is the prediction result data, and the output is the visualized data report.

[0788] In a specific example of operation, the server compiles the predicted data into a report and sends it to the device, which then visually displays the report in graphs and text format and allows medical professionals to adjust the treatment plan.

[0789] (Application example 1)

[0790] 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."

[0791] Conventional medical systems have difficulty receiving, integrating, and analyzing patients' vital signs and diagnostic results in real time. Furthermore, there are insufficient means to use generative AI to analyze text data from electronic medical records, extract important medical information, and provide it to medical professionals. In particular, brick-and-mortar stores lack real-time data acquisition and analysis methods for managing customers' health and recommending appropriate treatments. This makes it difficult to provide personalized health advice to customers.

[0792] 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.

[0793] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and sending the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from a cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means, which is installed in smart glasses, for acquiring a customer's biometric information in real time and displaying the analysis results; means for acquiring electronic medical record information using HL7 or FHIR protocols; means for displaying appropriate treatments and health management suggestions on the display of the smart glasses; and means for providing advice based on the latest medical research and evidence. This will enable physical stores to provide personalized health advice to customers in real time.

[0794] "Patient's biological information" refers to physiological data obtained from within the patient's body, such as heart rate, blood pressure, blood sugar level, and body temperature.

[0795] "Diagnosis results" are the results of professional diagnoses or tests conducted by a doctor or medical institution regarding a patient's medical condition or health status.

[0796] A "cloud database" is a database service provided by a remote server that allows data to be stored, managed, and accessed over the Internet.

[0797] A "patient profile" is a set of information that represents the health status of an individual patient, constructed based on medical data such as the patient's biometric information, diagnosis results, and electronic medical records.

[0798] "Generative AI" is an artificial intelligence technique that can generate new information and insights using large datasets and machine learning algorithms.

[0799] An "electronic medical record" is a system that electronically records and manages a patient's medical history, prescriptions, test results, etc.

[0800] "Dashboard data" is a data set that visually organizes patient biometric information and diagnostic results, and displays them in a way that can be understood at a glance.

[0801] A "terminal" is a device that a user operates, and in this case refers to a PC, smartphone, tablet, etc.

[0802] An "interface" is a software or hardware component that provides a screen or means of operation for a user to interact with a system.

[0803] "Medical research" is scientific research conducted with the goal of advancing medical care, understanding disease, and developing treatments.

[0804] "Evidence" refers to data and research results that provide scientific evidence used in the medical field.

[0805] "Predicting future disease states and treatment outcomes" is the process of using past data and generative AI to predict a patient's future health condition and treatment outcomes.

[0806] "Smart glasses" are a wearable eyeglass-type device equipped with a display that can display data in real time and provide information to users.

[0807] The "HL7 and FHIR protocols" are standards for electronically exchanging medical information and are formats and communication protocols that ensure interoperability of medical data.

[0808] "Health management suggestions" involve providing specific advice and recommendations on lifestyle changes, treatment options, etc. to improve a patient's health.

[0809] The system according to the present invention integrates various medical data and realizes advanced medical analysis. Specific embodiments of the present invention will be described below.

[0810] 1. Hardware Configuration

[0811] The system includes the following hardware:

[0812] Server: The central component responsible for data collection, integration, analysis, and cloud database management.

[0813] Smart glasses: A wearable device that allows users to check data in real time and receive appropriate health advice.

[0814] IoT devices: These devices collect patients' vital signs, such as heart rate, blood pressure, and blood sugar levels, in real time.

[0815] Device: The device that provides the data visualization or interface, including computers, smartphones, tablets, etc.

[0816] 2. Software Configuration

[0817] The system uses the following software:

[0818] Python: The language on which the program is based.

[0819] OpenAI API: Generative AI models (e.g., GPT-4) used for natural language processing (NLP).

[0820] Requests (Python library): A library for retrieving data from APIs.

[0821] HL7 / FHIR API: A standard protocol for obtaining electronic medical record information.

[0822] 3. Data Collection and Integration

[0823] The server receives patient biometric information from IoT devices in real time and retrieves electronic medical record information from medical institutions using HL7 and FHIR protocols. These data are integrated and stored in a cloud database, and patient profiles are updated in real time.

[0824] 4. Data Analysis

[0825] The server uses generative AI to parse the text data in the electronic medical record to extract important medical information and patterns, which are then added to the corresponding patient profile and made easily accessible to medical professionals.

[0826] 5. Dashboard generation and display

[0827] The server generates dashboard data based on the patient's information and sends it to the device. The device visualizes the dashboard data and provides an interface for medical professionals to use. The smart glasses collect the patient's biometric information in real time and display the analysis results to provide appropriate health advice to the patient.

[0828] 6. Providing the latest medical information and evidence

[0829] The server collects the latest medical research and evidence from a cloud database and associates the collected medical information with patient data, thereby suggesting applicable treatments and medical findings.

[0830] 7. Predictive Analytics and Reporting

[0831] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data, and the results are generated as a data report, which is sent to the device and displayed to medical professionals.

[0832] Specific examples

[0833] For example, when a customer visits a pharmacy, the smart glasses can be used to check their heart rate and past diagnostic information, and provide them with on-the-spot medication and health advice.

[0834] Prompt Sentence Examples

[0835] Patient data: {"physiological_data": {"heart_rate": 85, "blood_pressure": "120 / 80", "blood_sugar": 110}, "medical_records": {"condition": "hypertension", "medication": ["Drug A", "Drug B"]}}.

[0836] Provide a summary and recommendations.

[0837] This will enable physical stores to provide personalized health advice to customers in real time.

[0838] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0839] Step 1:

[0840] Collecting patient vital signs in real time

[0841] The server receives real-time biometric information such as heart rate, blood pressure, and blood sugar levels from IoT devices. Specifically, it periodically acquires data sent from IoT devices using an API and stores it in a cloud database.

[0842] Input: Biometric data from IoT devices

[0843] Output: Biometric information stored in a cloud database

[0844] Step 2:

[0845] Obtain electronic medical record information

[0846] The server retrieves electronic medical record information from medical institutions' systems using the HL7 or FHIR protocol. Specifically, based on the specified protocol, it extracts information such as patient diagnosis results and past medical history from the medical institution's database and integrates it into a cloud database.

[0847] Input: Electronic medical record information from medical institutions

[0848] Output: Electronic medical record information stored in a cloud database

[0849] Step 3:

[0850] Data integration and profile updates

[0851] The server integrates the received vital signs and electronic medical records into a cloud database and updates patient profiles in real time. Specifically, it organizes different types of data for each patient and adds them to the existing data profile.

[0852] Input: Biometric information and electronic medical record information

[0853] Output: Updated patient profile

[0854] Step 4:

[0855] Using generative AI to analyze text data from electronic medical records

[0856] The server uses generative AI (e.g., OpenAI's GPT-4) to analyze the text data of the electronic medical record and extract important medical information and patterns. Specifically, the server supplies the text data of the electronic medical record and obtains the extracted important information as the output of the AI ​​model.

[0857] Input: Text data from electronic medical records

[0858] Output: Extracted important medical information

[0859] Step 5:

[0860] Adding analysis results to patient profiles

[0861] The server adds the key medical information extracted by the generative AI to the corresponding patient profile, making it easily accessible to medical professionals.

[0862] Input: Extracted vital medical information

[0863] Output: Updated patient profile

[0864] Step 6:

[0865] Generate dashboard data and send it to the device

[0866] The server generates dashboard data based on the patient's information and sends it to the terminal. Specifically, it extracts the necessary data from the patient profile, converts it into a visually easy-to-understand format, and generates the dashboard.

[0867] Input: Patient Profile

[0868] Output: Generated dashboard data

[0869] Step 7:

[0870] The device visualizes the dashboard data and provides it as an interface.

[0871] The device visualizes the transmitted dashboard data and provides a user-friendly interface for medical professionals, displaying key patient information in the form of graphs and charts.

[0872] Input: Submitted dashboard data

[0873] Output: Visualized dashboard

[0874] Step 8:

[0875] Collect the latest medical research and evidence and link it to patient data

[0876] The server collects the latest medical research and evidence from a cloud database and associates it with patient data, specifically retrieving the latest information from academic paper databases and medical information platforms, and reflecting it in patient profiles.

[0877] Input: Latest medical research and evidence

[0878] Output: Updated patient profile

[0879] Step 9:

[0880] Using generative AI to predict future disease states and treatment outcomes

[0881] The server uses generative AI based on past data to predict future medical conditions and treatment outcomes. Specifically, it analyzes past biometric information and diagnostic result data to predict future health risks and treatment outcomes.

[0882] Input: Past vital signs and diagnostic results data

[0883] Output: Predicted future disease status and treatment effects

[0884] Step 10:

[0885] The application installed on the smart glasses collects the customer's biometric information in real time and displays the analysis results.

[0886] The application installed on the smart glasses collects the customer's biometric information in real time and displays the results analyzed by the generative AI. Specifically, the glasses display shows treatment and health management suggestions, providing appropriate advice to the user.

[0887] Input: Customer's biometric information and the analysis results of the generated AI

[0888] Output: Health advice displayed on smart glasses

[0889] Step 11:

[0890] Displaying appropriate treatment and health management suggestions on the smart glasses display

[0891] The smart glasses will then display appropriate treatment and health management suggestions based on the analysis results, allowing users to receive specific advice in real time.

[0892] Input: Analysis results

[0893] Output: Displayed treatment and health management suggestions

[0894] Step 12:

[0895] Providing the latest medical research and evidence-based advice

[0896] The server provides users with appropriate advice based on the latest medical research and evidence collected, specifically suggesting optimal treatments and health management based on the latest medical information linked to patient data.

[0897] Input: Latest medical research and evidence

[0898] Output: Advice provided

[0899] 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.

[0900] The system of the present invention not only integrates, analyzes, and visualizes medical data, but also recognizes the user's emotions and adjusts the interface based on those emotions to provide more optimal medical support. The following describes embodiments of the present invention and specific examples thereof.

[0901] 1. Data Collection

[0902] The server receives patient vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time from IoT devices, which transmit data using APIs or dedicated protocols.

[0903] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol and obtains the necessary diagnostic results and case notes.

[0904] 2. Data Integration

[0905] The server integrates and stores the received biometric information and diagnostic results in a cloud database, standardizing the data format and organizing each piece of data based on patient ID.

[0906] The server checks the integrity of the data and updates existing patient profiles in real time.

[0907] 3. Electronic Medical Record Analysis

[0908] The server uses generative AI to analyze the text data in the electronic medical records and extract important information, such as "past diabetes," using natural language processing (NLP) technology to extract information and convert it into structured data.

[0909] The server adds and updates the patient profile with the analysis results, allowing medical professionals to quickly access the information they need.

[0910] 4. Dashboard display

[0911] The server generates dashboard data based on the patient's information and sends the compiled data set to the terminal.

[0912] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[0913] 5. Providing the latest medical information and evidence

[0914] The server collects the latest medical research and evidence from a cloud database, obtains the latest information from academic paper APIs and databases, and reflects it in patient data.

[0915] The device provides medical professionals with the latest collected information to aid in diagnosis and treatment planning.

[0916] 6. Predictive analysis and reporting functions

[0917] The server uses generative AI to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes, and generates a data report of the results, which is sent to the device and displayed to medical professionals.

[0918] The device provides an interface for adjusting treatment plans and conducting early intervention based on the received predictive report.

[0919] 7. Incorporating an Emotional Engine

[0920] The server incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state, for example, recognizing emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis.

[0921] The server then reflects the emotional data obtained from the emotion engine in the dashboard data, allowing medical professionals to make comprehensive judgments that take into account their own emotional state.

[0922] The device adjusts the interface display and operation based on the user's emotions: for example, if a medical professional is feeling highly stressed, the system will automatically change the screen layout and highlight important information.

[0923] Examples:

[0924] The server receives data in real time from heart rate monitors and blood glucose sensors, stores it in a cloud database, and consolidates it.

[0925] The server analyzes electronic medical records to determine whether the patient has had diabetes in the past and adds this information to the patient profile.

[0926] The device generates a dashboard that visually displays the patient's overall health status and diagnostic results.

[0927] The server uses an emotion engine to analyze the emotional state of the medical professional as they view the dashboard: for example, if the professional is feeling anxious, the system will highlight important information more prominently.

[0928] The device adjusts the interface display based on the patient's emotional state, helping medical professionals make efficient decisions.

[0929] The entire system empowers healthcare professionals with real-time, integrated patient data for fast and accurate decision-making in an interface optimized for the user's emotional state.

[0930] The processing flow will be explained below.

[0931] Program processing flow

[0932] 1. Data collection and integration

[0933] Step 1:

[0934] The server receives the patient's vital signs (heart rate, blood pressure, blood sugar level, etc.) in real time from the IoT device.

[0935] The server collects data from each device through an API and checks the integrity of the data received.

[0936] Step 2:

[0937] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[0938] The server sends the request, extracts the corresponding data, and converts the format.

[0939] Step 3:

[0940] The server integrates and stores the received biometric information and electronic medical record data in a cloud database.

[0941] The server organizes each piece of data based on the patient ID and creates a database entry for centralized management.

[0942] 2. Electronic Medical Record Analysis

[0943] Step 1:

[0944] The server analyzes the text data in the electronic medical records using generative AI (natural language processing technology).

[0945] The server preprocesses the text data of the electronic medical records, removes noise, and performs morphological analysis.

[0946] Step 2:

[0947] The server uses generative AI to extract important medical information and patterns.

[0948] The server detects important information, such as "past diabetes," and tags and converts that information into structured data.

[0949] Step 3:

[0950] The server adds the analysis results to the patient profile and integrates them with existing data.

