System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving clinical test data and medical record information; means for obtaining drug information from a drug database; means for classifying data using a specific algorithm and extracting features; means for recommending optimal drugs based on the features; and means for generating and transmitting a recommended drug list.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 systems, doctors rely on their experience and records to write individual prescriptions, making it a time-consuming process. It is also difficult to fully understand rapidly changing drug information, which can lead to inadequate management of side effects due to pre-existing conditions or drug interactions. These issues increase the burden on doctors and hinder optimal medical care for patients. The present invention aims to solve these problems. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving clinical test data and medical record information, a means for retrieving drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, and a means for generating and transmitting a list of recommended drugs. Furthermore, the system includes a means for evaluating the risk of side effects based on chronic illnesses and drug interactions and reflecting this in the recommended drug list, and a means for verifying the consistency and completeness of the clinical test data and medical record information, thereby enabling efficient and highly accurate prescription drug recommendations. This system reduces the burden on doctors and enables patients to receive appropriate medications promptly.

[0006] "Clinical test data" refers to data obtained from various tests conducted by medical institutions regarding the health status of patients, and includes numerical information such as blood sugar levels and blood pressure.

[0007] "Medical record information" is a general term for medical records managed by doctors, such as a patient's medical history, current medical history, medical records, and medication information.

[0008] A "drug database" is an information source that stores detailed information related to drugs, such as the type of drug, its effects, side effects, and precautions for use.

[0009] An "algorithm" is a set of computational steps or rules designed to solve a particular problem.

[0010] "Feature extraction" means extracting important elements and patterns from data and preparing them in a form that can be analyzed.

[0011] "Recommending the optimal medication" means selecting and presenting the most effective and safe medication based on the patient's health condition and clinical test data.

[0012] A "recommended drug list" is a candidate list of drugs that have been determined to be suitable for a particular patient, and also includes related information (e.g., risk of side effects and drug interactions).

[0013] "Risk of adverse effects" refers to the unwanted health effects that may occur from using a drug.

[0014] "Consistency" refers to a state in which data is consistent and consistent, ensuring the reliability of the information.

[0015] "Complete" means that the data is comprehensive and includes all relevant information derived from the primary source. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that enables doctors to prepare prescriptions efficiently and with high accuracy, and an embodiment of the system will be described in detail below. This system is composed of a server, a terminal, and a user (doctor).

[0038] Server Processing

[0039] The server plays a central role in the system and performs the following processes:

[0040] 1. Data Reception

[0041] The server receives the clinical test data and medical record information sent from the terminal.

[0042] Check the consistency and completeness of the data received.

[0043] 2. Database Reference

[0044] The server accesses a drug database to obtain the latest drug information and statistical data.

[0045] 3. Data Classification and Feature Extraction

[0046] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[0047] 4. Generating medication recommendations

[0048] The server generates a list of optimal drug recommendations based on the extracted features.

[0049] This list also reflects the risk of side effects based on pre-existing conditions and interactions with other medications.

[0050] 5. Sending the results

[0051] The server transmits the recommended medication list to the terminal.

[0052] Terminal handling

[0053] The terminal is a device operated by a doctor and performs the following processes:

[0054] 1. Data entry and submission

[0055] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[0056] The terminal formats the input data and sends it to the server.

[0057] 2. Receive a list of recommended medications

[0058] The terminal receives the recommended medication list sent from the server.

[0059] 3. Display and confirmation

[0060] The terminal displays the received recommended drug list to the user (doctor).

[0061] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[0062] User (doctor) processing

[0063] The user (doctor) performs the following processes through the system.

[0064] 1. Data Entry

[0065] The user (doctor) inputs clinical test data and medical record information into the terminal.

[0066] 2. Check recommended medications

[0067] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[0068] 3. Final formulation decision

[0069] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[0070] Record the medication selected and the reason for it in the patient's chart.

[0071] Specific examples

[0072] For example, consider the case where a patient has diabetes.

[0073] 1. Data entry and submission

[0074] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[0075] The terminal transmits this data to the server.

[0076] 2. Server Processing

[0077] The server checks the received data for consistency and completeness.

[0078] The server accesses the drug database to obtain the latest drug information.

[0079] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[0080] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[0081] The list takes into account the risk of side effects and sends a list of recommended medications to the terminal.

[0082] 3. Receive and review the recommended medication list

[0083] The terminal receives the recommended medication list and displays it to the user (doctor).

[0084] The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[0085] 4. Final formulation decision

[0086] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[0087] In this way, the system of the present invention efficiently processes clinical test data and medical record information and recommends optimal medications, thereby reducing the burden on doctors and helping to provide prompt and appropriate treatment to patients.

[0088] The processing flow will be explained below.

[0089] Step 1:

[0090] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[0091] Step 2:

[0092] The terminal formats the entered clinical test data and medical record information and generates a data transmission request to be sent to the server.

[0093] Step 3:

[0094] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[0095] Step 4:

[0096] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[0097] Step 5:

[0098] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[0099] Step 6:

[0100] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[0101] Step 7:

[0102] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[0103] Step 8:

[0104] The server transmits the generated recommended drug list to the terminal.

[0105] Step 9:

[0106] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[0107] Step 10:

[0108] The user (doctor) checks the list of recommended medications displayed on the terminal and selects the medication appropriate for the patient.

[0109] Step 11:

[0110] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[0111] Example 1

[0112] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0113] Conventional medical systems have issues with the accuracy and speed with which they can efficiently process clinical test data and medical record information and recommend optimal medications to doctors. Furthermore, they lack a mechanism for effectively assessing the risk of side effects due to chronic illnesses or interactions with other medications, placing a heavy burden on doctors and making it difficult to provide appropriate treatment to patients promptly. To address these issues, the present invention aims to provide a more efficient and accurate prescription preparation system.

[0114] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0115] In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, a means for formatting data entered by a user on a terminal and transmitting the data to the server, and a means for displaying the list of recommended drugs transmitted from the server. This enables rapid and accurate drug recommendations based on the clinical test data and medical record information, and allows appropriate evaluation of the risk of side effects due to chronic illnesses and drug interactions. It also reduces the burden on doctors and enables prompt and accurate treatment for patients.

[0116] "Laboratory data" refers to the results of various tests performed to assess a patient's health, including blood tests, urine tests, and diagnostic imaging.

[0117] "Medical record information" refers to the comprehensive medical record of a patient, including medical records, medical history, current medication status, allergy information, etc.

[0118] The "drug database" is a database that collects information about various drugs, including drug efficacy, side effects, drug interactions, and the latest clinical research results.

[0119] A "specific algorithm" refers to a computational method that analyzes input data and extracts certain patterns or characteristics, using machine learning and statistical analysis techniques.

[0120] "Feature extraction" is the process of finding important information and patterns in input data, which allows us to understand the essence of the data.

[0121] "Recommending" means showing the best option based on specific conditions and data. This system plays a role in suggesting the best medication to doctors.

[0122] The "recommended drug list" is a list of drugs selected based on data analyzed by the system, including information on efficacy, side effects, and risks.

[0123] A "terminal" is a device used by a physician, including a desktop computer, notebook, tablet, etc.

[0124] "Formatting" is the process of converting data into a specific structure or form, which improves data compatibility and processing efficiency.

[0125] "User" refers to anyone who operates this system, especially a doctor who uses this system in the medical field.

[0126] The "server" is the central computer in this system, which handles data transfer and processing.

[0127] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of three elements: a server, a terminal, and a user (doctor).

[0128] Server Processing

[0129] The server plays a central role in this system and performs the following processes:

[0130] Data reception

[0131] The server receives the clinical test data and medical record information sent from the terminal. After receiving the data, the server checks the consistency and completeness of the data. This check process includes checking the data structure and format. The server receives the data securely using the HTTPS protocol.

[0132] Database Reference

[0133] The server accesses the drug database to retrieve the latest drug information and statistical data. This process uses SQL queries. The drug database can be a relational database such as MySQL (registered trademark) or PostgreSQL.

[0134] Data Classification and Feature Extraction

[0135] The server classifies the received data using a specific algorithm and extracts features. It does this using machine learning algorithms (e.g., random forests and support vector machines).

[0136] Generate medication recommendations

[0137] The server generates a list of optimal medication recommendations based on the extracted features, taking into account pre-existing conditions and the risk of side effects due to interactions with other medications.

[0138] Sending the results

[0139] The server converts the recommended medication list into JSON format and sends it to the terminal using the HTTPS protocol.

[0140] Terminal handling

[0141] The terminal is a device operated by a doctor and performs the following processes:

[0142] Data entry and submission

[0143] The user (doctor) enters the patient's laboratory test data and medical record information into the terminal, which formats and transmits this data to the server using the HTTPS protocol.

[0144] Receive a list of recommended medications

[0145] The terminal receives the recommended drug list sent from the server and converts the received data into an internal data structure.

[0146] Display and confirmation

[0147] The terminal displays the received list of recommended medications to the user (doctor). The user (doctor) checks the displayed list and, if necessary, conducts further research and consideration. The terminal also has an interface for providing detailed information.

[0148] User (doctor) processing

[0149] The user (doctor) performs the following processes through the system.

[0150] Data Entry

[0151] The user (physician) enters laboratory test data and medical record information into the terminal, either manually using an input form or by importing data from an existing electronic medical record system.

[0152] Check recommended medications

[0153] The user (doctor) checks the list of recommended medications displayed on the device and selects the appropriate medication. Detailed information on each medication can also be viewed.

[0154] Final formulation decision

[0155] The user (doctor) selects the most appropriate medication and decides on the final prescription. The information on the selected medication is recorded in the patient's chart.

[0156] Specific examples

[0157] For example, consider the case where a patient has diabetes.

[0158] Data entry and submission

[0159] The user (doctor) inputs the clinical test data (e.g., blood glucose level 180 mg / dL) of a diabetic patient and medical record information (e.g., medical history, no current medication) into the terminal. The terminal converts this data into JSON format and sends it to the server as an HTTPS POST request.

[0160] Server Processing

[0161] The server checks the received data for consistency and completeness. Next, it accesses a drug database and executes SQL queries to obtain the latest drug information. It then uses machine learning algorithms to classify the data and extract features related to diabetes. It then lists the most suitable drugs (e.g., metformin, insulin) and finalizes the list by taking into account the risk of side effects. Finally, it sends the recommended drug list in JSON format to the device.

[0162] Receive and review recommended medication lists

[0163] The device receives the list of recommended medications and displays it to the user (doctor). The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[0164] Final formulation decision

[0165] The user (doctor) decides on "metformin" as the final prescribed medication and records that information in the patient's chart.

[0166] Prompt Sentence Examples

[0167] "Please explain in natural language the process by which a doctor uses the system to determine a prescription for a diabetic patient."

[0168] As described above, the system of the present invention efficiently processes clinical test data and medical record information and makes highly accurate drug recommendations, thereby reducing the burden on doctors and providing patients with prompt and appropriate treatment.

[0169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0170] Step 1: Enter and submit data

[0171] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal. Specifically, the user records blood glucose levels, medical history, current medication status, etc. in the input form on the terminal.

[0172] The terminal formats the entered data into JSON format and sends it to the server using the HTTPS protocol.

[0173] Input: Laboratory test data and medical record information (e.g., blood glucose level, medical history)

[0174] Output: Formatted JSON data sent to the server

[0175] Step 2: Receiving data

[0176] The server receives the JSON formatted clinical test data and medical record information sent from the terminal via the HTTPS protocol.

[0177] Upon receipt, the server checks the data for consistency and completeness, specifically verifying that the data structure and format are correct.

[0178] Input: JSON data sent from the terminal

[0179] Output: Verified laboratory data and medical record information

[0180] Step 3: Database Reference

[0181] The server accesses the drug database and executes SQL queries to retrieve the latest drug information.

[0182] The acquired information includes drug efficacy, side effects, and drug interaction information.

[0183] Input: Validated data stored on the server

[0184] Output: Drug information retrieved from the drug database

[0185] Step 4: Data classification and feature extraction

[0186] The server uses specific machine learning algorithms (e.g., random forests or support vector machines) to classify the data and extract features.

[0187] This allows for the extraction of important health conditions such as diabetes and hyperglycemia.

[0188] Input: Validated data and drug database information

[0189] Output: Extracted features (e.g., diabetes, hyperglycemia)

[0190] Step 5: Generate drug recommendations

[0191] The server generates a list of recommended optimal medications based on the extracted features, and a recommendation engine ranks the medications based on each feature, taking into account the risk of side effects.

[0192] A list of recommended medications is completed, including information on the efficacy, side effects, and risks of each recommended medication.

[0193] Input: Extracted features

[0194] Output: Recommended medication list

[0195] Step 6: Sending the results

[0196] The server converts the generated list of recommended medications into JSON format and sends it to the terminal using the HTTPS protocol.

[0197] Input: Recommended medication list

[0198] Output: JSON data sent to the terminal

[0199] Step 7: Receive a list of recommended medications

[0200] The terminal receives the recommended drug list in JSON format sent from the server.

[0201] Converts received data into an internal data structure.

[0202] Input: JSON data sent from the server

[0203] Output: Recommended medication list converted into internal data structure

[0204] Step 8: View and verify

[0205] The terminal displays the recommended medication list to the user (doctor) on a GUI, and the doctor can also access detailed information.

[0206] Input: Recommended medication list converted into internal data structure

[0207] Output: A list of recommended medications that is displayed to the user

[0208] Step 9: Selecting a recommended medication

[0209] The user (doctor) checks the displayed list of recommended medications and selects an appropriate medication.

[0210] View details to investigate further if needed.

[0211] Input: Recommended medication list shown to user

[0212] Output: Selected drug information

[0213] Step 10: Finalize the formula

[0214] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[0215] Record the final prescription information in the patient's chart.

[0216] Input: Selected drug information

[0217] Output: Prescription information recorded in the patient record

[0218] By using the specific processing steps described above, the system of the present invention can reduce the burden on doctors and provide prompt and appropriate treatment to patients.

[0219] (Application example 1)

[0220] 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."

[0221] In modern autonomous vehicles, it is difficult to monitor the health status of passengers in real time and take necessary measures promptly. Especially when clinical testing equipment is not installed in the vehicle, it is important to respond quickly when a passenger suddenly becomes ill. Furthermore, there is a need for a system that can recommend optimal medications based on medical history and current medication status, and can take emergency action after an abnormality is discovered. Ensuring consistency and completeness when handling large amounts of data is also a challenge.

[0222] 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.

[0223] In this invention, the server includes means for receiving clinical test data and medical record information, means for acquiring drug information from a drug database, means for classifying data using a specific algorithm and extracting features, means for recommending optimal drugs based on the features, means for generating and transmitting a list of recommended drugs, means for collecting and analyzing biometric data of the passenger, means for constantly monitoring health data and detecting abnormalities, and means for automatically guiding the passenger to the nearest medical institution in an emergency. This makes it possible to monitor the passenger's biometric data in real time, quickly recommend optimal drugs, and navigate to an appropriate medical institution in an emergency.

[0224] "Laboratory data" refers to numerical information obtained from tests performed by medical institutions to assess a patient's health status.

[0225] "Medical record information" is data that includes medical records such as a patient's medical history and prescription history.

[0226] A "drug database" is a digital database that stores information about various drugs.

[0227] An "algorithm" is a set of rules and procedures for processing data and performing classification and feature extraction.

[0228] "Drug recommendation" is the process of selecting the most appropriate medication based on a patient's specific symptoms and clinical test data.

[0229] A "recommended drug list" is a list of drugs suitable for a patient generated by an AI model or algorithm.