[0951] The server updates the database and adds the extracted medical information.

[0952] 3. Dashboard display

[0953] Step 1:

[0954] The server creates dashboard data based on the patient's real-time biometric information and analysis results.

[0955] The server transforms the data into graphs and charts and generates a data set for the dashboard.

[0956] Step 2:

[0957] The server transmits the generated dashboard data to the terminal.

[0958] The server encrypts the data to ensure secure transmission and transmits it using HTTPS.

[0959] Step 3:

[0960] The terminal visually displays the received dashboard data.

[0961] The device uses graphs and charts to make the information easy for medical professionals to understand.

[0962] 4. Providing the latest medical information and evidence

[0963] Step 1:

[0964] The server accesses a cloud database to collect the latest medical research and evidence.

[0965] The server sends requests to retrieve information from academic paper APIs and medical databases.

[0966] Step 2:

[0967] The server integrates the collected medical information with the patient's data.

[0968] The server adds the latest evidence to the patient's profile and suggests applicable treatments.

[0969] Step 3:

[0970] The terminal displays an interface that provides the medical professional with the latest collected information.

[0971] The terminal provides visualization options where appropriate to allow the user to easily view the new information.

[0972] 5. Predictive analysis and reporting functions

[0973] Step 1:

[0974] The server uses generative AI to perform predictive analysis based on past data.

[0975] The server inputs time-series data into an AI model to predict future disease conditions and treatment outcomes.

[0976] Step 2:

[0977] The server generates the prediction results as a data report.

[0978] The server generates a report containing the predicted results, risk assessment, and recommended actions.

[0979] Step 3:

[0980] The server transmits the generated data report to the terminal.

[0981] The server encrypts the data reports and transmits them over a secure channel.

[0982] Step 4:

[0983] The terminal displays the received prediction report to the medical professional.

[0984] The terminal provides an interface that allows the user to review predicted results and adjust the treatment plan.

[0985] 6. Use of Emotion Engines

[0986] Step 1:

[0987] The terminal activates an emotion engine to recognize the emotions of the user (medical professional).

[0988] The device recognizes the user's facial expressions and analyzes their voice to determine their emotional state.

[0989] Step 2:

[0990] The server receives the emotion data obtained from the emotion engine and reflects it in the dashboard data.

[0991] The server analyzes and prepares the necessary data to adjust the interface according to the user's emotional state.

[0992] Step 3:

[0993] The device adjusts the interface display and operation method based on the emotional state.

[0994] If the user is feeling stressed, the device will highlight important information or change the screen layout.

[0995] Examples:

[0996] The server receives data in real time from the heart rate monitor and blood glucose sensor, stores it in a cloud database, and consolidates it.

[0997] The server adds information extracted from the electronic medical record, such as "past diabetes," to the patient profile and updates the database.

[0998] The device generates a dashboard that visually displays the patient's overall health status and diagnostic results.

[0999] The server uses an emotion engine to analyze the emotional state of the medical professional as he or she reviews the dashboard.

[1000] If the user feels anxious, the device will automatically highlight important information and change the screen layout to optimize the user experience.

[1001] This will enable healthcare professionals to make faster and more accurate decisions through integrated medical data and an optimized user interface.

[1002] Example 2

[1003] 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."

[1004] Traditional medical systems do not integrate patients' vital signs and diagnostic results in real time, making it difficult for medical professionals to access information quickly. They also do not take into account the patient's emotional state, potentially resulting in a decline in the quality of medical care. Furthermore, it is difficult to predict future disease conditions and treatment outcomes, limiting diagnostic and treatment planning.

[1005] 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.

[1006] In this invention, the server includes: means for receiving patient biometric information and diagnostic results in real time; means for storing and centrally integrating the patient biometric information and diagnostic results in a cloud database; means for updating patient profiles in real time based on the integrated data; means for analyzing text data from electronic medical records using a generative AI to extract important medical information and patterns; means for adding the analysis results to the corresponding patient profile for easy access by medical professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from a cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment outcomes based on past data using a generative AI; means for recognizing and analyzing a user's emotional state and reflecting the emotional data in the interface; and means for adjusting the interface based on the user's emotional state. This enables centralized management of patient biometric information and diagnostic results, real-time information updates, and predictive analysis based on patient data. Furthermore, adjusting the interface to take the user's emotional state into account is expected to improve the quality of medical care.

[1007] "Patient's vital signs" refers to data that indicates the patient's physical condition, such as heart rate, blood pressure, and blood sugar level.

[1008] "Diagnosis" means the result of a diagnosis made by a medical professional and is information related to a patient's medical condition and treatment plan.

[1009] "Cloud database" refers to a database stored on a remote server accessible via the Internet.

[1010] "Integrating" refers to the process of combining data collected from different sources into one database.

[1011] A "patient profile" refers to a data set that compiles medical information about an individual patient, such as biometric information, diagnostic results, and treatment history.

[1012] "Generative AI" refers to artificial intelligence technology that uses machine learning and deep learning algorithms to analyze data and generate new information and predictions.

[1013] "Electronic medical record text data" refers to the text information of an electronically recorded medical record.

[1014] "Dashboard Data" refers to data that has been processed to visually display consolidated patient information.

[1015] "Terminal" refers to a device, such as a text editor, with computer graphics used by a healthcare professional to view and manipulate information.

[1016] "Interface" refers to the screen and operation method used by users to operate software or hardware.

[1017] "The latest medical research and evidence" refers to medical information and evidence obtained through recent scientific research and clinical trials.

[1018] "Predictive analytics" refers to the process of predicting and analyzing future disease conditions and treatment outcomes based on past data.

[1019] "Emotion engine" refers to software technology for recognizing and analyzing a user's emotional state from their facial expressions and voice.

[1020] "Interface adjustment" refers to the process of changing the operating screen and display content based on the user's emotional state.

[1021] The system of the present invention receives, integrates, analyzes, and visualizes the patient's vital signs and diagnostic results in real time, and also recognizes the user's emotions and adjusts the interface to provide more optimal medical support. Specific embodiments of the present invention are described below.

[1022] Data collection

[1023] The server receives the patient's vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time. This data is sent from IoT devices using APIs or dedicated protocols. For example, when receiving data from a heart rate monitor or blood glucose sensor, the server obtains heart rate data of 70 bpm via an HTTP request and stores it in a cloud database.

[1024] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. This allows it to collect diagnosis results and case records. For example, it retrieves information such as "Diabetes: positive" from "Patient ID: 1234" via the FHIR protocol.

[1025] Data Integration

[1026] The server integrates the collected vital signs and diagnostic results into a cloud database. The data format is standardized and each data item is organized based on the patient ID. For example, the data is stored in the database in a standardized JSON format as "Patient ID: 1234, heart_rate: 70 bpm, blood_pressure: 120 / 80, diabetes_history: positive."

[1027] The server checks the data for consistency and updates the patient profile in real time: for example, if the heart rate is an unrealistic value (such as 0 bpm or 300 bpm), the data is invalidated.

[1028] Electronic medical record analysis

[1029] The server uses a generative AI model to analyze the text data in the electronic medical record and extract important information. It uses natural language processing (NLP) technology to extract information such as "past diabetes" and convert it into structured data. For example, text such as "The patient had diabetes in the past" is converted into structured data as "diabetes_history: positive."

[1030] The server adds the extracted information to and updates the patient profile, allowing medical professionals to quickly access the information they need.

[1031] Dashboard View

[1032] The server generates dashboard data based on the patient information and sends it to the terminal in a format such as "Patient ID: 1234, chart_data: ...".

[1033] The device visually displays the received dashboard data, allowing medical professionals to see important information at a glance through graphs and charts. For example, it generates graphs such as "Heart Rate Trend" and "Blood Glucose Chart" and updates the dashboard.

[1034] Providing the latest medical information and evidence

[1035] The server collects the latest medical research and evidence from a cloud database. It retrieves the latest information from academic paper APIs and databases and reflects it in patient data. For example, it searches the database with the query "latest diabetes treatments" to retrieve the latest paper information.

[1036] The device then provides medical professionals with the latest information it has collected to aid in diagnosis and treatment planning, for example by notifying them that "five new diabetes treatments have been discovered."

[1037] Predictive analytics and reporting

[1038] The server uses the generative AI model to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes. For example, it sends a query to the generative AI model, such as "Predict blood glucose fluctuations over the next six months for patient ID: 1234," and obtains the predicted results.

[1039] The server generates a data report of the prediction results and sends it to the device. Medical professionals can use this information to adjust their diagnosis and treatment plan. For example, a "blood glucose prediction report for the next six months" can be generated in PDF format and sent to the device.

[1040] Incorporating an emotion engine

[1041] The server uses an emotion engine to analyze the user's emotional state. For example, it recognizes emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis. It analyzes facial expression data and voice data acquired through a camera and microphone and determines the user's "stress level: high."

[1042] The server reflects the emotional data in the dashboard data, which enables comprehensive judgment. For example, data such as "emotional state: high stress level" can be integrated into the dashboard data.

[1043] The device adjusts the interface display based on the user's emotions. For example, if a medical professional is feeling highly stressed, important information will be highlighted. Based on the emotional data, important information will be highlighted with a red frame.

[1044] Prompt Sentence Examples

[1045] Use the following parameters to generate dashboard content that can be easily understood by healthcare professionals.

[1046] Parameters: Patient ID, heart rate, blood pressure, blood glucose, past medical history, latest diagnosis

[1047] Generative AI models should use natural language processing to extract key information, such as "past diabetes," and provide it as structured data, and also adapt the interface based on the user's emotional state.

[1048] The entire system empowers healthcare professionals with real-time, integrated patient data to make fast and accurate decisions with an interface optimized for the user's emotional state.

[1049] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1050] Step 1: Data collection

[1051] The server receives real-time patient vital signs from IoT devices such as heart rate monitors and blood glucose sensors, which are transmitted using APIs and proprietary protocols.

[1052] Input: Biometric information such as heart rate, blood pressure, and blood sugar level

[1053] Data processing: The server converts the received data into an appropriate format and stores it in a cloud database.

[1054] Output: Formatted biometric data

[1055] Specific operation:

[1056] The server receives an HTTP request from the heart rate monitor and stores the heart rate of 70 bpm in a cloud database in JSON format.

[1057] Step 2: Obtaining electronic medical record information

[1058] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[1059] Input: Patient ID, electronic medical record information

[1060] Data processing: The server analyzes the acquired medical record information, extracts diagnostic results and case records, and stores them in a database.

[1061] Output: Analyzed medical record information

[1062] Specific operation:

[1063] The server queries the diagnosis results for "Patient ID: 1234" using the FHIR protocol and integrates the obtained "Diabetes: positive" information into the database.

[1064] Step 3: Data Integration

[1065] The server integrates the biometric information and diagnostic results into a cloud database.

[1066] Input: Biometric information, diagnosis results

[1067] Data processing: The server standardizes the data format and organizes each data based on the patient ID.

[1068] Output: Unified patient data

[1069] Specific operation:

[1070] The server stores the data in a database in the format "Patient ID: 1234, heart_rate: 70 bpm, blood_pressure: 120 / 80, diabetes_history: positive".

[1071] Step 4: Check data integrity

[1072] The server checks the integrity of the merged data and eliminates inconsistent data.

[1073] Input: Unified patient data

[1074] Data calculation: The server checks the data format and outliers.

[1075] Output: consistent data

[1076] Specific operation:

[1077] The server detects unrealistic heart rate data such as 0 bpm or 300 bpm and rejects it as inconsistent data.

[1078] Step 5: Electronic medical record analysis

[1079] The server uses a generative AI model to analyze the text data in the electronic medical record and extract key information.

[1080] Input: Electronic medical record text data

[1081] Data calculation: Using natural language processing technology, information such as "past diabetes" is extracted from text and converted into structured data.

[1082] Output: Structured important information

[1083] Specific operation:

[1084] The server converts text such as "The patient had diabetes in the past" as "diabetes_history: positive".

[1085] Step 6: Update the patient profile

[1086] The server adds and updates the patient profile with the analysis results.

[1087] Input: Structured critical information

[1088] Data calculations: Add new information to an existing patient profile.

[1089] Output: Updated patient profile

[1090] Specific operation:

[1091] The server adds the "Past History of Diabetes" data to the profile and updates it as "Patient ID: 1234, diabetes_history: positive".

[1092] Step 7: Generate dashboard data

[1093] The server generates dashboard data based on the patient's information and sends it to the terminal.

[1094] Input: Patient profile data

[1095] Data processing: Converting data into a visualizable format.

[1096] Output: Dashboard data

[1097] Specific operation:

[1098] The server sends the dashboard data to the terminal in the format "Patient ID: 1234, chart_data: ...".

[1099] Step 8: View the Dashboard

[1100] The terminal visually displays the received dashboard data.

[1101] Input: Dashboard data

[1102] Data processing: Display the data using visualization tools.

[1103] Output: Visualized information

[1104] Specific operation:

[1105] The device generates graphs such as "heart rate trend" and "blood glucose chart" and updates the dashboard.

[1106] Step 9: Gather the latest medical information

[1107] The server collects the latest medical research and evidence from a cloud database.

[1108] Input: Query, medical information database

[1109] Data Calculation: The server uses the specified query to extract the latest information.

[1110] Output: Latest medical information

[1111] Specific operation:

[1112] The server searches the database using the keyword "latest diabetes treatments" to obtain new paper information.

[1113] Step 10: Provide medical information

[1114] The device displays the latest collected medical information to medical professionals to aid in diagnosis and treatment planning.

[1115] Input: Latest medical information

[1116] Data processing: Converting information into a user-friendly format for display.