[0230] "Passenger" refers to a person riding in an autonomous vehicle.

[0231] "Biometric data" is digital information obtained from the human body, such as heart rate, blood pressure, and blood sugar levels.

[0232] "Anomaly detection" is the process of detecting biometric data that deviates from the normal range.

[0233] "Emergency Navigation" is a function that automatically guides passengers to the nearest medical institution if an abnormality in their health condition is detected.

[0234] The present invention is a system that monitors the health status of passengers in autonomous vehicles in real time and recommends appropriate medications when necessary. This system operates based on three main components: a server, a terminal, and a user (vehicle passenger).

[0235] Server Processing

[0236] The server plays a central role in the entire system and performs the following processes:

[0237] Data receipt and confirmation:

[0238] The server receives the lab test data and medical record information sent from the device and checks its consistency and completeness. This data includes heart rate, blood pressure, blood glucose level, etc. The server then verifies the received data with an integrity check algorithm.

[0239] Database Reference:

[0240] The server accesses the drug database to obtain the latest drug information, allowing the information on drugs suitable for each patient to be updated as needed.

[0241] Data classification and feature extraction:

[0242] Data analysis algorithms are used to classify incoming data and extract key features, which allow for drug recommendations tailored to specific diseases and health conditions.

[0243] Generate drug recommendations:

[0244] Based on the extracted features, the system generates a list of optimal drug recommendations. It also evaluates the risk of side effects based on pre-existing conditions and drug interactions and reflects this in the recommendation list.

[0245] Sending results:

[0246] A list of recommended medications is sent to the terminal and displayed to the passenger.

[0247] Terminal handling

[0248] The terminal is a device such as a tablet or smartphone installed inside the autonomous vehicle, and performs the following processes.

[0249] Data entry and submission:

[0250] Passengers input biometric data measured using sensors such as a heart rate monitor, blood pressure monitor, and blood glucose monitor into a terminal, which then transmits this data to a server.

[0251] Receive and view recommended medication lists:

[0252] The terminal receives the list of recommended medications sent from the server and displays it to the passenger.

[0253] Anomaly detection and emergency response:

[0254] The device constantly monitors biometric data and, if it detects an abnormality, quickly directs the user to the nearest medical institution.

[0255] User (vehicle passenger) processing

[0256] The user (vehicle passenger) performs the following processes through the system.

[0257] Data Entry:

[0258] The user measures his / her own biometric data and inputs it into the terminal.

[0259] Check recommended medications:

[0260] The user checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[0261] Take necessary action:

[0262] The user then goes to the indicated medical facility in case of an emergency or takes the recommended medication.

[0263] For example, the following prompt sentence can be input into a generative AI model to recommend an appropriate medication:

[0264] Example input:

[0265] "The patient is 50 years old, has a blood pressure of 160 / 100 mmHg, and a blood glucose level of 150 mg / dL. Please recommend the appropriate medication for this patient."

[0266] This prompt may recommend, for example, an ACE inhibitor (e.g., losartan) as an antihypertensive drug or metformin as a hypoglycemic drug. In this way, the system of the present invention can efficiently monitor the passenger's health status and provide prompt and appropriate responses.

[0267] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0268] Step 1:

[0269] Data collection

[0270] The device measures biometric data such as heart rate, blood pressure, and blood glucose level from passengers in the vehicle. This data is acquired using sensors such as a blood pressure monitor, heart rate sensor, and blood glucose meter. The input is biometric data obtained from various sensors, and the output is the measured biometric data.

[0271] Step 2:

[0272] Data transmission

[0273] The device sends the biometric data acquired in step 1 to the server. The protocol used for data transmission is HTTP or HTTPS. The input is the measured biometric data, and the output is the biometric data formatted to be received by the server.

[0274] Step 3:

[0275] Data Receipt and Confirmation

[0276] The server receives the biometric data received from the terminal and checks its consistency and completeness. It uses a data integrity check algorithm to detect missing or outlier values. The input is the biometric data received by the server, and the output is the biometric data that has been checked for consistency and completeness.

[0277] Step 4:

[0278] Database Reference

[0279] The server accesses the drug database to obtain the latest drug information. It then executes a database query to obtain drug information appropriate for the current condition. The input is the confirmed biometric data, and the output is the corresponding drug information.

[0280] Step 5:

[0281] Data Classification and Feature Extraction

[0282] The server uses a specific algorithm to classify the received data and extract features. This uses a data analysis algorithm. The input is the drug information and biometric data obtained from the drug database, and the output is the extracted feature data.

[0283] Step 6:

[0284] Generate medication recommendations

[0285] The server generates a list of optimal medication recommendations based on the extracted feature data. It also evaluates the risk of side effects due to chronic illnesses and drug interactions and reflects this in the list. The input is feature data and drug data, and the output is a list of recommended medications. At this time, it is also possible to create prompt sentences using a generative AI model. Example: "The patient is 50 years old, his blood pressure is 160 / 100 mmHg, and his blood sugar level is 150 mg / dL. Please recommend the appropriate medication for this patient."

[0286] Step 7:

[0287] Sending the results

[0288] The server sends the generated recommended medication list to the terminal. The input is the recommended medication list, and the output is the recommended medication list formatted to be received by the terminal.

[0289] Step 8:

[0290] Results display

[0291] The terminal displays the recommended medication list received from the server to the passenger. The display is on a tablet or smartphone. The input is the recommended medication list, and the output is a list displayed in a format that can be viewed by the passenger.

[0292] Step 9:

[0293] Anomaly detection and emergency response

[0294] The device constantly monitors vital signs and guides the user to the nearest medical facility if an abnormality is detected. It uses a GPS module and a navigation system to provide prompt guidance. The input is real-time vital signs, and the output is emergency response alerts and navigation information if an abnormality is detected.

[0295] 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.

[0296] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy, and its configuration and operation method will be described in detail. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[0297] Server Processing

[0298] The server plays a central role in the system and performs the following processes:

[0299] 1. Data Reception

[0300] The server receives the clinical test data and medical record information sent from the terminal.

[0301] Check the consistency and completeness of the data received.

[0302] 2. Database Reference

[0303] The server accesses a drug database to obtain the latest drug information and statistical data.

[0304] 3. Data Classification and Feature Extraction

[0305] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[0306] 4. Generating medication recommendations

[0307] The server generates a list of optimal drug recommendations based on the extracted features.

[0308] This list also reflects information on the risk of side effects based on pre-existing conditions and interactions with other medications.

[0309] 5. Use of Emotion Engine

[0310] The server uses an emotion engine to recognize the user's (doctor's) emotions.

[0311] The emotional data collected by the emotion engine is analyzed and reflected in the recommended medication list.

[0312] 6. Submitting the results

[0313] The server transmits the recommended medication list to the terminal.

[0314] Terminal handling

[0315] The terminal is a device operated by a doctor and performs the following processes:

[0316] 1. Data entry and submission

[0317] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[0318] The terminal formats the input data and sends it to the server.

[0319] 2. Receive a list of recommended medications

[0320] The terminal receives the recommended medication list sent from the server.

[0321] 3. Display and confirmation

[0322] The terminal displays the received recommended drug list to the user (doctor).

[0323] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[0324] User (doctor) processing

[0325] The user (doctor) performs the following processes through the system.

[0326] 1. Data Entry

[0327] The user (doctor) inputs clinical test data and medical record information into the terminal.

[0328] 2. Check recommended medications

[0329] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[0330] The final prescription is determined with reference to the emotional data provided by the emotion engine.

[0331] 3. Final formulation decision

[0332] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[0333] Specific examples

[0334] For example, consider the process when a diabetic patient visits a doctor.

[0335] 1. Data entry and submission

[0336] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[0337] The terminal transmits this data to the server.

[0338] 2. Server Processing

[0339] The server checks the consistency and integrity of the data received.

[0340] The server accesses the drug database to obtain the latest drug information.