[1117] Output: Medical information displayed

[1118] Specific operation:

[1119] The device notifies the user that "five new diabetes treatments have been discovered" and displays details.

[1120] Step 11: Perform predictive analysis

[1121] The server uses a generative AI model to perform predictive analysis based on historical data.

[1122] Input: Historical Patient Data

[1123] Data calculation: Predicting future disease conditions and treatment outcomes from past data.

[1124] Output: Prediction result data

[1125] Specific operation:

[1126] The server sends a query to the generative AI model saying, "Predict blood glucose fluctuations for the next 6 months for patient ID: 1234" and obtains the prediction results.

[1127] Step 12: Generate forecast data reports

[1128] The server generates a data report based on the prediction results and sends it to the terminal.

[1129] Input: Prediction result data

[1130] Data processing: Compile the prediction results into a report format.

[1131] Output: Data report

[1132] Specific operation:

[1133] The server generates a "blood glucose prediction report for the next six months" in PDF format and sends it to the terminal.

[1134] Step 13: Emotion Engine Analysis

[1135] The server uses an emotion engine to analyze the user's emotional state.

[1136] Input: facial expression and voice data from camera and microphone

[1137] Data Computation: Analyze emotional states using an emotion engine.

[1138] Output: Emotion data

[1139] Specific operation:

[1140] The server analyzes facial expression and voice data acquired through the camera and microphone and determines the "stress level: high."

[1141] Step 14: Reflecting Emotional Data

[1142] The server reflects the emotion data on the dashboard.

[1143] Input: Emotion data

[1144] Data processing: Integrating sentiment data into dashboard data.

[1145] Output: Dashboard data after reflecting emotions

[1146] Specific operation:

[1147] The server consolidates and displays data such as "Emotional state: High stress level" on a dashboard.

[1148] Step 15: Adjusting the Interface

[1149] The terminal adjusts the display content of the interface based on the user's emotional state.

[1150] Input: Dashboard data after reflecting emotions

[1151] Data processing: Adjusting the interface, such as highlighting important information.

[1152] Output: Adjusted interface

[1153] Specific operation:

[1154] If the device determines that your stress level is high, it will highlight important information in a red frame.

[1155] (Application example 2)

[1156] 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."

[1157] Current medical support systems lack the ability to not only integrate and analyze patients' biometric information and diagnostic results, but also adjust their interfaces based on the user's emotional state. This makes it difficult for medical professionals to make quick and accurate decisions, even in stressful situations. Furthermore, there is a need for an efficient way to display important information in emergency situations. To solve these issues, a mechanism is needed to collect user emotional data in real time and adjust the interface appropriately.

[1158] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving patient biometric information and diagnostic results in real time, means for storing and centrally integrating the patient biometric information and diagnostic results in a cloud database, means for updating the patient profile in real time based on the integrated data, means for analyzing text data in the electronic medical record using a generating AI to extract important medical information and patterns, means for adding the analysis results to the corresponding patient profile so that medical professionals can easily access it, means for generating dashboard data based on the patient information and transmitting the dashboard data to a terminal, means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals, means for collecting the latest medical research and evidence from a cloud database, means for associating the collected medical information with patient data, means for predicting future medical conditions and treatment effects based on past data using a generating AI, means for collecting user emotional data in real time, and means for adjusting the interface based on the collected emotional data. This enables appropriate information display and interface adjustment according to the user's emotional state, enabling medical professionals to make quick and accurate decisions even in stressful situations.

[1159] "Biometric information" refers to data on a patient's physical condition, such as heart rate, blood pressure, and blood sugar level, obtained in real time.

[1160] "Diagnosis results" are data obtained as a result of a diagnosis made to a patient by a medical institution, and are information recorded in an electronic medical record.

[1161] A "cloud database" refers to data stored on remote servers accessible over the internet, and is often used to store medical information.

[1162] A "patient profile" is an integrated data set that includes a patient's biometric information, diagnostic results, and medical history.

[1163] "Generative AI" is a type of artificial intelligence technology that refers to algorithms that analyze data and make predictions using models trained for specific purposes.

[1164] An "electronic medical record" is a patient's medical record stored in digital format, and refers to a record of diagnosis and treatment within a medical institution.

[1165] "Dashboard data" is summary data configured to visually display information aggregated from multiple data sources.

[1166] A "terminal" is a device that a user uses to check data or information, and includes a PC, tablet, smartphone, etc.

[1167] "State-of-the-art medical research" refers to ongoing or recently completed research and results in the field of medicine.

[1168] "Evidence" refers to scientific evidence that serves as the basis for medical treatment and diagnosis in the medical field.

[1169] "Emotion data" is information about the emotional state extracted from the user's facial expressions, voice, behavior, etc.

[1170] "Interface adjustment" refers to changing the display and operation method of the system used by the user based on the user's emotional state.

[1171] To implement this invention, the following system configuration is required: This system integrates the patient's biometric information and diagnostic results, and incorporates the user's emotional data to assist medical professionals in making quick and effective decisions.

[1172] 1. Data collection and integration

[1173] The server receives patient vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time from IoT devices, which transmit data using APIs or dedicated protocols.

[1174] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol and receives the necessary diagnostic results and case notes.

[1175] The server integrates and stores the received biometric information and diagnostic results in a cloud database, standardizing the data format and organizing each piece of data based on patient ID.

[1176] 2. Electronic Medical Record Analysis

[1177] The server uses generative AI to analyze the text data in the electronic medical records and extract important information, such as "past diabetes," using natural language processing (NLP) technology to extract information and convert it into structured data.

[1178] 3. Dashboard display

[1179] The server generates dashboard data based on the patient's information and sends the compiled data set to the terminal.

[1180] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[1181] 4. Providing the latest medical information and evidence

[1182] The server collects the latest medical research and evidence from a cloud database, obtains the latest information from academic paper APIs and databases, and reflects it in patient data.

[1183] The device provides medical professionals with the latest collected information to aid in diagnosis and treatment planning.

[1184] 5. Predictive analytics and reporting

[1185] The server uses generative AI to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes, and generates a data report of the results, which is sent to the device and displayed to medical professionals.

[1186] 6. Incorporating an Emotional Engine

[1187] The server incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state, for example, recognizing emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis.

[1188] The device adjusts the interface and controls based on the user's emotions: if a medical professional is feeling stressed, the system automatically changes the screen layout and highlights important information.

[1189] Specific examples

[1190] For example, if a medical professional is stressed during an emergency, the displayed dashboard data will automatically highlight important information, allowing for a quicker response, while if the medical professional remains calm, the normal interface will be displayed.

[1191] Prompt Sentence Examples

[1192] Please provide a concrete example of a system that collects user sentiment data in real time and adjusts the interface accordingly. Also explain how the data is stored with a timestamp and used to generate dashboard data.

[1193] This system configuration allows healthcare professionals to make fast and accurate decisions using real-time integrated patient data and an interface that adapts to the user's emotional state.

[1194] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1195] Step 1:

[1196] Data collection

[1197] The server receives the patient's vital signs (heart rate, blood pressure, blood glucose level, etc.) from the IoT device in real time. The data is sent via API or dedicated communication protocol. The input is the vital signs from the IoT device, and the output is the raw data for integration.

[1198] Step 2:

[1199] Acquisition of electronic medical record information

[1200] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. The input is diagnosis results and case notes from the medical institution's system, and the output is raw data for storing this information.

[1201] Step 3:

[1202] Data Integration and Storage

[1203] The server integrates and stores the received biometric information and diagnostic results in a cloud database. The data format is standardized and each data item is organized based on the patient ID. The input is raw data of biometric information and diagnostic results, and the output is integrated patient profile data.

[1204] Step 4:

[1205] Electronic medical record analysis

[1206] The server uses generative AI to analyze the text data in the electronic medical record. It uses natural language processing (NLP) technology to extract information such as "past diabetes" and convert it into structured data. The input is the text data of the raw medical record, and the output is the analyzed structured data.

[1207] Step 5:

[1208] Generate dashboard data

[1209] The server generates dashboard data based on patient information. The generated data is sent to the terminal. The input is the integrated patient profile data and analysis results, and the output is the dashboard data for visualization.

[1210] Step 6:

[1211] Dashboard View

[1212] The terminal visually displays the received dashboard data, allowing medical professionals to see important information at a glance through graphs and charts. The input is the dashboard data sent from the server, and the output is the visualized data.

[1213] Step 7:

[1214] Obtaining the latest medical information

[1215] The server collects the latest medical research and evidence from a cloud database. It obtains the latest information from academic paper APIs and databases and reflects this information in patient data. The input is the latest information from academic paper APIs and databases, and the output is an updated patient profile.

[1216] Step 8:

[1217] Predictive Analytics and Reporting

[1218] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data. The prediction results are generated as a data report and sent to the device. The input is the past data and the generative AI model, and the output is a data report containing the prediction results.

[1219] Step 9:

[1220] Collecting Emotional Data

[1221] The server uses an emotion engine to collect user emotion data in real time. For example, it recognizes emotions from facial expressions and voice when a medical professional confirms diagnostic information. The input is the user's facial expression data and voice data, and the output is data indicating the user's emotional state.

[1222] Step 10:

[1223] Interface adjustments

[1224] The device adjusts the interface display and operation based on the collected emotional data. If the medical professional is feeling stressed, the system automatically changes the screen layout and highlights important information. The input is data indicating the emotional state, and the output is an adjusted interface.

[1225] In this way, the object of the invention is achieved by collecting, analyzing, and integrating data at each processing step, and performing a series of processes that provide information in the most optimal form for the user.

[1226] 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.

[1227] 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.

[1228] 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.

[1229] [Third embodiment]

[1230] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1231] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1232] 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).

[1233] 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.

[1234] 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.

[1235] 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).

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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."

[1242] The system of the present invention integrates various medical data and supports advanced medical analysis. The following describes embodiments of the present invention and specific examples thereof.

[1243] 1. Data Collection

[1244] The server receives real-time biological information from the patient's body (e.g., heart rate, blood pressure, blood glucose level, temperature, etc.) from IoT devices and medical institution systems. For example, when receiving data from a heart rate monitor or blood glucose level sensor, this data is sent through an API.

[1245] The server retrieves electronic medical record information from medical institutions' systems using HL7 or FHIR protocols, allowing it to centrally manage the necessary diagnostic results and case records in real time.

[1246] 2. Data Integration

[1247] The server integrates and stores the received vital signs and diagnostic results in a cloud database, which allows data in different formats to be organized and centralized based on patient IDs.

[1248] The server checks data integrity and updates existing patient profiles in real time, adding new data entries and linking them to historical data.

[1249] 3. Electronic Medical Record Analysis

[1250] The server uses generative AI to analyze the text data in the electronic medical records. For example, it uses natural language processing (NLP) technology to extract important information from the records, such as "the patient had diabetes in the past."

[1251] The server converts the analysis results into structured data and adds it to the corresponding patient profile, allowing medical professionals to quickly access the information they need.

[1252] 4. Dashboard display

[1253] The server generates dashboard data based on the patient's information and sends the compiled data set to the device, displaying, for example, the patient's real-time heart rate and past diagnostic data on a single screen.

[1254] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[1255] 5. Providing the latest medical information and evidence

[1256] The server collects the latest medical research and evidence from cloud databases, including accessing academic paper APIs and medical databases.

[1257] The server associates the collected medical information with the patient's data and presents applicable treatments and medical findings.

[1258] 6. Predictive analysis and reporting functions

[1259] The server uses generative AI based on past data to predict future disease conditions and treatment outcomes. For example, it analyzes blood glucose level data from the past year to predict future risk of diabetes complications.

[1260] The server generates a data report of the predicted results, sends it to the device, and displays it to medical professionals, who can use the predicted data to adjust treatment plans or intervene early.

[1261] A specific example would be a cardiologist simultaneously viewing information from a patient's heart rate monitor and electronic medical record to determine whether an abnormal heart rate is related to a previous diagnosis. Based on this information, the doctor can quickly make treatment decisions. Generative AI can also be used to predict future disease states and proactively plan patient care.

[1262] In this way, the present invention provides a system that greatly improves the efficiency and accuracy of medical care through medical data integration, real-time analysis, and intuitive information display.

[1263] The processing flow will be explained below.

[1264] Program processing flow

[1265] 1. Data collection and integration

[1266] Step 1:

[1267] The server receives the patient's vital signs (heart rate, blood sugar level, etc.) in real time from the IoT device.

[1268] The server connects to each device and uses an API or dedicated protocol to collect data.

[1269] Step 2:

[1270] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[1271] The server sends a request to the medical institution's system to obtain the required patient data.

[1272] Step 3:

[1273] The server stores the received data in a cloud database and centrally consolidates it.

[1274] The server unifies the data format and organizes each piece of data based on the patient ID.

[1275] 2. Electronic Medical Record Analysis

[1276] Step 1:

[1277] The server begins processing to analyze the text data in the electronic medical record using the generation AI.

[1278] The server preprocesses the text data and removes noise.

[1279] Step 2:

[1280] The server uses natural language processing (NLP) techniques to extract key information and convert it into structured data.

[1281] The server extracts information such as "past diabetes" from the electronic medical record and attaches appropriate tags.

[1282] Step 3:

[1283] The server adds and updates the patient profile with the analysis results.

[1284] The server integrates new medical information into existing profiles and maintains data integrity.

[1285] 3. Dashboard display

[1286] Step 1:

[1287] The server generates dashboard data based on real-time patient data and analysis results.

[1288] The server extracts the data sets and converts them into graphs and charts.

[1289] Step 2:

[1290] The server transmits the generated dashboard data to the terminal.

[1291] The server encrypts the data for transmission and ensures secure communication.

[1292] Step 3:

[1293] The terminal visually displays the received dashboard data.

[1294] The terminal provides an interface that allows the user to easily understand the data.

[1295] 4. Providing the latest medical information and evidence

[1296] Step 1:

[1297] The server accesses a cloud database to collect the latest medical research and evidence.

[1298] The server retrieves the latest information from academic paper APIs and databases.

[1299] Step 2:

[1300] The server integrates the collected information with relevant patient data.

[1301] The server updates patient profiles with the latest treatments and research findings.

[1302] Step 3:

[1303] The device will provide updates to medical professionals with this new information.

[1304] The terminal displays the latest evidence so that the user can easily refer to it.

[1305] 5. Predictive analysis and reporting functions

[1306] Step 1:

[1307] The server uses generative AI to perform predictive analysis based on historical data.

[1308] The server inputs time-series data into an AI model to predict future risks and treatment effects.

[1309] Step 2:

[1310] The server generates the prediction results as a data report.

[1311] The server generates a report containing the predicted results along with a risk assessment and recommended actions.

[1312] Step 3:

[1313] The server transmits the generated forecast report to the terminal.

[1314] The server encrypts and securely transmits the reports.

[1315] Step 4:

[1316] The terminal displays the received prediction report to the medical professional.

[1317] The terminal provides an interface for the user to adjust the treatment plan based on the predicted results.

[1318] Throughout the system, healthcare professionals can leverage real-time, integrated patient data to make more accurate decisions.

[1319] Example 1

[1320] 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."

[1321] Conventional medical data management systems have incomplete integration of patient biometric information and diagnostic results, making it difficult to update and analyze information in real time. Furthermore, important medical information cannot be quickly extracted when analyzing text data from electronic medical records, making it difficult for medical professionals to easily access the information they need. Furthermore, there are insufficient mechanisms for effectively utilizing the latest medical research and evidence in clinical settings, leading to inaccurate predictions of treatment effectiveness and future disease conditions. As a result, there are issues with delays in the formulation of treatment plans and early intervention.

[1322] 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.

[1323] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from the cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means for analyzing the medical information collected from the cloud database and suggesting treatments appropriate for the patient's condition; means for predicting trends in heart rate and blood sugar level based on past data; means for generating the prediction results as a data report and transmitting it to the terminal; and means for the terminal to visually display the data report so that it can be used by medical professionals. This will enable the integration of diverse medical data from different sources, updating and analyzing it in real time, and providing medical professionals with quick access to the information they need. It will also promote the use of the latest medical research and evidence, improving the accuracy of future disease predictions, allowing for the rapid development of treatment plans and early intervention.

[1324] "Biometric information" is data obtained directly from a patient's body, and examples include heart rate, blood pressure, blood sugar level, and body temperature.

[1325] "Diagnostic results" refers to the evaluations and findings obtained through examinations and medical treatment of patients by medical institutions, and specifically includes the contents of medical certificates and test reports.

[1326] A "cloud database" refers to a database service that can be accessed via the Internet and allows for the centralized management and storage of large amounts of data.

[1327] A "patient profile" is a data set that centrally manages individual information about a patient, including medical history, biometric information, and diagnostic results.

[1328] "Generative AI" refers to systems that use artificial intelligence techniques to generate and analyze data, and is particularly used for advanced pattern recognition and predictive analysis.

[1329] An "electronic medical record" refers to a system that electronically records and manages patient medical information at medical institutions, including medical records, prescriptions, test results, etc.

[1330] "Dashboard data" refers to a data set that integrates information obtained from multiple data sources and displays it visually.

[1331] An "interface" is a means of enabling interaction between a user and a system, and includes screens and operating means that users can use intuitively.

[1332] "Medical research" means scientific research activities in the field of medicine, including experiments and investigations aimed at developing new treatments and understanding disease states.

[1333] "Evidence" refers to scientific evidence supporting the effectiveness of a particular medical procedure or treatment.

[1334] "Trend forecasting" refers to an analytical method that predicts future fluctuations and patterns based on past data.

[1335] A "data report" is a report that includes analytical results and forecast information and provides a summary of data for a specific purpose.

[1336] The system of the present invention integrates various medical data and supports advanced medical analysis. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[1337] Data collection

[1338] First, the server has a means to receive patient biometric information and diagnostic results in real time. Specifically, biometric information such as the patient's heart rate, blood pressure, blood glucose level, and body temperature is obtained via an API from IoT devices such as heart rate monitors and blood glucose sensors. Electronic medical record information is also obtained from medical institution systems using the HL7 and FHIR protocols.

[1339] Example: A server receives data from a heart rate monitor every minute and stores it in a database. Electronic medical record data is retrieved periodically using the HL7 protocol.

[1340] Data Integration

[1341] The server stores the received vital signs and diagnostic results in a cloud database, centrally integrating them, organizing data in different formats while maintaining consistency based on patient IDs, and updating patient profiles in real time.

[1342] Example: The server integrates heart rate and blood glucose data into a cloud database and appends it to an existing patient profile.

[1343] Electronic medical record analysis

[1344] The server uses generative AI to analyze the text data in the electronic medical record. It uses natural language processing (NLP) techniques to extract important information and patterns from the records, convert them into structured data, and add them to the patient profile.

[1345] Example: The server inputs the prompt "Extract past diabetes history from the patient's electronic medical record data" into the generative AI model and adds the retrieved information to the patient profile.

[1346] Dashboard View

[1347] The server generates dashboard data based on the patient's information and sends it to the device, which displays a single screen that integrates the patient's real-time heart rate and past diagnostic data.

[1348] The terminal visually displays the received dashboard data and provides an interface for use by medical professionals.

[1349] Example: The server generates dashboard data that combines heart rate data and past diagnostic data and sends it to the device, which displays this data in a graph format, allowing medical professionals to understand the patient's condition at a glance.

[1350] Providing the latest medical information and evidence

[1351] The server collects the latest medical research and evidence from a cloud database, associates it with patient data, analyzes the collected medical information, and suggests treatments appropriate for the patient's condition.

[1352] Example: The server uses the academic journal API to collect the latest research data and associate it with patient profiles to suggest optimal treatment options.

[1353] Predictive analytics and reporting

[1354] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data. The prediction results are generated as a data report and sent to the device, which then visually displays the data report and makes it available to medical professionals.

[1355] Example: The server analyzes blood glucose data from the past year to predict future diabetes risk. A report of the prediction results is sent to the device, which medical professionals can use to adjust treatment plans.

[1356] Prompt Sentence Examples

[1357] "Extract past diabetes history from a patient's electronic medical record data."

[1358] "Based on your heart rate data from the past year, predict your heart rate trend for the next six months."

[1359] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1360] Step 1: Receiving data

[1361] The server receives patient biometric information (heart rate, blood pressure, blood glucose level, body temperature, etc.) from IoT devices via an API. The input is data from the heart rate monitor and blood glucose level sensor, and the output is biometric information stored in a cloud database.

[1362] As a specific example of operation, the server receives the patient's heart rate data every minute through the API and stores it in a cloud database.

[1363] Step 2: Obtain electronic medical record data

[1364] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. The input is HL7 or FHIR format data from the medical institution's system, and the output is electronic medical record information stored in a cloud database.

[1365] As a specific example of operation, the server periodically acquires electronic medical record data from medical institutions every day via a protocol and centrally manages it.

[1366] Step 3: Data Integration

[1367] The server integrates the received biometric information and diagnostic results into a cloud database. The input is the biometric information and electronic medical record information obtained in steps 1 and 2, and the output is unified patient profile data.

[1368] As a specific example of how it works, heart rate data and blood glucose data are integrated into a cloud database and organized based on patient ID.

[1369] Step 4: Data integrity check

[1370] The server checks the integrity of the data and adds new data entries to the existing patient profile. The input is the merged patient profile data and the output is the updated patient profile.

[1371] As a specific example of operation, new heart rate data and diagnostic results are compared with the existing profile, and consistency is confirmed before updating.

[1372] Step 5: Electronic medical record analysis

[1373] The server analyzes the text data of the electronic medical record using a generative AI model. The input is the text data of the electronic medical record, and the output is structured medical information.

[1374] As a specific example of operation, a prompt statement such as "Extract past diabetes history from the patient's electronic medical record data" is input into the generative AI model, and the extracted information is converted into structured data.

[1375] Step 6: Generate dashboard data

[1376] The server generates dashboard data based on the patient information and sends it to the terminal. The input is the updated patient profile data, and the output is the dashboard data for visualization.

[1377] As a specific example of operation, dashboard data that integrates heart rate data and past diagnostic data is generated and sent to the terminal.

[1378] Step 7: View the dashboard

[1379] The terminal visually displays the received dashboard data. The input is the dashboard data sent from the server, and the output is the visualized data as a user interface.

[1380] As a specific example of how it works, the device displays heart rate and past diagnostic data at a glance through graphs and charts.

[1381] Step 8: Providing the latest medical information and evidence

[1382] The server collects the latest medical research and evidence from a cloud database and associates it with patient data. The input is the latest medical research data and patient information, and the output is the associated treatment and medical knowledge.

[1383] As a specific example of how it works, the server uses an academic paper API to collect the latest research data, associates it with patient profiles, and presents applicable treatments.

[1384] Step 9: Predictive analytics

[1385] The server uses a generative AI model based on past data to predict future disease conditions and treatment outcomes. The input is past heart rate and blood sugar data, and the output is a data report of the predicted disease conditions and treatment outcomes.

[1386] As a specific example of how it works, it analyzes blood glucose data from the past year and predicts the risk of future diabetic complications.

[1387] Step 10: Generate and view data reports

[1388] The server generates a data report based on the prediction results and sends it to the terminal, which visually displays the data report and makes it available to medical professionals. The input is the prediction result data, and the output is the visualized data report.

[1389] In a specific example of operation, the server compiles the predicted data into a report and sends it to the device, which then visually displays the report in graphs and text format and allows medical professionals to adjust the treatment plan.

[1390] (Application example 1)

[1391] 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."

[1392] Conventional medical systems have difficulty receiving, integrating, and analyzing patients' vital signs and diagnostic results in real time. Furthermore, there are insufficient means to use generative AI to analyze text data from electronic medical records, extract important medical information, and provide it to medical professionals. In particular, brick-and-mortar stores lack real-time data acquisition and analysis methods for managing customers' health and recommending appropriate treatments. This makes it difficult to provide personalized health advice to customers.

[1393] 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.

[1394] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and sending the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from a cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means, which is installed in smart glasses, for acquiring a customer's biometric information in real time and displaying the analysis results; means for acquiring electronic medical record information using HL7 or FHIR protocols; means for displaying appropriate treatments and health management suggestions on the display of the smart glasses; and means for providing advice based on the latest medical research and evidence. This will enable physical stores to provide personalized health advice to customers in real time.

[1395] "Patient's biological information" refers to physiological data obtained from within the patient's body, such as heart rate, blood pressure, blood sugar level, and body temperature.

[1396] "Diagnosis results" are the results of professional diagnoses or tests conducted by a doctor or medical institution regarding a patient's medical condition or health status.

[1397] A "cloud database" is a database service provided by a remote server that allows data to be stored, managed, and accessed over the Internet.

[1398] A "patient profile" is a set of information that represents the health status of an individual patient, constructed based on medical data such as the patient's biometric information, diagnosis results, and electronic medical records.

[1399] "Generative AI" is an artificial intelligence technique that can generate new information and insights using large datasets and machine learning algorithms.

[1400] An "electronic medical record" is a system that electronically records and manages a patient's medical history, prescriptions, test results, etc.

[1401] "Dashboard data" is a data set that visually organizes patient biometric information and diagnostic results, and displays them in a way that can be understood at a glance.

[1402] A "terminal" is a device that a user operates, and in this case refers to a PC, smartphone, tablet, etc.

[1403] An "interface" is a software or hardware component that provides a screen or means of operation for a user to interact with a system.

[1404] "Medical research" is scientific research conducted with the goal of advancing medical care, understanding disease, and developing treatments.

[1405] "Evidence" refers to data and research results that provide scientific evidence used in the medical field.

[1406] "Predicting future disease states and treatment outcomes" is the process of using past data and generative AI to predict a patient's future health condition and treatment outcomes.

[1407] "Smart glasses" are a wearable eyeglass-type device equipped with a display that can display data in real time and provide information to users.

[1408] The "HL7 and FHIR protocols" are standards for electronically exchanging medical information and are formats and communication protocols that ensure interoperability of medical data.

[1409] "Health management suggestions" involve providing specific advice and recommendations on lifestyle changes, treatment options, etc. to improve a patient's health.

[1410] The system according to the present invention integrates various medical data and realizes advanced medical analysis. Specific embodiments of the present invention will be described below.

[1411] 1. Hardware Configuration

[1412] The system includes the following hardware:

[1413] Server: The central component responsible for data collection, integration, analysis, and cloud database management.

[1414] Smart glasses: A wearable device that allows users to check data in real time and receive appropriate health advice.

[1415] IoT devices: These devices collect patients' vital signs, such as heart rate, blood pressure, and blood sugar levels, in real time.

[1416] Device: The device that provides the data visualization or interface, including computers, smartphones, tablets, etc.

[1417] 2. Software Configuration

[1418] The system uses the following software:

[1419] Python: The language on which the program is based.

[1420] OpenAI API: Generative AI models (e.g., GPT-4) used for natural language processing (NLP).

[1421] Requests (Python library): A library for retrieving data from APIs.

[1422] HL7 / FHIR API: A standard protocol for obtaining electronic medical record information.

[1423] 3. Data Collection and Integration

[1424] The server receives patient biometric information from IoT devices in real time and retrieves electronic medical record information from medical institutions using HL7 and FHIR protocols. These data are integrated and stored in a cloud database, and patient profiles are updated in real time.