[0341] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[0342] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[0343] The emotion engine analyzes the user's (doctor's) emotional data (e.g., fatigue, impatience) collected and reflects it in the recommended medication list.

[0344] A list of recommended medications is sent to the terminal.

[0345] 3. Receive and review the recommended medication list

[0346] The terminal receives the recommended medication list and displays it to the user (doctor).

[0347] The user (doctor) checks the list and selects "metformin," which is suitable for diabetic patients.

[0348] The prescription is decided taking into consideration feedback from the emotion engine.

[0349] 4. Final formulation decision

[0350] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[0351] In this way, the system of the present invention, which combines an emotion engine, can recommend prescription drugs with greater accuracy by taking into account the user's (doctor's) emotional data in addition to clinical test data and medical record information. This reduces the burden on doctors and enables them to provide patients with prompt and accurate treatment.

[0352] The processing flow will be explained below.

[0353] Step 1:

[0354] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[0355] Step 2:

[0356] The terminal formats the input clinical test data and medical record information and generates a data transmission request to be transmitted to the server.

[0357] Step 3:

[0358] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[0359] Step 4:

[0360] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[0361] Step 5:

[0362] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[0363] Step 6:

[0364] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[0365] Step 7:

[0366] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[0367] Step 8:

[0368] The server uses an emotion engine to recognize the user's (doctor's) emotions, and collects voice and facial expression data when the user operates the device.

[0369] Step 9:

[0370] The emotion engine analyzes the collected emotion data (e.g., stress, fatigue, impatience) to determine the user's current emotional state.

[0371] Step 10:

[0372] The server takes into account the emotional data recognized by the emotion engine and applies emotion-based adjustments to the recommended medication list.

[0373] Step 11:

[0374] The server transmits the adjusted recommended medication list to the terminal.

[0375] Step 12:

[0376] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[0377] Step 13:

[0378] The user (doctor) checks the adjusted list of recommended medications displayed on the terminal and selects the appropriate medication for the patient.

[0379] Step 14:

[0380] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[0381] Example 2

[0382] 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."

[0383] Conventional drug recommendation systems did not take into account the emotional state of the doctor when recommending drugs using clinical test data and medical record information. As a result, the doctor's judgment could be affected by fatigue or stress, and the optimal drug could not be prescribed. Furthermore, recommendations were made without verifying the consistency and completeness of the data, which created a risk of selecting the wrong drug. The present invention aims to solve these problems.

[0384] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for checking the consistency and completeness of the received data, a means for acquiring drug information from a drug database, a means for classifying data using a specific algorithm and extracting features, a means for recommending optimal drugs based on the extracted features, a means for generating and transmitting a recommended drug list, and a means for recognizing the user's emotions, analyzing the emotion data, and reflecting the analysis results in the recommendation list. This enables highly accurate drug recommendations that take the doctor's emotional state into consideration.

[0385] "Clinical test data" refers to information resulting from analyses of samples such as blood, urine, and tissue of patients conducted at medical institutions such as hospitals and clinics.

[0386] "Medical record information" refers to a set of information that a doctor needs when treating a patient, such as the patient's medical history, current symptoms, and prescribed medications.

[0387] "Consistency" means that data is consistent in context and maintains logical consistency.

[0388] "Completeness" means that all data is included without any missing or incorrect information.

[0389] A "pharmaceutical database" is a database system that systematically collects and organizes information on various pharmaceuticals and stores it in a searchable and accessible format.

[0390] An "algorithm" is a procedure or computational sequence designed to solve a particular problem.

[0391] "Feature extraction" is the process of identifying and extracting important information and patterns from data.

[0392] A "recommendation" is a presentation of an option that is considered optimal based on specific conditions and information.

[0393] "Emotion recognition" is the process of detecting and evaluating a user's emotional state using sensors and analytical techniques.

[0394] "Emotion data" refers to observed and analyzed data such as numerical values ​​and categorical information related to the user's emotional state.

[0395] This paper describes in detail the configuration and operation of a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[0396] The server plays a central role in the system and provides multiple functions. First, the server receives clinical test data and medical record information sent from the terminal using the HTTPS protocol. The received data is checked for consistency and completeness. If the data is inconsistent or missing, the server detects this and performs appropriate error handling.

[0397] The server then accesses the drug database to retrieve the latest drug information and statistical data. This process is performed using a database management system, for example, MongoDB or MySQL. The retrieved data is cached internally on the server for efficient access.

[0398] The server then uses specific algorithms, such as Python's Scikit-learn library, to classify and extract features from the received lab test data and medical records. This feature extraction process involves using, for example, decision tree algorithms to classify the data based on the patient's medical history and current clinical data.

[0399] Based on the results of feature extraction, the server recommends the most appropriate medication. This recommendation takes into account side effect risk information and includes a detailed risk assessment, including pre-existing conditions and interactions with other medications. Before the recommended medication list is finally sent to the device, an emotion engine analyzes the collected user (doctor) emotion data and reflects it in the recommendation list. This emotion engine is implemented, for example, using the Affectiva API.

[0400] The terminal functions as a device operated by the user (doctor), and inputs and checks data through a GUI (graphical user interface). The user (doctor) inputs the patient's clinical test data and medical record information into the terminal and sends this to the server. When the terminal receives a list of recommended medications from the server, it displays this list on the GUI. The user (doctor) checks the displayed list and, if necessary, conducts further research or consideration.

[0401] As a concrete example, consider a diabetic patient undergoing a medical examination. The user (doctor) enters clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into a terminal and sends them to the server. The server receives this data and checks its consistency and completeness. The server then retrieves the latest drug information from a pharmaceutical database and classifies the data and extracts features using a specific algorithm. It then generates a list of recommended optimal medications, such as "metformin" and "insulin," and analyzes the user's (doctor's) emotional data (e.g., fatigue), using an emotion engine to reflect this in the recommendation list. This list of recommended medications is sent to the terminal and reviewed by the user (doctor). The user (doctor) then decides on "metformin" as the final prescription medication and records it in the patient's medical record.

[0402] As an example of a prompt, give the generative AI model the following input:

[0403] "Please recommend an appropriate medication based on the clinical data and medical record information of a diabetic patient (blood glucose level 180 mg / dL, no medical history). Also, please display the following recommended medication assuming it is used by a doctor who is feeling fatigued."

[0404] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0405] Step 1:

[0406] The terminal collects the patient's clinical test data and medical record information entered by the user (doctor) through an input device (e.g., keyboard or tablet). The input data is information such as blood glucose levels and medical history. This is converted into JSON format and sent to the server using the HTTPS protocol. The input is the clinical test data and medical record information entered by the user (doctor), and the output is JSON format data sent to the server.

[0407] Step 2:

[0408] The server receives clinical test data and medical record information in JSON format from the terminal. The received data is checked for consistency and completeness within the system. Specifically, it checks whether each field of the data has been entered properly and whether there are any inconsistencies. The input is the JSON data received from the terminal, and the output is the checked data.

[0409] Step 3:

[0410] The server uses the validated data to issue a search query to the drug database. For example, it uses an SQL query to retrieve the latest drug information from the database. This process uses a database management system such as MongoDB or MySQL. Specifically, it establishes a database connection and executes the appropriate query. The input is the validated data, and the output is the retrieved drug information.

[0411] Step 4:

[0412] The server uses a specific algorithm to classify data and extract features based on the acquired drug information, clinical test data, and medical record information. For example, it applies a decision tree algorithm using Python's Scikit-learn library. Specifically, it performs analysis based on the patient's medical history and test results. The input is the acquired drug information and confirmed data, and the output is classified feature data.

[0413] Step 5:

[0414] The server recommends the most appropriate medication based on the extracted feature data, taking into account the risk of side effects and drug interactions. The recommendation list is generated based on internal rules. The input is the classified feature data, and the output is a list of recommended medications.