[1425] 4. Data Analysis

[1426] The server uses generative AI to parse the text data in the electronic medical record to extract important medical information and patterns, which are then added to the corresponding patient profile and made easily accessible to medical professionals.

[1427] 5. Dashboard generation and display

[1428] The server generates dashboard data based on the patient's information and sends it to the device. The device visualizes the dashboard data and provides an interface for medical professionals to use. The smart glasses collect the patient's biometric information in real time and display the analysis results to provide appropriate health advice to the patient.

[1429] 6. Providing the latest medical information and evidence

[1430] The server collects the latest medical research and evidence from a cloud database and associates the collected medical information with patient data, thereby suggesting applicable treatments and medical findings.

[1431] 7. Predictive Analytics and Reporting

[1432] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data, and the results are generated as a data report, which is sent to the device and displayed to medical professionals.

[1433] Specific examples

[1434] For example, when a customer visits a pharmacy, the smart glasses can be used to check their heart rate and past diagnostic information, and provide them with on-the-spot medication and health advice.

[1435] Prompt Sentence Examples

[1436] Patient data: {"physiological_data": {"heart_rate": 85, "blood_pressure": "120 / 80", "blood_sugar": 110}, "medical_records": {"condition": "hypertension", "medication": ["Drug A", "Drug B"]}}.

[1437] Provide a summary and recommendations.

[1438] This will enable physical stores to provide personalized health advice to customers in real time.

[1439] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1440] Step 1:

[1441] Collecting patient vital signs in real time

[1442] The server receives real-time biometric information such as heart rate, blood pressure, and blood sugar levels from IoT devices. Specifically, it periodically acquires data sent from IoT devices using an API and stores it in a cloud database.

[1443] Input: Biometric data from IoT devices

[1444] Output: Biometric information stored in a cloud database

[1445] Step 2:

[1446] Obtain electronic medical record information

[1447] The server retrieves electronic medical record information from medical institutions' systems using the HL7 or FHIR protocol. Specifically, based on the specified protocol, it extracts information such as patient diagnosis results and past medical history from the medical institution's database and integrates it into a cloud database.

[1448] Input: Electronic medical record information from medical institutions

[1449] Output: Electronic medical record information stored in a cloud database

[1450] Step 3:

[1451] Data integration and profile updates

[1452] The server integrates the received vital signs and electronic medical records into a cloud database and updates patient profiles in real time. Specifically, it organizes different types of data for each patient and adds them to the existing data profile.

[1453] Input: Biometric information and electronic medical record information

[1454] Output: Updated patient profile

[1455] Step 4:

[1456] Using generative AI to analyze text data from electronic medical records

[1457] The server uses generative AI (e.g., OpenAI's GPT-4) to analyze the text data of the electronic medical record and extract important medical information and patterns. Specifically, the server supplies the text data of the electronic medical record and obtains the extracted important information as the output of the AI ​​model.

[1458] Input: Text data from electronic medical records

[1459] Output: Extracted important medical information

[1460] Step 5:

[1461] Adding analysis results to patient profiles

[1462] The server adds the key medical information extracted by the generative AI to the corresponding patient profile, making it easily accessible to medical professionals.

[1463] Input: Extracted vital medical information

[1464] Output: Updated patient profile

[1465] Step 6:

[1466] Generate dashboard data and send it to the device

[1467] The server generates dashboard data based on the patient's information and sends it to the terminal. Specifically, it extracts the necessary data from the patient profile, converts it into a visually easy-to-understand format, and generates the dashboard.

[1468] Input: Patient Profile

[1469] Output: Generated dashboard data

[1470] Step 7:

[1471] The device visualizes the dashboard data and provides it as an interface.

[1472] The device visualizes the transmitted dashboard data and provides a user-friendly interface for medical professionals, displaying key patient information in the form of graphs and charts.

[1473] Input: Submitted dashboard data

[1474] Output: Visualized dashboard

[1475] Step 8:

[1476] Collect the latest medical research and evidence and link it to patient data

[1477] The server collects the latest medical research and evidence from a cloud database and associates it with patient data, specifically retrieving the latest information from academic paper databases and medical information platforms, and reflecting it in patient profiles.

[1478] Input: Latest medical research and evidence

[1479] Output: Updated patient profile

[1480] Step 9:

[1481] Using generative AI to predict future disease states and treatment outcomes

[1482] The server uses generative AI based on past data to predict future medical conditions and treatment outcomes. Specifically, it analyzes past biometric information and diagnostic result data to predict future health risks and treatment outcomes.

[1483] Input: Past vital signs and diagnostic results data

[1484] Output: Predicted future disease status and treatment effects

[1485] Step 10:

[1486] The application installed on the smart glasses collects the customer's biometric information in real time and displays the analysis results.

[1487] The application installed on the smart glasses collects the customer's biometric information in real time and displays the results analyzed by the generative AI. Specifically, the glasses display shows treatment and health management suggestions, providing appropriate advice to the user.

[1488] Input: Customer's biometric information and the analysis results of the generated AI

[1489] Output: Health advice displayed on smart glasses

[1490] Step 11:

[1491] Displaying appropriate treatment and health management suggestions on the smart glasses display

[1492] The smart glasses will then display appropriate treatment and health management suggestions based on the analysis results, allowing users to receive specific advice in real time.

[1493] Input: Analysis results

[1494] Output: Displayed treatment and health management suggestions

[1495] Step 12:

[1496] Providing the latest medical research and evidence-based advice

[1497] The server provides users with appropriate advice based on the latest medical research and evidence collected, specifically suggesting optimal treatments and health management based on the latest medical information linked to patient data.

[1498] Input: Latest medical research and evidence

[1499] Output: Advice provided

[1500] 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.

[1501] The system of the present invention not only integrates, analyzes, and visualizes medical data, but also recognizes the user's emotions and adjusts the interface based on those emotions to provide more optimal medical support. The following describes embodiments of the present invention and specific examples thereof.

[1502] 1. Data Collection

[1503] The server receives patient vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time from IoT devices, which transmit data using APIs or dedicated protocols.

[1504] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol and obtains the necessary diagnostic results and case notes.

[1505] 2. Data Integration

[1506] The server integrates and stores the received biometric information and diagnostic results in a cloud database, standardizing the data format and organizing each piece of data based on patient ID.

[1507] The server checks the integrity of the data and updates existing patient profiles in real time.

[1508] 3. Electronic Medical Record Analysis

[1509] The server uses generative AI to analyze the text data in the electronic medical records and extract important information, such as "past diabetes," using natural language processing (NLP) technology to extract information and convert it into structured data.

[1510] The server adds and updates the patient profile with the analysis results, allowing medical professionals to quickly access the information they need.

[1511] 4. Dashboard display

[1512] The server generates dashboard data based on the patient's information and sends the compiled data set to the terminal.

[1513] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[1514] 5. Providing the latest medical information and evidence

[1515] The server collects the latest medical research and evidence from a cloud database, obtains the latest information from academic paper APIs and databases, and reflects it in patient data.

[1516] The device provides medical professionals with the latest collected information to aid in diagnosis and treatment planning.

[1517] 6. Predictive analysis and reporting functions

[1518] The server uses generative AI to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes, and generates a data report of the results, which is sent to the device and displayed to medical professionals.

[1519] The device provides an interface for adjusting treatment plans and conducting early intervention based on the received predictive report.

[1520] 7. Incorporating an Emotional Engine

[1521] The server incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state, for example, recognizing emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis.

[1522] The server then reflects the emotional data obtained from the emotion engine in the dashboard data, allowing medical professionals to make comprehensive judgments that take into account their own emotional state.

[1523] The device adjusts the interface display and operation based on the user's emotions: for example, if a medical professional is feeling highly stressed, the system will automatically change the screen layout and highlight important information.

[1524] Examples:

[1525] The server receives data in real time from heart rate monitors and blood glucose sensors, stores it in a cloud database, and consolidates it.

[1526] The server analyzes electronic medical records to determine whether the patient has had diabetes in the past and adds this information to the patient profile.

[1527] The device generates a dashboard that visually displays the patient's overall health status and diagnostic results.

[1528] The server uses an emotion engine to analyze the emotional state of the medical professional as they view the dashboard: for example, if the professional is feeling anxious, the system will highlight important information more prominently.

[1529] The device adjusts the interface display based on the patient's emotional state, helping medical professionals make efficient decisions.

[1530] The entire system empowers healthcare professionals with real-time, integrated patient data for fast and accurate decision-making in an interface optimized for the user's emotional state.

[1531] The processing flow will be explained below.

[1532] Program processing flow

[1533] 1. Data collection and integration

[1534] Step 1:

[1535] The server receives the patient's vital signs (heart rate, blood pressure, blood sugar level, etc.) in real time from the IoT device.

[1536] The server collects data from each device through an API and checks the integrity of the data received.

[1537] Step 2:

[1538] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[1539] The server sends the request, extracts the corresponding data, and converts the format.

[1540] Step 3:

[1541] The server integrates and stores the received biometric information and electronic medical record data in a cloud database.

[1542] The server organizes each piece of data based on the patient ID and creates a database entry for centralized management.

[1543] 2. Electronic Medical Record Analysis

[1544] Step 1:

[1545] The server analyzes the text data in the electronic medical records using generative AI (natural language processing technology).

[1546] The server preprocesses the text data of the electronic medical records, removes noise, and performs morphological analysis.

[1547] Step 2:

[1548] The server uses generative AI to extract important medical information and patterns.

[1549] The server detects important information, such as "past diabetes," and tags and converts that information into structured data.

[1550] Step 3:

[1551] The server adds the analysis results to the patient profile and integrates them with existing data.

[1552] The server updates the database and adds the extracted medical information.

[1553] 3. Dashboard display

[1554] Step 1:

[1555] The server creates dashboard data based on the patient's real-time biometric information and analysis results.

[1556] The server transforms the data into graphs and charts and generates a data set for the dashboard.

[1557] Step 2:

[1558] The server transmits the generated dashboard data to the terminal.

[1559] The server encrypts the data to ensure secure transmission and transmits it using HTTPS.

[1560] Step 3:

[1561] The terminal visually displays the received dashboard data.

[1562] The device uses graphs and charts to make the information easy for medical professionals to understand.

[1563] 4. Providing the latest medical information and evidence

[1564] Step 1:

[1565] The server accesses a cloud database to collect the latest medical research and evidence.

[1566] The server sends requests to retrieve information from academic paper APIs and medical databases.

[1567] Step 2:

[1568] The server integrates the collected medical information with the patient's data.

[1569] The server adds the latest evidence to the patient's profile and suggests applicable treatments.

[1570] Step 3:

[1571] The terminal displays an interface that provides the medical professional with the latest collected information.

[1572] The terminal provides visualization options where appropriate to allow the user to easily view the new information.

[1573] 5. Predictive analysis and reporting functions

[1574] Step 1:

[1575] The server uses generative AI to perform predictive analysis based on past data.

[1576] The server inputs time-series data into an AI model to predict future disease conditions and treatment outcomes.

[1577] Step 2:

[1578] The server generates the prediction results as a data report.

[1579] The server generates a report containing the predicted results, risk assessment, and recommended actions.

[1580] Step 3:

[1581] The server transmits the generated data report to the terminal.

[1582] The server encrypts the data reports and transmits them over a secure channel.

[1583] Step 4:

[1584] The terminal displays the received prediction report to the medical professional.

[1585] The terminal provides an interface that allows the user to review predicted results and adjust the treatment plan.

[1586] 6. Use of Emotion Engines

[1587] Step 1:

[1588] The terminal activates an emotion engine to recognize the emotions of the user (medical professional).

[1589] The device recognizes the user's facial expressions and analyzes their voice to determine their emotional state.

[1590] Step 2:

[1591] The server receives the emotion data obtained from the emotion engine and reflects it in the dashboard data.

[1592] The server analyzes and prepares the necessary data to adjust the interface according to the user's emotional state.

[1593] Step 3:

[1594] The device adjusts the interface display and operation method based on the emotional state.

[1595] If the user is feeling stressed, the device will highlight important information or change the screen layout.

[1596] Examples:

[1597] The server receives data in real time from the heart rate monitor and blood glucose sensor, stores it in a cloud database, and consolidates it.

[1598] The server adds information extracted from the electronic medical record, such as "past diabetes," to the patient profile and updates the database.

[1599] The device generates a dashboard that visually displays the patient's overall health status and diagnostic results.

[1600] The server uses an emotion engine to analyze the emotional state of the medical professional as he or she reviews the dashboard.

[1601] If the user feels anxious, the device will automatically highlight important information and change the screen layout to optimize the user experience.

[1602] This will enable healthcare professionals to make faster and more accurate decisions through integrated medical data and an optimized user interface.

[1603] Example 2

[1604] 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."

[1605] Traditional medical systems do not integrate patients' vital signs and diagnostic results in real time, making it difficult for medical professionals to access information quickly. They also do not take into account the patient's emotional state, potentially resulting in a decline in the quality of medical care. Furthermore, it is difficult to predict future disease conditions and treatment outcomes, limiting diagnostic and treatment planning.

[1606] 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.

[1607] In this invention, the server includes: means for receiving patient biometric information and diagnostic results in real time; means for storing and centrally integrating the patient biometric information and diagnostic results in a cloud database; means for updating patient profiles in real time based on the integrated data; means for analyzing text data from electronic medical records using a generative AI to extract important medical information and patterns; means for adding the analysis results to the corresponding patient profile for easy access by medical professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from a cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment outcomes based on past data using a generative AI; means for recognizing and analyzing a user's emotional state and reflecting the emotional data in the interface; and means for adjusting the interface based on the user's emotional state. This enables centralized management of patient biometric information and diagnostic results, real-time information updates, and predictive analysis based on patient data. Furthermore, adjusting the interface to take the user's emotional state into account is expected to improve the quality of medical care.