[0415] Step 6:

[0416] The server uses an emotion engine based on the generated recommended drug list to analyze the user's (doctor's) emotional data. This process uses, for example, the Affectiva API. Specifically, it acquires the user's emotional data and reflects it in the recommendation list. The input is the recommended drug list and emotional data, and the output is a recommended drug list that reflects the emotional data.

[0417] Step 7:

[0418] The server sends the final recommended drug list to the terminal using the HTTPS protocol. Specifically, it formats the list and transfers it to the terminal. The input is the recommendation list that reflects the emotion data, and the output is the recommendation list sent to the terminal.

[0419] Step 8:

[0420] The terminal displays the recommended drug list received from the server on a GUI. The user (doctor) checks this list and selects the most appropriate drug based on the options presented. Specifically, the user selects an item on the list and operates the UI to check detailed information. The input is the recommended list received from the server, and the output is the drug selected by the user.

[0421] Step 9:

[0422] The user (doctor) decides on the selected medication as the final prescription and records it in the patient's chart. This adds the prescription information to the electronic medical record system, making it available for future reference. The specific operation involves inputting and saving the prescription information. The input is the medication selected by the user, and the output is the prescription information recorded in the patient's chart.

[0423] (Application example 2)

[0424] 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."

[0425] In modern medical settings, doctors are required to write prescriptions efficiently and with high accuracy. However, they need to process a large amount of information in a short amount of time, and their own emotions and fatigue can sometimes affect their judgment. Furthermore, selecting medications requires assessing the risk of pre-existing conditions and drug interactions, and it is difficult to perform these tasks consistently in a single system.

[0426] Furthermore, efficient information processing and display is required when pharmacists select the most appropriate medication based on conversations with patients in physical stores such as pharmacies. To address these issues, a system is needed that processes information holistically and efficiently, reducing the burden on doctors and pharmacists.

[0427] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, and a means for displaying the list of recommended drugs on a wearable display device. This enables doctors and pharmacists to select drugs efficiently and with high accuracy and provide patients with prompt and appropriate treatment.

[0428] "Clinical test data" refers to medical data obtained as a result of a patient's blood test, urine test, diagnostic imaging, etc.

[0429] "Medical record information" refers to medical records necessary for medical treatment, such as a patient's medical history, medical history, medication information, and allergy information.

[0430] A "drug database" is a database that contains information about drug ingredients, effects, side effects, and interactions with other drugs.

[0431] A "specific algorithm" is a mathematical or statistical procedure used to classify data or extract features.

[0432] A "feature extraction method" is a technique or method for extracting important patterns or information from data.

[0433] The "medication recommendation method" is a process for selecting the most suitable medication for a patient based on the extracted features.

[0434] A "recommended drug list" is a list of drugs selected based on specific conditions or characteristics.

[0435] A "wearable display device" is a display device worn by doctors and pharmacists, such as glasses or a head-mounted display.

[0436] An "emotion engine" is a technology or software that recognizes and analyzes a user's emotional state and reflects it in the system's recommendations.

[0437] This invention is a system that efficiently processes clinical test data and medical record information, allowing pharmacists to select prescription drugs quickly and accurately in physical stores. The system of this invention is composed of a server, a terminal, a user (pharmacist), an emotion engine, and a wearable display device.

[0438] Server Processing

[0439] The server plays a central role in the system and performs the following processes:

[0440] 1. The server receives the clinical test data and medical record information sent from the terminal.

[0441] 2. The server checks the received data for consistency and integrity.

[0442] 3. The server accesses the drug database and obtains the latest drug information.

[0443] 4. The server uses specific algorithms to classify and extract features from the received clinical test data and medical record information.

[0444] 5. The server generates a list of optimal drug recommendations based on the extracted features.

[0445] 6. The server uses an emotion engine to recognize the user's (pharmacist's) emotional data and reflects it in the recommended medication list.

[0446] 7. The server sends the generated recommended medication list to the terminal.

[0447] Terminal handling

[0448] The terminal is a device operated by a pharmacist and performs the following processes:

[0449] 1. The terminal receives the patient's clinical test data and medical record information from the pharmacist via the wearable display device.

[0450] 2. The terminal formats the input data and sends it to the server.

[0451] 3. The terminal receives the recommended medication list sent from the server.

[0452] 4. The terminal displays the received list of recommended medications to the pharmacist via the wearable display device.

[0453] User (pharmacist) processing

[0454] The user (pharmacist) performs the following processes through the system.

[0455] 1. The user (pharmacist) uses the wearable display device to input the patient's clinical test data and medical record information into the terminal.

[0456] 2. The user (pharmacist) checks the list of recommended medications displayed on the terminal and selects the appropriate medication.

[0457] 3. The user (pharmacist) decides on the final prescription, taking into account the emotional data provided by the emotion engine.

[0458] 4. The user (pharmacist) prescribes the selected medication to the patient and records it in the patient's medical record.

[0459] Specific examples

[0460] For example, consider the case where a diabetic patient visits a drugstore for a consultation.

[0461] 1. The user (pharmacist) uses the wearable display device to input the diabetic patient's clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[0462] 2. The device sends this data to the server.

[0463] 3. The server checks the consistency and completeness of the received data, then classifies the data and extracts features using specific algorithms.

[0464] 4. The server generates a list of recommendations for optimal medications, such as metformin and insulin, based on the extracted features.

[0465] 5. Analyze the user's (pharmacist's) emotional data (e.g., fatigue, impatience) collected by the emotion engine and reflect it in the recommended medication list.

[0466] 6. The server sends the final recommended medication list to the terminal.

[0467] 7. The terminal receives the list of recommended medications and displays it to the user (pharmacist) via the wearable display device.

[0468] 8. The user (pharmacist) checks the list of recommended medications and selects "metformin," which is suitable for the diabetic patient. The user decides on the prescription, taking into consideration feedback from the emotion engine.

[0469] 9. The user (pharmacist) determines "metformin" as the final prescription and records it in the patient's chart.

[0470] Prompt Sentence Examples

[0471] "A user inputs the test results of a diabetic patient into the smart glasses. The emotion engine detects the user's emotions based on the results and sends them to the server."

[0472] In this way, the system of the present invention comprehensively utilizes clinical test data, medical record information, and emotional data to achieve more accurate prescription drug recommendations.

[0473] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0474] Step 1:

[0475] The user uses the wearable display device to input the patient's clinical test data and medical record information into the terminal by voice. The terminal formats the input clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) and sends them to the server.

[0476] Step 2:

[0477] The server receives the clinical test data and medical record information sent from the terminal. The server checks the consistency and completeness of the received data, specifically checking the data format and missing values, and generates warning messages if necessary.

[0478] Step 3:

[0479] The server compares the received clinical test data and medical record information with a drug database to obtain relevant and up-to-date drug information. In this process, it extracts the effects, side effects, and interactions of the corresponding drugs from the database.

[0480] Step 4:

[0481] The server uses a specific algorithm to classify the received data and extract features. For example, if a diabetic patient's blood sugar level exceeds the normal range, the server classifies the data as "hyperglycemia." The extracted features, such as diabetes and hyperglycemia, are listed.

[0482] Step 5:

[0483] The server generates a list of optimal medication recommendations based on the extracted features. For example, based on the features of hyperglycemia, drugs such as "metformin" and "insulin" are added to the recommendation list. Side effect risk information based on chronic illnesses and interactions with other drugs is also reflected.

[0484] Step 6:

[0485] The server recognizes the user's (pharmacist's) emotional data using an emotion engine. The emotion engine analyzes data obtained from sensors installed in the wearable display device and detects the user's emotional state (e.g., fatigue, impatience).

[0486] Step 7:

[0487] The server analyzes the emotion data collected by the emotion engine and reflects it in the recommended medication list. For example, for a user who is fatigued, medications that are easy to select are displayed preferentially on the list.

[0488] Step 8:

[0489] The server transmits the generated recommended medication list to the terminal. For example, data including detailed information on "metformin" and "insulin" is transmitted to the terminal as the recommended medication list.