[1608] "Patient's vital signs" refers to data that indicates the patient's physical condition, such as heart rate, blood pressure, and blood sugar level.

[1609] "Diagnosis" means the result of a diagnosis made by a medical professional and is information related to a patient's medical condition and treatment plan.

[1610] "Cloud database" refers to a database stored on a remote server accessible via the Internet.

[1611] "Integrating" refers to the process of combining data collected from different sources into one database.

[1612] A "patient profile" refers to a data set that compiles medical information about an individual patient, such as biometric information, diagnostic results, and treatment history.

[1613] "Generative AI" refers to artificial intelligence technology that uses machine learning and deep learning algorithms to analyze data and generate new information and predictions.

[1614] "Electronic medical record text data" refers to the text information of an electronically recorded medical record.

[1615] "Dashboard Data" refers to data that has been processed to visually display consolidated patient information.

[1616] "Terminal" refers to a device, such as a text editor, with computer graphics used by a healthcare professional to view and manipulate information.

[1617] "Interface" refers to the screen and operation method used by users to operate software or hardware.

[1618] "The latest medical research and evidence" refers to medical information and evidence obtained through recent scientific research and clinical trials.

[1619] "Predictive analytics" refers to the process of predicting and analyzing future disease conditions and treatment outcomes based on past data.

[1620] "Emotion engine" refers to software technology for recognizing and analyzing a user's emotional state from their facial expressions and voice.

[1621] "Interface adjustment" refers to the process of changing the operating screen and display content based on the user's emotional state.

[1622] The system of the present invention receives, integrates, analyzes, and visualizes the patient's vital signs and diagnostic results in real time, and also recognizes the user's emotions and adjusts the interface to provide more optimal medical support. Specific embodiments of the present invention are described below.

[1623] Data collection

[1624] The server receives the patient's vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time. This data is sent from IoT devices using APIs or dedicated protocols. For example, when receiving data from a heart rate monitor or blood glucose sensor, the server obtains heart rate data of 70 bpm via an HTTP request and stores it in a cloud database.

[1625] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. This allows it to collect diagnosis results and case records. For example, it retrieves information such as "Diabetes: positive" from "Patient ID: 1234" via the FHIR protocol.

[1626] Data Integration

[1627] The server integrates the collected vital signs and diagnostic results into a cloud database. The data format is standardized and each data item is organized based on the patient ID. For example, the data is stored in the database in a standardized JSON format as "Patient ID: 1234, heart_rate: 70 bpm, blood_pressure: 120 / 80, diabetes_history: positive."

[1628] The server checks the data for consistency and updates the patient profile in real time: for example, if the heart rate is an unrealistic value (such as 0 bpm or 300 bpm), the data is invalidated.

[1629] Electronic medical record analysis

[1630] The server uses a generative AI model to analyze the text data in the electronic medical record and extract important information. It uses natural language processing (NLP) technology to extract information such as "past diabetes" and convert it into structured data. For example, text such as "The patient had diabetes in the past" is converted into structured data as "diabetes_history: positive."

[1631] The server adds the extracted information to and updates the patient profile, allowing medical professionals to quickly access the information they need.

[1632] Dashboard View

[1633] The server generates dashboard data based on the patient information and sends it to the terminal in a format such as "Patient ID: 1234, chart_data: ...".

[1634] The device visually displays the received dashboard data, allowing medical professionals to see important information at a glance through graphs and charts. For example, it generates graphs such as "Heart Rate Trend" and "Blood Glucose Chart" and updates the dashboard.

[1635] Providing the latest medical information and evidence

[1636] The server collects the latest medical research and evidence from a cloud database. It retrieves the latest information from academic paper APIs and databases and reflects it in patient data. For example, it searches the database with the query "latest diabetes treatments" to retrieve the latest paper information.

[1637] The device then provides medical professionals with the latest information it has collected to aid in diagnosis and treatment planning, for example by notifying them that "five new diabetes treatments have been discovered."

[1638] Predictive analytics and reporting

[1639] The server uses the generative AI model to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes. For example, it sends a query to the generative AI model, such as "Predict blood glucose fluctuations over the next six months for patient ID: 1234," and obtains the predicted results.

[1640] The server generates a data report of the prediction results and sends it to the device. Medical professionals can use this information to adjust their diagnosis and treatment plan. For example, a "blood glucose prediction report for the next six months" can be generated in PDF format and sent to the device.

[1641] Incorporating an emotion engine

[1642] The server uses an emotion engine to analyze the user's emotional state. For example, it recognizes emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis. It analyzes facial expression data and voice data acquired through a camera and microphone and determines the user's "stress level: high."

[1643] The server reflects the emotional data in the dashboard data, which enables comprehensive judgment. For example, data such as "emotional state: high stress level" can be integrated into the dashboard data.

[1644] The device adjusts the interface display based on the user's emotions. For example, if a medical professional is feeling highly stressed, important information will be highlighted. Based on the emotional data, important information will be highlighted with a red frame.

[1645] Prompt Sentence Examples

[1646] Use the following parameters to generate dashboard content that can be easily understood by healthcare professionals.

[1647] Parameters: Patient ID, heart rate, blood pressure, blood glucose, past medical history, latest diagnosis

[1648] Generative AI models should use natural language processing to extract key information, such as "past diabetes," and provide it as structured data, and also adapt the interface based on the user's emotional state.

[1649] The entire system empowers healthcare professionals with real-time, integrated patient data to make fast and accurate decisions with an interface optimized for the user's emotional state.

[1650] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1651] Step 1: Data collection

[1652] The server receives real-time patient vital signs from IoT devices such as heart rate monitors and blood glucose sensors, which are transmitted using APIs and proprietary protocols.

[1653] Input: Biometric information such as heart rate, blood pressure, and blood sugar level

[1654] Data processing: The server converts the received data into an appropriate format and stores it in a cloud database.

[1655] Output: Formatted biometric data

[1656] Specific operation:

[1657] The server receives an HTTP request from the heart rate monitor and stores the heart rate of 70 bpm in a cloud database in JSON format.

[1658] Step 2: Obtaining electronic medical record information

[1659] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[1660] Input: Patient ID, electronic medical record information

[1661] Data processing: The server analyzes the acquired medical record information, extracts diagnostic results and case records, and stores them in a database.

[1662] Output: Analyzed medical record information

[1663] Specific operation:

[1664] The server queries the diagnosis results for "Patient ID: 1234" using the FHIR protocol and integrates the obtained "Diabetes: positive" information into the database.

[1665] Step 3: Data Integration

[1666] The server integrates the biometric information and diagnostic results into a cloud database.

[1667] Input: Biometric information, diagnosis results

[1668] Data processing: The server standardizes the data format and organizes each data based on the patient ID.

[1669] Output: Unified patient data

[1670] Specific operation:

[1671] The server stores the data in a database in the format "Patient ID: 1234, heart_rate: 70 bpm, blood_pressure: 120 / 80, diabetes_history: positive".

[1672] Step 4: Check data integrity

[1673] The server checks the integrity of the merged data and eliminates inconsistent data.

[1674] Input: Unified patient data

[1675] Data calculation: The server checks the data format and outliers.

[1676] Output: consistent data

[1677] Specific operation:

[1678] The server detects unrealistic heart rate data such as 0 bpm or 300 bpm and rejects it as inconsistent data.

[1679] Step 5: Electronic medical record analysis

[1680] The server uses a generative AI model to analyze the text data in the electronic medical record and extract key information.

[1681] Input: Electronic medical record text data

[1682] Data calculation: Using natural language processing technology, information such as "past diabetes" is extracted from text and converted into structured data.

[1683] Output: Structured important information

[1684] Specific operation:

[1685] The server converts text such as "The patient had diabetes in the past" as "diabetes_history: positive".

[1686] Step 6: Update the patient profile

[1687] The server adds and updates the patient profile with the analysis results.

[1688] Input: Structured critical information

[1689] Data calculations: Add new information to an existing patient profile.

[1690] Output: Updated patient profile

[1691] Specific operation:

[1692] The server adds the "Past History of Diabetes" data to the profile and updates it as "Patient ID: 1234, diabetes_history: positive".

[1693] Step 7: Generate dashboard data

[1694] The server generates dashboard data based on the patient's information and sends it to the terminal.

[1695] Input: Patient profile data

[1696] Data processing: Converting data into a visualizable format.

[1697] Output: Dashboard data

[1698] Specific operation:

[1699] The server sends the dashboard data to the terminal in the format "Patient ID: 1234, chart_data: ...".

[1700] Step 8: View the Dashboard

[1701] The terminal visually displays the received dashboard data.

[1702] Input: Dashboard data

[1703] Data processing: Display the data using visualization tools.

[1704] Output: Visualized information

[1705] Specific operation:

[1706] The device generates graphs such as "heart rate trend" and "blood glucose chart" and updates the dashboard.

[1707] Step 9: Gather the latest medical information

[1708] The server collects the latest medical research and evidence from a cloud database.

[1709] Input: Query, medical information database

[1710] Data Calculation: The server uses the specified query to extract the latest information.

[1711] Output: Latest medical information

[1712] Specific operation:

[1713] The server searches the database using the keyword "latest diabetes treatments" to obtain new paper information.

[1714] Step 10: Provide medical information

[1715] The device displays the latest collected medical information to medical professionals to aid in diagnosis and treatment planning.

[1716] Input: Latest medical information

[1717] Data processing: Converting information into a user-friendly format for display.

[1718] Output: Medical information displayed

[1719] Specific operation:

[1720] The device notifies the user that "five new diabetes treatments have been discovered" and displays details.

[1721] Step 11: Perform predictive analysis

[1722] The server uses a generative AI model to perform predictive analysis based on historical data.

[1723] Input: Historical Patient Data

[1724] Data calculation: Predicting future disease conditions and treatment outcomes from past data.

[1725] Output: Prediction result data

[1726] Specific operation:

[1727] The server sends a query to the generative AI model saying, "Predict blood glucose fluctuations for the next 6 months for patient ID: 1234" and obtains the prediction results.

[1728] Step 12: Generate forecast data reports

[1729] The server generates a data report based on the prediction results and sends it to the terminal.

[1730] Input: Prediction result data

[1731] Data processing: Compile the prediction results into a report format.

[1732] Output: Data report

[1733] Specific operation:

[1734] The server generates a "blood glucose prediction report for the next six months" in PDF format and sends it to the terminal.

[1735] Step 13: Emotion Engine Analysis

[1736] The server uses an emotion engine to analyze the user's emotional state.

[1737] Input: facial expression and voice data from camera and microphone

[1738] Data Computation: Analyze emotional states using an emotion engine.

[1739] Output: Emotion data

[1740] Specific operation:

[1741] The server analyzes facial expression and voice data acquired through the camera and microphone and determines the "stress level: high."

[1742] Step 14: Reflecting Emotional Data

[1743] The server reflects the emotion data on the dashboard.

[1744] Input: Emotion data

[1745] Data processing: Integrating sentiment data into dashboard data.

[1746] Output: Dashboard data after reflecting emotions

[1747] Specific operation:

[1748] The server consolidates and displays data such as "Emotional state: High stress level" on a dashboard.

[1749] Step 15: Adjusting the Interface

[1750] The terminal adjusts the display content of the interface based on the user's emotional state.

[1751] Input: Dashboard data after reflecting emotions

[1752] Data processing: Adjusting the interface, such as highlighting important information.

[1753] Output: Adjusted interface

[1754] Specific operation:

[1755] If the device determines that your stress level is high, it will highlight important information in a red frame.

[1756] (Application example 2)

[1757] 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."

[1758] Current medical support systems lack the ability to not only integrate and analyze patients' biometric information and diagnostic results, but also adjust their interfaces based on the user's emotional state. This makes it difficult for medical professionals to make quick and accurate decisions, even in stressful situations. Furthermore, there is a need for an efficient way to display important information in emergency situations. To solve these issues, a mechanism is needed to collect user emotional data in real time and adjust the interface appropriately.

[1759] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving patient biometric information and diagnostic results in real time, means for storing and centrally integrating the patient biometric information and diagnostic results in a cloud database, means for updating the patient profile in real time based on the integrated data, means for analyzing text data in the electronic medical record using a generating AI to extract important medical information and patterns, means for adding the analysis results to the corresponding patient profile so that medical professionals can easily access it, means for generating dashboard data based on the patient information and transmitting the dashboard data to a terminal, means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals, means for collecting the latest medical research and evidence from a cloud database, means for associating the collected medical information with patient data, means for predicting future medical conditions and treatment effects based on past data using a generating AI, means for collecting user emotional data in real time, and means for adjusting the interface based on the collected emotional data. This enables appropriate information display and interface adjustment according to the user's emotional state, enabling medical professionals to make quick and accurate decisions even in stressful situations.

[1760] "Biometric information" refers to data on a patient's physical condition, such as heart rate, blood pressure, and blood sugar level, obtained in real time.

[1761] "Diagnosis results" are data obtained as a result of a diagnosis made to a patient by a medical institution, and are information recorded in an electronic medical record.

[1762] A "cloud database" refers to data stored on remote servers accessible over the internet, and is often used to store medical information.

[1763] A "patient profile" is an integrated data set that includes a patient's biometric information, diagnostic results, and medical history.

[1764] "Generative AI" is a type of artificial intelligence technology that refers to algorithms that analyze data and make predictions using models trained for specific purposes.

[1765] An "electronic medical record" is a patient's medical record stored in digital format, and refers to a record of diagnosis and treatment within a medical institution.

[1766] "Dashboard data" is summary data configured to visually display information aggregated from multiple data sources.