[0490] Step 9:

[0491] The terminal displays the list of recommended medications sent from the server on the wearable display device. The user (pharmacist) checks the displayed list of medications and selects the appropriate medication. For example, specific information about "metformin" (efficacy, side effects, drug interactions) is displayed.

[0492] Step 10:

[0493] The user (pharmacist) decides on the final prescription while referring to the recommended medication list. The selected medication (e.g., metformin) is recorded in the patient's medical record and prescribed to the patient. In some cases, feedback from the emotion engine is also used to help with the prescription decision.

[0494] In this way, the system comprehensively utilizes clinical test data, medical record information, and emotional data to achieve efficient and highly accurate drug selection.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] [Second embodiment]

[0499] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0500] 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.

[0501] 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).

[0502] 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.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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.

[0508] 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.

[0509] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0510] 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."

[0511] The present invention is a system that enables doctors to prepare prescriptions efficiently and with high accuracy, and an embodiment of the system will be described in detail below. This system is composed of a server, a terminal, and a user (doctor).

[0512] Server Processing

[0513] The server plays a central role in the system and performs the following processes:

[0514] 1. Data Reception

[0515] The server receives the clinical test data and medical record information sent from the terminal.

[0516] Check the consistency and completeness of the data received.

[0517] 2. Database Reference

[0518] The server accesses a drug database to obtain the latest drug information and statistical data.

[0519] 3. Data Classification and Feature Extraction

[0520] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[0521] 4. Generating medication recommendations

[0522] The server generates a list of optimal drug recommendations based on the extracted features.

[0523] This list also reflects the risk of side effects based on pre-existing conditions and interactions with other medications.

[0524] 5. Sending the results

[0525] The server transmits the recommended medication list to the terminal.

[0526] Terminal handling

[0527] The terminal is a device operated by a doctor and performs the following processes:

[0528] 1. Data entry and submission

[0529] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[0530] The terminal formats the input data and sends it to the server.

[0531] 2. Receive a list of recommended medications

[0532] The terminal receives the recommended medication list sent from the server.

[0533] 3. Display and confirmation

[0534] The terminal displays the received recommended drug list to the user (doctor).

[0535] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[0536] User (doctor) processing

[0537] The user (doctor) performs the following processes through the system.

[0538] 1. Data Entry

[0539] The user (doctor) inputs clinical test data and medical record information into the terminal.

[0540] 2. Check recommended medications

[0541] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[0542] 3. Final formulation decision

[0543] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[0544] Record the medication selected and the reason for it in the patient's chart.

[0545] Specific examples

[0546] For example, consider the case where a patient has diabetes.

[0547] 1. Data entry and submission

[0548] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[0549] The terminal transmits this data to the server.

[0550] 2. Server Processing

[0551] The server checks the received data for consistency and completeness.

[0552] The server accesses the drug database to obtain the latest drug information.

[0553] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[0554] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[0555] The list takes into account the risk of side effects and sends a list of recommended medications to the terminal.

[0556] 3. Receive and review the recommended medication list

[0557] The terminal receives the recommended medication list and displays it to the user (doctor).

[0558] The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[0559] 4. Final formulation decision

[0560] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[0561] In this way, the system of the present invention efficiently processes clinical test data and medical record information and recommends optimal medications, thereby reducing the burden on doctors and helping to provide prompt and appropriate treatment to patients.

[0562] The processing flow will be explained below.

[0563] Step 1:

[0564] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[0565] Step 2:

[0566] The terminal formats the entered clinical test data and medical record information and generates a data transmission request to be sent to the server.

[0567] Step 3:

[0568] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[0569] Step 4:

[0570] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[0571] Step 5:

[0572] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[0573] Step 6:

[0574] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[0575] Step 7:

[0576] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[0577] Step 8:

[0578] The server transmits the generated recommended drug list to the terminal.

[0579] Step 9:

[0580] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[0581] Step 10:

[0582] The user (doctor) checks the list of recommended medications displayed on the terminal and selects the medication appropriate for the patient.

[0583] Step 11:

[0584] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[0585] Example 1

[0586] 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."

[0587] Conventional medical systems have issues with the accuracy and speed with which they can efficiently process clinical test data and medical record information and recommend optimal medications to doctors. Furthermore, they lack a mechanism for effectively assessing the risk of side effects due to chronic illnesses or interactions with other medications, placing a heavy burden on doctors and making it difficult to provide appropriate treatment to patients promptly. To address these issues, the present invention aims to provide a more efficient and accurate prescription preparation system.

[0588] 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.

[0589] In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, a means for formatting data entered by a user on a terminal and transmitting the data to the server, and a means for displaying the list of recommended drugs transmitted from the server. This enables rapid and accurate drug recommendations based on the clinical test data and medical record information, and allows appropriate evaluation of the risk of side effects due to chronic illnesses and drug interactions. It also reduces the burden on doctors and enables prompt and accurate treatment for patients.

[0590] "Laboratory data" refers to the results of various tests performed to assess a patient's health, including blood tests, urine tests, and diagnostic imaging.

[0591] "Medical record information" refers to the comprehensive medical record of a patient, including medical records, medical history, current medication status, allergy information, etc.

[0592] The "drug database" is a database that collects information about various drugs, including drug efficacy, side effects, drug interactions, and the latest clinical research results.

[0593] A "specific algorithm" refers to a computational method that analyzes input data and extracts certain patterns or characteristics, using machine learning and statistical analysis techniques.

[0594] "Feature extraction" is the process of finding important information and patterns in input data, which allows us to understand the essence of the data.

[0595] "Recommending" means showing the best option based on specific conditions and data. This system plays a role in suggesting the best medication to doctors.

[0596] The "recommended drug list" is a list of drugs selected based on data analyzed by the system, including information on efficacy, side effects, and risks.

[0597] A "terminal" is a device used by a physician, including a desktop computer, notebook, tablet, etc.

[0598] "Formatting" is the process of converting data into a specific structure or form, which improves data compatibility and processing efficiency.

[0599] "User" refers to anyone who operates this system, especially a doctor who uses this system in the medical field.

[0600] The "server" is the central computer in this system, which handles data transfer and processing.

[0601] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of three elements: a server, a terminal, and a user (doctor).

[0602] Server Processing

[0603] The server plays a central role in this system and performs the following processes:

[0604] Data reception

[0605] The server receives the clinical test data and medical record information sent from the terminal. After receiving the data, the server checks the consistency and completeness of the data. This check process includes checking the data structure and format. The server receives the data securely using the HTTPS protocol.

[0606] Database Reference

[0607] The server accesses the drug database to retrieve the latest drug information and statistical data. This process uses SQL queries. The drug database can be a relational database such as MySQL or PostgreSQL.

[0608] Data Classification and Feature Extraction

[0609] The server classifies the received data using a specific algorithm and extracts features. It does this using machine learning algorithms (e.g., random forests and support vector machines).

[0610] Generate medication recommendations

[0611] The server generates a list of optimal medication recommendations based on the extracted features, taking into account pre-existing conditions and the risk of side effects due to interactions with other medications.

[0612] Sending the results

[0613] The server converts the recommended medication list into JSON format and sends it to the terminal using the HTTPS protocol.

[0614] Terminal handling

[0615] The terminal is a device operated by a doctor and performs the following processes:

[0616] Data entry and submission

[0617] The user (doctor) enters the patient's laboratory test data and medical record information into the terminal, which formats and transmits this data to the server using the HTTPS protocol.

[0618] Receive a list of recommended medications

[0619] The terminal receives the recommended drug list sent from the server and converts the received data into an internal data structure.

[0620] Display and confirmation

[0621] The terminal displays the received list of recommended medications to the user (doctor). The user (doctor) checks the displayed list and, if necessary, conducts further research and consideration. The terminal also has an interface for providing detailed information.

[0622] User (doctor) processing

[0623] The user (doctor) performs the following processes through the system.

[0624] Data Entry

[0625] The user (physician) enters laboratory test data and medical record information into the terminal, either manually using an input form or by importing data from an existing electronic medical record system.

[0626] Check recommended medications

[0627] The user (doctor) checks the list of recommended medications displayed on the device and selects the appropriate medication. Detailed information on each medication can also be viewed.

[0628] Final formulation decision

[0629] The user (doctor) selects the most appropriate medication and decides on the final prescription. The information on the selected medication is recorded in the patient's chart.

[0630] Specific examples

[0631] For example, consider the case where a patient has diabetes.

[0632] Data entry and submission

[0633] The user (doctor) inputs the clinical test data (e.g., blood glucose level 180 mg / dL) of a diabetic patient and medical record information (e.g., medical history, no current medication) into the terminal. The terminal converts this data into JSON format and sends it to the server as an HTTPS POST request.

[0634] Server Processing

[0635] The server checks the received data for consistency and completeness. Next, it accesses a drug database and executes SQL queries to obtain the latest drug information. It then uses machine learning algorithms to classify the data and extract features related to diabetes. It then lists the most suitable drugs (e.g., metformin, insulin) and finalizes the list by taking into account the risk of side effects. Finally, it sends the recommended drug list in JSON format to the device.

[0636] Receive and review recommended medication lists

[0637] The device receives the list of recommended medications and displays it to the user (doctor). The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[0638] Final formulation decision

[0639] The user (doctor) decides on "metformin" as the final prescribed medication and records that information in the patient's chart.

[0640] Prompt Sentence Examples

[0641] "Please explain in natural language the process by which a doctor uses the system to determine a prescription for a diabetic patient."

[0642] As described above, the system of the present invention efficiently processes clinical test data and medical record information and makes highly accurate drug recommendations, thereby reducing the burden on doctors and providing patients with prompt and appropriate treatment.

[0643] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0644] Step 1: Enter and submit data

[0645] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal. Specifically, the user records blood glucose levels, medical history, current medication status, etc. in the input form on the terminal.

[0646] The terminal formats the entered data into JSON format and sends it to the server using the HTTPS protocol.

[0647] Input: Laboratory test data and medical record information (e.g., blood glucose level, medical history)

[0648] Output: Formatted JSON data sent to the server

[0649] Step 2: Receiving data

[0650] The server receives the JSON formatted clinical test data and medical record information sent from the terminal via the HTTPS protocol.

[0651] Upon receipt, the server checks the data for consistency and completeness, specifically verifying that the data structure and format are correct.

[0652] Input: JSON data sent from the terminal

[0653] Output: Verified laboratory data and medical record information

[0654] Step 3: Database Reference

[0655] The server accesses the drug database and executes SQL queries to retrieve the latest drug information.

[0656] The acquired information includes drug efficacy, side effects, and drug interaction information.

[0657] Input: Validated data stored on the server

[0658] Output: Drug information retrieved from the drug database

[0659] Step 4: Data classification and feature extraction

[0660] The server uses specific machine learning algorithms (e.g., random forests or support vector machines) to classify the data and extract features.

[0661] This allows for the extraction of important health conditions such as diabetes and hyperglycemia.

[0662] Input: Validated data and drug database information

[0663] Output: Extracted features (e.g., diabetes, hyperglycemia)

[0664] Step 5: Generate drug recommendations

[0665] The server generates a list of recommended optimal medications based on the extracted features, and a recommendation engine ranks the medications based on each feature, taking into account the risk of side effects.

[0666] A list of recommended medications is completed, including information on the efficacy, side effects, and risks of each recommended medication.

[0667] Input: Extracted features

[0668] Output: Recommended medication list

[0669] Step 6: Sending the results

[0670] The server converts the generated list of recommended medications into JSON format and sends it to the terminal using the HTTPS protocol.

[0671] Input: Recommended medication list

[0672] Output: JSON data sent to the terminal

[0673] Step 7: Receive a list of recommended medications

[0674] The terminal receives the recommended drug list in JSON format sent from the server.

[0675] Converts received data into an internal data structure.

[0676] Input: JSON data sent from the server

[0677] Output: Recommended medication list converted into internal data structure

[0678] Step 8: View and verify

[0679] The terminal displays the recommended medication list to the user (doctor) on a GUI, and the doctor can also access detailed information.

[0680] Input: Recommended medication list converted into internal data structure

[0681] Output: A list of recommended medications that is displayed to the user

[0682] Step 9: Selecting a recommended medication

[0683] The user (doctor) checks the displayed list of recommended medications and selects an appropriate medication.

[0684] View details to investigate further if needed.

[0685] Input: Recommended medication list shown to user

[0686] Output: Selected drug information

[0687] Step 10: Finalize the formula

[0688] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[0689] Record the final prescription information in the patient's chart.

[0690] Input: Selected drug information

[0691] Output: Prescription information recorded in the patient record

[0692] By using the specific processing steps described above, the system of the present invention can reduce the burden on doctors and provide prompt and appropriate treatment to patients.

[0693] (Application example 1)

[0694] 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."

[0695] In modern autonomous vehicles, it is difficult to monitor the health status of passengers in real time and take necessary measures promptly. Especially when clinical testing equipment is not installed in the vehicle, it is important to respond quickly when a passenger suddenly becomes ill. Furthermore, there is a need for a system that can recommend optimal medications based on medical history and current medication status, and can take emergency action after an abnormality is discovered. Ensuring consistency and completeness when handling large amounts of data is also a challenge.

[0696] 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.

[0697] In this invention, the server includes means for receiving clinical test data and medical record information, means for acquiring drug information from a drug database, means for classifying data using a specific algorithm and extracting features, means for recommending optimal drugs based on the features, means for generating and transmitting a list of recommended drugs, means for collecting and analyzing biometric data of the passenger, means for constantly monitoring health data and detecting abnormalities, and means for automatically guiding the passenger to the nearest medical institution in an emergency. This makes it possible to monitor the passenger's biometric data in real time, quickly recommend optimal drugs, and navigate to an appropriate medical institution in an emergency.

[0698] "Laboratory data" refers to numerical information obtained from tests performed by medical institutions to assess a patient's health status.

[0699] "Medical record information" is data that includes medical records such as a patient's medical history and prescription history.

[0700] A "drug database" is a digital database that stores information about various drugs.

[0701] An "algorithm" is a set of rules and procedures for processing data and performing classification and feature extraction.

[0702] "Drug recommendation" is the process of selecting the most appropriate medication based on a patient's specific symptoms and clinical test data.

[0703] A "recommended drug list" is a list of drugs suitable for a patient generated by an AI model or algorithm.

[0704] "Passenger" refers to a person riding in an autonomous vehicle.

[0705] "Biometric data" is digital information obtained from the human body, such as heart rate, blood pressure, and blood sugar levels.

[0706] "Anomaly detection" is the process of detecting biometric data that deviates from the normal range.

[0707] "Emergency Navigation" is a function that automatically guides passengers to the nearest medical institution if an abnormality in their health condition is detected.

[0708] The present invention is a system that monitors the health status of passengers in autonomous vehicles in real time and recommends appropriate medications when necessary. This system operates based on three main components: a server, a terminal, and a user (vehicle passenger).

[0709] Server Processing

[0710] The server plays a central role in the entire system and performs the following processes:

[0711] Data receipt and confirmation:

[0712] The server receives the lab test data and medical record information sent from the device and checks its consistency and completeness. This data includes heart rate, blood pressure, blood glucose level, etc. The server then verifies the received data with an integrity check algorithm.

[0713] Database Reference:

[0714] The server accesses the drug database to obtain the latest drug information, allowing the information on drugs suitable for each patient to be updated as needed.

[0715] Data classification and feature extraction:

[0716] Data analysis algorithms are used to classify incoming data and extract key features, which allow for drug recommendations tailored to specific diseases and health conditions.