[1767] A "terminal" is a device that a user uses to check data or information, and includes a PC, tablet, smartphone, etc.

[1768] "State-of-the-art medical research" refers to ongoing or recently completed research and results in the field of medicine.

[1769] "Evidence" refers to scientific evidence that serves as the basis for medical treatment and diagnosis in the medical field.

[1770] "Emotion data" is information about the emotional state extracted from the user's facial expressions, voice, behavior, etc.

[1771] "Interface adjustment" refers to changing the display and operation method of the system used by the user based on the user's emotional state.

[1772] To implement this invention, the following system configuration is required: This system integrates the patient's biometric information and diagnostic results, and incorporates the user's emotional data to assist medical professionals in making quick and effective decisions.

[1773] 1. Data collection and integration

[1774] The server receives patient vital signs (heart rate, blood pressure, blood glucose level, etc.) in real time from IoT devices, which transmit data using APIs or dedicated protocols.

[1775] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol and receives the necessary diagnostic results and case notes.

[1776] The server integrates and stores the received biometric information and diagnostic results in a cloud database, standardizing the data format and organizing each piece of data based on patient ID.

[1777] 2. Electronic Medical Record Analysis

[1778] The server uses generative AI to analyze the text data in the electronic medical records and extract important information, such as "past diabetes," using natural language processing (NLP) technology to extract information and convert it into structured data.

[1779] 3. Dashboard display

[1780] The server generates dashboard data based on the patient's information and sends the compiled data set to the terminal.

[1781] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[1782] 4. Providing the latest medical information and evidence

[1783] The server collects the latest medical research and evidence from a cloud database, obtains the latest information from academic paper APIs and databases, and reflects it in patient data.

[1784] The device provides medical professionals with the latest collected information to aid in diagnosis and treatment planning.

[1785] 5. Predictive analytics and reporting

[1786] The server uses generative AI to perform predictive analysis based on past data to predict future disease conditions and treatment outcomes, and generates a data report of the results, which is sent to the device and displayed to medical professionals.

[1787] 6. Incorporating an Emotional Engine

[1788] The server incorporates an emotion engine that recognizes the user's emotions and analyzes their emotional state, for example, recognizing emotions from facial expressions and voice when a medical professional confirms a patient's diagnosis.

[1789] The device adjusts the interface and controls based on the user's emotions: if a medical professional is feeling stressed, the system automatically changes the screen layout and highlights important information.

[1790] Specific examples

[1791] For example, if a medical professional is stressed during an emergency, the displayed dashboard data will automatically highlight important information, allowing for a quicker response, while if the medical professional remains calm, the normal interface will be displayed.

[1792] Prompt Sentence Examples

[1793] Please provide a concrete example of a system that collects user sentiment data in real time and adjusts the interface accordingly. Also explain how the data is stored with a timestamp and used to generate dashboard data.

[1794] This system configuration allows healthcare professionals to make fast and accurate decisions using real-time integrated patient data and an interface that adapts to the user's emotional state.

[1795] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1796] Step 1:

[1797] Data collection

[1798] The server receives the patient's vital signs (heart rate, blood pressure, blood glucose level, etc.) from the IoT device in real time. The data is sent via API or dedicated communication protocol. The input is the vital signs from the IoT device, and the output is the raw data for integration.

[1799] Step 2:

[1800] Acquisition of electronic medical record information

[1801] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. The input is diagnosis results and case notes from the medical institution's system, and the output is raw data for storing this information.

[1802] Step 3:

[1803] Data Integration and Storage

[1804] The server integrates and stores the received biometric information and diagnostic results in a cloud database. The data format is standardized and each data item is organized based on the patient ID. The input is raw data of biometric information and diagnostic results, and the output is integrated patient profile data.

[1805] Step 4:

[1806] Electronic medical record analysis

[1807] The server uses generative AI to analyze the text data in the electronic medical record. It uses natural language processing (NLP) technology to extract information such as "past diabetes" and convert it into structured data. The input is the text data of the raw medical record, and the output is the analyzed structured data.

[1808] Step 5:

[1809] Generate dashboard data

[1810] The server generates dashboard data based on patient information. The generated data is sent to the terminal. The input is the integrated patient profile data and analysis results, and the output is the dashboard data for visualization.

[1811] Step 6:

[1812] Dashboard View

[1813] The terminal visually displays the received dashboard data, allowing medical professionals to see important information at a glance through graphs and charts. The input is the dashboard data sent from the server, and the output is the visualized data.

[1814] Step 7:

[1815] Obtaining the latest medical information

[1816] The server collects the latest medical research and evidence from a cloud database. It obtains the latest information from academic paper APIs and databases and reflects this information in patient data. The input is the latest information from academic paper APIs and databases, and the output is an updated patient profile.

[1817] Step 8:

[1818] Predictive Analytics and Reporting

[1819] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data. The prediction results are generated as a data report and sent to the device. The input is the past data and the generative AI model, and the output is a data report containing the prediction results.

[1820] Step 9:

[1821] Collecting Emotional Data

[1822] The server uses an emotion engine to collect user emotion data in real time. For example, it recognizes emotions from facial expressions and voice when a medical professional confirms diagnostic information. The input is the user's facial expression data and voice data, and the output is data indicating the user's emotional state.

[1823] Step 10:

[1824] Interface adjustments

[1825] The device adjusts the interface display and operation based on the collected emotional data. If the medical professional is feeling stressed, the system automatically changes the screen layout and highlights important information. The input is data indicating the emotional state, and the output is an adjusted interface.

[1826] In this way, the object of the invention is achieved by collecting, analyzing, and integrating data at each processing step, and performing a series of processes that provide information in the most optimal form for the user.

[1827] 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.

[1828] 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.

[1829] 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.

[1830] [Fourth embodiment]

[1831] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1832] 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.

[1833] 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).

[1834] 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.

[1835] 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.

[1836] 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).

[1837] 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.

[1838] 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.

[1839] 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.

[1840] 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.

[1841] 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.

[1842] 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.

[1843] 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."

[1844] The system of the present invention integrates various medical data and supports advanced medical analysis. The following describes embodiments of the present invention and specific examples thereof.

[1845] 1. Data Collection

[1846] The server receives real-time biological information from the patient's body (e.g., heart rate, blood pressure, blood glucose level, temperature, etc.) from IoT devices and medical institution systems. For example, when receiving data from a heart rate monitor or blood glucose level sensor, this data is sent through an API.

[1847] The server retrieves electronic medical record information from medical institutions' systems using HL7 or FHIR protocols, allowing it to centrally manage the necessary diagnostic results and case records in real time.

[1848] 2. Data Integration

[1849] The server integrates and stores the received vital signs and diagnostic results in a cloud database, which allows data in different formats to be organized and centralized based on patient IDs.

[1850] The server checks data integrity and updates existing patient profiles in real time, adding new data entries and linking them to historical data.

[1851] 3. Electronic Medical Record Analysis

[1852] The server uses generative AI to analyze the text data in the electronic medical records. For example, it uses natural language processing (NLP) technology to extract important information from the records, such as "the patient had diabetes in the past."

[1853] The server converts the analysis results into structured data and adds it to the corresponding patient profile, allowing medical professionals to quickly access the information they need.

[1854] 4. Dashboard display

[1855] The server generates dashboard data based on the patient's information and sends the compiled data set to the device, displaying, for example, the patient's real-time heart rate and past diagnostic data on a single screen.

[1856] The device visually displays the received dashboard data, allowing medical professionals to see key information at a glance through graphs and charts.

[1857] 5. Providing the latest medical information and evidence

[1858] The server collects the latest medical research and evidence from cloud databases, including accessing academic paper APIs and medical databases.

[1859] The server associates the collected medical information with the patient's data and presents applicable treatments and medical findings.

[1860] 6. Predictive analysis and reporting functions

[1861] The server uses generative AI based on past data to predict future disease conditions and treatment outcomes. For example, it analyzes blood glucose level data from the past year to predict future risk of diabetes complications.

[1862] The server generates a data report of the predicted results, sends it to the device, and displays it to medical professionals, who can use the predicted data to adjust treatment plans or intervene early.

[1863] A specific example would be a cardiologist simultaneously viewing information from a patient's heart rate monitor and electronic medical record to determine whether an abnormal heart rate is related to a previous diagnosis. Based on this information, the doctor can quickly make treatment decisions. Generative AI can also be used to predict future disease states and proactively plan patient care.

[1864] In this way, the present invention provides a system that greatly improves the efficiency and accuracy of medical care through medical data integration, real-time analysis, and intuitive information display.

[1865] The processing flow will be explained below.

[1866] Program processing flow

[1867] 1. Data collection and integration

[1868] Step 1:

[1869] The server receives the patient's vital signs (heart rate, blood sugar level, etc.) in real time from the IoT device.

[1870] The server connects to each device and uses an API or dedicated protocol to collect data.

[1871] Step 2:

[1872] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol.

[1873] The server sends a request to the medical institution's system to obtain the required patient data.

[1874] Step 3:

[1875] The server stores the received data in a cloud database and centrally consolidates it.

[1876] The server unifies the data format and organizes each piece of data based on the patient ID.

[1877] 2. Electronic Medical Record Analysis

[1878] Step 1:

[1879] The server begins processing to analyze the text data in the electronic medical record using the generation AI.

[1880] The server preprocesses the text data and removes noise.

[1881] Step 2:

[1882] The server uses natural language processing (NLP) techniques to extract key information and convert it into structured data.

[1883] The server extracts information such as "past diabetes" from the electronic medical record and attaches appropriate tags.

[1884] Step 3:

[1885] The server adds and updates the patient profile with the analysis results.

[1886] The server integrates new medical information into existing profiles and maintains data integrity.

[1887] 3. Dashboard display

[1888] Step 1:

[1889] The server generates dashboard data based on real-time patient data and analysis results.

[1890] The server extracts the data sets and converts them into graphs and charts.

[1891] Step 2:

[1892] The server transmits the generated dashboard data to the terminal.

[1893] The server encrypts the data for transmission and ensures secure communication.

[1894] Step 3:

[1895] The terminal visually displays the received dashboard data.

[1896] The terminal provides an interface that allows the user to easily understand the data.

[1897] 4. Providing the latest medical information and evidence

[1898] Step 1:

[1899] The server accesses a cloud database to collect the latest medical research and evidence.

[1900] The server retrieves the latest information from academic paper APIs and databases.

[1901] Step 2:

[1902] The server integrates the collected information with relevant patient data.

[1903] The server updates patient profiles with the latest treatments and research findings.

[1904] Step 3:

[1905] The device will provide updates to medical professionals with this new information.

[1906] The terminal displays the latest evidence so that the user can easily refer to it.

[1907] 5. Predictive analysis and reporting functions

[1908] Step 1:

[1909] The server uses generative AI to perform predictive analysis based on historical data.

[1910] The server inputs time-series data into an AI model to predict future risks and treatment effects.

[1911] Step 2:

[1912] The server generates the prediction results as a data report.

[1913] The server generates a report containing the predicted results along with a risk assessment and recommended actions.

[1914] Step 3:

[1915] The server transmits the generated forecast report to the terminal.

[1916] The server encrypts and securely transmits the reports.

[1917] Step 4:

[1918] The terminal displays the received prediction report to the medical professional.

[1919] The terminal provides an interface for the user to adjust the treatment plan based on the predicted results.

[1920] Throughout the system, healthcare professionals can leverage real-time, integrated patient data to make more accurate decisions.

[1921] Example 1

[1922] 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."

[1923] Conventional medical data management systems have incomplete integration of patient biometric information and diagnostic results, making it difficult to update and analyze information in real time. Furthermore, important medical information cannot be quickly extracted when analyzing text data from electronic medical records, making it difficult for medical professionals to easily access the information they need. Furthermore, there are insufficient mechanisms for effectively utilizing the latest medical research and evidence in clinical settings, leading to inaccurate predictions of treatment effectiveness and future disease conditions. As a result, there are issues with delays in the formulation of treatment plans and early intervention.

[1924] 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.

[1925] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from the cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means for analyzing the medical information collected from the cloud database and suggesting treatments appropriate for the patient's condition; means for predicting trends in heart rate and blood sugar level based on past data; means for generating the prediction results as a data report and transmitting it to the terminal; and means for the terminal to visually display the data report so that it can be used by medical professionals. This will enable the integration of diverse medical data from different sources, updating and analyzing it in real time, and providing medical professionals with quick access to the information they need. It will also promote the use of the latest medical research and evidence, improving the accuracy of future disease predictions, allowing for the rapid development of treatment plans and early intervention.

[1926] "Biometric information" is data obtained directly from a patient's body, and examples include heart rate, blood pressure, blood sugar level, and body temperature.

[1927] "Diagnostic results" refers to the evaluations and findings obtained through examinations and medical treatment of patients by medical institutions, and specifically includes the contents of medical certificates and test reports.

[1928] A "cloud database" refers to a database service that can be accessed via the Internet and allows for the centralized management and storage of large amounts of data.

[1929] A "patient profile" is a data set that centrally manages individual information about a patient, including medical history, biometric information, and diagnostic results.

[1930] "Generative AI" refers to systems that use artificial intelligence techniques to generate and analyze data, and is particularly used for advanced pattern recognition and predictive analysis.

[1931] An "electronic medical record" refers to a system that electronically records and manages patient medical information at medical institutions, including medical records, prescriptions, test results, etc.

[1932] "Dashboard data" refers to a data set that integrates information obtained from multiple data sources and displays it visually.

[1933] An "interface" is a means of enabling interaction between a user and a system, and includes screens and operating means that users can use intuitively.

[1934] "Medical research" means scientific research activities in the field of medicine, including experiments and investigations aimed at developing new treatments and understanding disease states.

[1935] "Evidence" refers to scientific evidence supporting the effectiveness of a particular medical procedure or treatment.

[1936] "Trend forecasting" refers to an analytical method that predicts future fluctuations and patterns based on past data.

[1937] A "data report" is a report that includes analytical results and forecast information and provides a summary of data for a specific purpose.

[1938] The system of the present invention integrates various medical data and supports advanced medical analysis. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[1939] Data collection

[1940] First, the server has a means to receive patient biometric information and diagnostic results in real time. Specifically, biometric information such as the patient's heart rate, blood pressure, blood glucose level, and body temperature is obtained via an API from IoT devices such as heart rate monitors and blood glucose sensors. Electronic medical record information is also obtained from medical institution systems using the HL7 and FHIR protocols.

[1941] Example: A server receives data from a heart rate monitor every minute and stores it in a database. Electronic medical record data is retrieved periodically using the HL7 protocol.

[1942] Data Integration

[1943] The server stores the received vital signs and diagnostic results in a cloud database, centrally integrating them, organizing data in different formats while maintaining consistency based on patient IDs, and updating patient profiles in real time.

[1944] Example: The server integrates heart rate and blood glucose data into a cloud database and appends it to an existing patient profile.

[1945] Electronic medical record analysis

[1946] The server uses generative AI to analyze the text data in the electronic medical record. It uses natural language processing (NLP) techniques to extract important information and patterns from the records, convert them into structured data, and add them to the patient profile.

[1947] Example: The server inputs the prompt "Extract past diabetes history from the patient's electronic medical record data" into the generative AI model and adds the retrieved information to the patient profile.

[1948] Dashboard View

[1949] The server generates dashboard data based on the patient's information and sends it to the device, which displays a single screen that integrates the patient's real-time heart rate and past diagnostic data.

[1950] The terminal visually displays the received dashboard data and provides an interface for use by medical professionals.

[1951] Example: The server generates dashboard data that combines heart rate data and past diagnostic data and sends it to the device, which displays this data in a graph format, allowing medical professionals to understand the patient's condition at a glance.

[1952] Providing the latest medical information and evidence

[1953] The server collects the latest medical research and evidence from a cloud database, associates it with patient data, analyzes the collected medical information, and suggests treatments appropriate for the patient's condition.

[1954] Example: The server uses the academic journal API to collect the latest research data and associate it with patient profiles to suggest optimal treatment options.

[1955] Predictive analytics and reporting

[1956] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data. The prediction results are generated as a data report and sent to the device, which then visually displays the data report and makes it available to medical professionals.

[1957] Example: The server analyzes blood glucose data from the past year to predict future diabetes risk. A report of the prediction results is sent to the device, which medical professionals can use to adjust treatment plans.

[1958] Prompt Sentence Examples

[1959] "Extract past diabetes history from a patient's electronic medical record data."

[1960] "Based on your heart rate data from the past year, predict your heart rate trend for the next six months."

[1961] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1962] Step 1: Receiving data

[1963] The server receives patient biometric information (heart rate, blood pressure, blood glucose level, body temperature, etc.) from IoT devices via an API. The input is data from the heart rate monitor and blood glucose level sensor, and the output is biometric information stored in a cloud database.

[1964] As a specific example of operation, the server receives the patient's heart rate data every minute through the API and stores it in a cloud database.

[1965] Step 2: Obtain electronic medical record data

[1966] The server retrieves electronic medical record information from the medical institution's system using the HL7 or FHIR protocol. The input is HL7 or FHIR format data from the medical institution's system, and the output is electronic medical record information stored in a cloud database.

[1967] As a specific example of operation, the server periodically acquires electronic medical record data from medical institutions every day via a protocol and centrally manages it.

[1968] Step 3: Data Integration

[1969] The server integrates the received biometric information and diagnostic results into a cloud database. The input is the biometric information and electronic medical record information obtained in steps 1 and 2, and the output is unified patient profile data.

[1970] As a specific example of how it works, heart rate data and blood glucose data are integrated into a cloud database and organized based on patient ID.

[1971] Step 4: Data integrity check

[1972] The server checks the integrity of the data and adds new data entries to the existing patient profile. The input is the merged patient profile data and the output is the updated patient profile.

[1973] As a specific example of operation, new heart rate data and diagnostic results are compared with the existing profile, and consistency is confirmed before updating.

[1974] Step 5: Electronic medical record analysis

[1975] The server analyzes the text data of the electronic medical record using a generative AI model. The input is the text data of the electronic medical record, and the output is structured medical information.

[1976] As a specific example of operation, a prompt statement such as "Extract past diabetes history from the patient's electronic medical record data" is input into the generative AI model, and the extracted information is converted into structured data.

[1977] Step 6: Generate dashboard data

[1978] The server generates dashboard data based on the patient information and sends it to the terminal. The input is the updated patient profile data, and the output is the dashboard data for visualization.

[1979] As a specific example of operation, dashboard data that integrates heart rate data and past diagnostic data is generated and sent to the terminal.

[1980] Step 7: View the dashboard

[1981] The terminal visually displays the received dashboard data. The input is the dashboard data sent from the server, and the output is the visualized data as a user interface.

[1982] As a specific example of how it works, the device displays heart rate and past diagnostic data at a glance through graphs and charts.

[1983] Step 8: Providing the latest medical information and evidence

[1984] The server collects the latest medical research and evidence from a cloud database and associates it with patient data. The input is the latest medical research data and patient information, and the output is the associated treatment and medical knowledge.

[1985] As a specific example of how it works, the server uses an academic paper API to collect the latest research data, associates it with patient profiles, and presents applicable treatments.

[1986] Step 9: Predictive analytics

[1987] The server uses a generative AI model based on past data to predict future disease conditions and treatment outcomes. The input is past heart rate and blood sugar data, and the output is a data report of the predicted disease conditions and treatment outcomes.

[1988] As a specific example of how it works, it analyzes blood glucose data from the past year and predicts the risk of future diabetic complications.

[1989] Step 10: Generate and view data reports

[1990] The server generates a data report based on the prediction results and sends it to the terminal, which visually displays the data report and makes it available to medical professionals. The input is the prediction result data, and the output is the visualized data report.

[1991] In a specific example of operation, the server compiles the predicted data into a report and sends it to the device, which then visually displays the report in graphs and text format and allows medical professionals to adjust the treatment plan.

[1992] (Application example 1)

[1993] 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."

[1994] Conventional medical systems have difficulty receiving, integrating, and analyzing patients' vital signs and diagnostic results in real time. Furthermore, there are insufficient means to use generative AI to analyze text data from electronic medical records, extract important medical information, and provide it to medical professionals. In particular, brick-and-mortar stores lack real-time data acquisition and analysis methods for managing customers' health and recommending appropriate treatments. This makes it difficult to provide personalized health advice to customers.

[1995] 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.

[1996] In this invention, the server includes: means for receiving a patient's biometric information and diagnostic results in real time; means for storing the patient's biometric information and diagnostic results in a cloud database and centrally integrating them; means for updating a patient profile in real time based on the integrated data; means for analyzing text data in an electronic medical record using a generating AI and extracting important medical information and patterns; means for adding the analysis results to a corresponding patient profile so that it can be easily accessed by medical professionals; means for generating dashboard data based on patient information and sending the dashboard data to a terminal; means for visualizing the dashboard data generated by the terminal and providing an interface for use by medical professionals; means for collecting the latest medical research and evidence from a cloud database; means for associating the collected medical information with patient data; means for predicting future medical conditions and treatment effects based on past data using a generating AI; means, which is installed in smart glasses, for acquiring a customer's biometric information in real time and displaying the analysis results; means for acquiring electronic medical record information using HL7 or FHIR protocols; means for displaying appropriate treatments and health management suggestions on the display of the smart glasses; and means for providing advice based on the latest medical research and evidence. This will enable physical stores to provide personalized health advice to customers in real time.

[1997] "Patient's biological information" refers to physiological data obtained from within the patient's body, such as heart rate, blood pressure, blood sugar level, and body temperature.

[1998] "Diagnosis results" are the results of professional diagnoses or tests conducted by a doctor or medical institution regarding a patient's medical condition or health status.

[1999] A "cloud database" is a database service provided by a remote server that allows data to be stored, managed, and accessed over the Internet.

[2000] A "patient profile" is a set of information that represents the health status of an individual patient, constructed based on medical data such as the patient's biometric information, diagnosis results, and electronic medical records.

[2001] "Generative AI" is an artificial intelligence technique that can generate new information and insights using large datasets and machine learning algorithms.

[2002] An "electronic medical record" is a system that electronically records and manages a patient's medical history, prescriptions, test results, etc.

[2003] "Dashboard data" is a data set that visually organizes patient biometric information and diagnostic results, and displays them in a way that can be understood at a glance.

[2004] A "terminal" is a device that a user operates, and in this case refers to a PC, smartphone, tablet, etc.

[2005] An "interface" is a software or hardware component that provides a screen or means of operation for a user to interact with a system.

[2006] "Medical research" is scientific research conducted with the goal of advancing medical care, understanding disease, and developing treatments.

[2007] "Evidence" refers to data and research results that provide scientific evidence used in the medical field.

[2008] "Predicting future disease states and treatment outcomes" is the process of using past data and generative AI to predict a patient's future health condition and treatment outcomes.

[2009] "Smart glasses" are a wearable eyeglass-type device equipped with a display that can display data in real time and provide information to users.

[2010] The "HL7 and FHIR protocols" are standards for electronically exchanging medical information and are formats and communication protocols that ensure interoperability of medical data.

[2011] "Health management suggestions" involve providing specific advice and recommendations on lifestyle changes, treatment options, etc. to improve a patient's health.

[2012] The system according to the present invention integrates various medical data and realizes advanced medical analysis. Specific embodiments of the present invention will be described below.

[2013] 1. Hardware Configuration

[2014] The system includes the following hardware:

[2015] Server: The central component responsible for data collection, integration, analysis, and cloud database management.

[2016] Smart glasses: A wearable device that allows users to check data in real time and receive appropriate health advice.

[2017] IoT devices: These devices collect patients' vital signs, such as heart rate, blood pressure, and blood sugar levels, in real time.

[2018] Device: The device that provides the data visualization or interface, including computers, smartphones, tablets, etc.

[2019] 2. Software Configuration

[2020] The system uses the following software:

[2021] Python: The language on which the program is based.

[2022] OpenAI API: Generative AI models (e.g., GPT-4) used for natural language processing (NLP).

[2023] Requests (Python library): A library for retrieving data from APIs.

[2024] HL7 / FHIR API: A standard protocol for obtaining electronic medical record information.

[2025] 3. Data Collection and Integration

[2026] The server receives patient biometric information from IoT devices in real time and retrieves electronic medical record information from medical institutions using HL7 and FHIR protocols. These data are integrated and stored in a cloud database, and patient profiles are updated in real time.

[2027] 4. Data Analysis

[2028] The server uses generative AI to parse the text data in the electronic medical record to extract important medical information and patterns, which are then added to the corresponding patient profile and made easily accessible to medical professionals.

[2029] 5. Dashboard generation and display

[2030] The server generates dashboard data based on the patient's information and sends it to the device. The device visualizes the dashboard data and provides an interface for medical professionals to use. The smart glasses collect the patient's biometric information in real time and display the analysis results to provide appropriate health advice to the patient.

[2031] 6. Providing the latest medical information and evidence

[2032] The server collects the latest medical research and evidence from a cloud database and associates the collected medical information with patient data, thereby suggesting applicable treatments and medical findings.

[2033] 7. Predictive Analytics and Reporting

[2034] The server uses generative AI to predict future disease conditions and treatment outcomes based on past data, and the results are generated as a data report, which is sent to the device and displayed to medical professionals.

[2035] Specific examples

[2036] For example, when a customer visits a pharmacy, the smart glasses can be used to check their heart rate and past diagnostic information, and provide them with on-the-spot medication and health advice.

[2037] Prompt Sentence Examples

[2038] Patient data: {"physiological_data": {"heart_rate": 85, "blood_pressure": "120 / 80", "blood_sugar": 110}, "medical_records": {"condition": "hypertension", "medication": ["Drug A", "Drug B"]}}.

[2039] Provide a summary and recommendations.

[2040] This will enable physical stores to provide personalized health advice to customers in real time.

[2041] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2042] Step 1:

[2043] Collecting patient vital signs in real time

[2044] The server receives real-time biometric information such as heart rate, blood pressure, and blood sugar levels from IoT devices. Specifically, it periodically acquires data sent from IoT devic...

Claims

1. means for receiving patient vital signs and diagnostic results in real time; A means of storing and centrally integrating patient biometric information and diagnostic results in a cloud database; and A means to update patient profiles in real time based on the integrated data; A means of analyzing text data from electronic medical records using generative AI to extract important medical information and patterns; a means for adding the analysis results to the corresponding patient profile and making them easily accessible to healthcare professionals; means for generating dashboard data based on patient information and transmitting the dashboard data to a terminal; A means for visualizing the dashboard data generated by the device and providing an interface for use by medical professionals; A means of collecting the latest medical research and evidence from cloud databases; a means of linking collected medical information with patient data; A system that includes a means to use generative AI to predict future disease states and treatment outcomes based on past data.

2. a dashboard data generating means based on the patient's biological information and diagnosis results; Interface provision based on the latest medical research and evidence, The system according to claim 1, further comprising an electronic medical record text data analysis means using a generation AI.

3. A method for predicting future disease conditions and treatment outcomes using generative AI, a data report generating means based on the prediction results; 10. The system of claim 1, further comprising means for transmitting the data report to a terminal for display to a medical professional.

Images