[0717] Generate drug recommendations:

[0718] Based on the extracted features, the system generates a list of optimal drug recommendations. It also evaluates the risk of side effects based on pre-existing conditions and drug interactions and reflects this in the recommendation list.

[0719] Sending results:

[0720] A list of recommended medications is sent to the terminal and displayed to the passenger.

[0721] Terminal handling

[0722] The terminal is a device such as a tablet or smartphone installed inside the autonomous vehicle, and performs the following processes.

[0723] Data entry and submission:

[0724] Passengers input biometric data measured using sensors such as a heart rate monitor, blood pressure monitor, and blood glucose monitor into a terminal, which then transmits this data to a server.

[0725] Receive and view recommended medication lists:

[0726] The terminal receives the list of recommended medications sent from the server and displays it to the passenger.

[0727] Anomaly detection and emergency response:

[0728] The device constantly monitors biometric data and, if it detects an abnormality, quickly directs the user to the nearest medical institution.

[0729] User (vehicle passenger) processing

[0730] The user (vehicle passenger) performs the following processes through the system.

[0731] Data Entry:

[0732] The user measures his / her own biometric data and inputs it into the terminal.

[0733] Check recommended medications:

[0734] The user checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[0735] Take necessary action:

[0736] The user then goes to the indicated medical facility in case of an emergency or takes the recommended medication.

[0737] For example, the following prompt sentence can be input into a generative AI model to recommend an appropriate medication:

[0738] Example input:

[0739] "The patient is 50 years old, has a blood pressure of 160 / 100 mmHg, and a blood glucose level of 150 mg / dL. Please recommend the appropriate medication for this patient."

[0740] This prompt may recommend, for example, an ACE inhibitor (e.g., losartan) as an antihypertensive drug or metformin as a hypoglycemic drug. In this way, the system of the present invention can efficiently monitor the passenger's health status and provide prompt and appropriate responses.

[0741] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0742] Step 1:

[0743] Data collection

[0744] The device measures biometric data such as heart rate, blood pressure, and blood glucose level from passengers in the vehicle. This data is acquired using sensors such as a blood pressure monitor, heart rate sensor, and blood glucose meter. The input is biometric data obtained from various sensors, and the output is the measured biometric data.

[0745] Step 2:

[0746] Data transmission

[0747] The device sends the biometric data acquired in step 1 to the server. The protocol used for data transmission is HTTP or HTTPS. The input is the measured biometric data, and the output is the biometric data formatted to be received by the server.

[0748] Step 3:

[0749] Data Receipt and Confirmation

[0750] The server receives the biometric data received from the terminal and checks its consistency and completeness. It uses a data integrity check algorithm to detect missing or outlier values. The input is the biometric data received by the server, and the output is the biometric data that has been checked for consistency and completeness.

[0751] Step 4:

[0752] Database Reference

[0753] The server accesses the drug database to obtain the latest drug information. It then executes a database query to obtain drug information appropriate for the current condition. The input is the confirmed biometric data, and the output is the corresponding drug information.

[0754] Step 5:

[0755] Data Classification and Feature Extraction

[0756] The server uses a specific algorithm to classify the received data and extract features. This uses a data analysis algorithm. The input is the drug information and biometric data obtained from the drug database, and the output is the extracted feature data.

[0757] Step 6:

[0758] Generate medication recommendations

[0759] The server generates a list of optimal medication recommendations based on the extracted feature data. It also evaluates the risk of side effects due to chronic illnesses and drug interactions and reflects this in the list. The input is feature data and drug data, and the output is a list of recommended medications. At this time, it is also possible to create prompt sentences using a generative AI model. Example: "The patient is 50 years old, his blood pressure is 160 / 100 mmHg, and his blood sugar level is 150 mg / dL. Please recommend the appropriate medication for this patient."

[0760] Step 7:

[0761] Sending the results

[0762] The server sends the generated recommended medication list to the terminal. The input is the recommended medication list, and the output is the recommended medication list formatted to be received by the terminal.

[0763] Step 8:

[0764] Results display

[0765] The terminal displays the recommended medication list received from the server to the passenger. The display is on a tablet or smartphone. The input is the recommended medication list, and the output is a list displayed in a format that can be viewed by the passenger.

[0766] Step 9:

[0767] Anomaly detection and emergency response

[0768] The device constantly monitors vital signs and guides the user to the nearest medical facility if an abnormality is detected. It uses a GPS module and a navigation system to provide prompt guidance. The input is real-time vital signs, and the output is emergency response alerts and navigation information if an abnormality is detected.

[0769] 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.

[0770] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy, and its configuration and operation method will be described in detail. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[0771] Server Processing

[0772] The server plays a central role in the system and performs the following processes:

[0773] 1. Data Reception

[0774] The server receives the clinical test data and medical record information sent from the terminal.

[0775] Check the consistency and completeness of the data received.

[0776] 2. Database Reference

[0777] The server accesses a drug database to obtain the latest drug information and statistical data.

[0778] 3. Data Classification and Feature Extraction

[0779] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[0780] 4. Generating medication recommendations

[0781] The server generates a list of optimal drug recommendations based on the extracted features.

[0782] This list also reflects information on the risk of side effects based on pre-existing conditions and interactions with other medications.

[0783] 5. Use of Emotion Engine

[0784] The server uses an emotion engine to recognize the user's (doctor's) emotions.

[0785] The emotional data collected by the emotion engine is analyzed and reflected in the recommended medication list.

[0786] 6. Submitting the results

[0787] The server transmits the recommended medication list to the terminal.

[0788] Terminal handling

[0789] The terminal is a device operated by a doctor and performs the following processes:

[0790] 1. Data entry and submission

[0791] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[0792] The terminal formats the input data and sends it to the server.

[0793] 2. Receive a list of recommended medications

[0794] The terminal receives the recommended medication list sent from the server.

[0795] 3. Display and confirmation

[0796] The terminal displays the received recommended drug list to the user (doctor).

[0797] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[0798] User (doctor) processing

[0799] The user (doctor) performs the following processes through the system.

[0800] 1. Data Entry

[0801] The user (doctor) inputs clinical test data and medical record information into the terminal.

[0802] 2. Check recommended medications

[0803] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[0804] The final prescription is determined with reference to the emotional data provided by the emotion engine.

[0805] 3. Final formulation decision

[0806] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[0807] Specific examples

[0808] For example, consider the process when a diabetic patient visits a doctor.

[0809] 1. Data entry and submission

[0810] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[0811] The terminal transmits this data to the server.

[0812] 2. Server Processing

[0813] The server checks the consistency and integrity of the data received.

[0814] The server accesses the drug database to obtain the latest drug information.

[0815] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[0816] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[0817] The emotion engine analyzes the user's (doctor's) emotional data (e.g., fatigue, impatience) collected and reflects it in the recommended medication list.

[0818] A list of recommended medications is sent to the terminal.

[0819] 3. Receive and review the recommended medication list

[0820] The terminal receives the recommended medication list and displays it to the user (doctor).

[0821] The user (doctor) checks the list and selects "metformin," which is suitable for diabetic patients.

[0822] The prescription is decided taking into consideration feedback from the emotion engine.

[0823] 4. Final formulation decision

[0824] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[0825] In this way, the system of the present invention, which combines an emotion engine, can recommend prescription drugs with greater accuracy by taking into account the user's (doctor's) emotional data in addition to clinical test data and medical record information. This reduces the burden on doctors and enables them to provide patients with prompt and accurate treatment.

[0826] The processing flow will be explained below.

[0827] Step 1:

[0828] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[0829] Step 2:

[0830] The terminal formats the input clinical test data and medical record information and generates a data transmission request to be transmitted to the server.

[0831] Step 3:

[0832] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[0833] Step 4:

[0834] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[0835] Step 5:

[0836] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[0837] Step 6:

[0838] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[0839] Step 7:

[0840] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[0841] Step 8:

[0842] The server uses an emotion engine to recognize the user's (doctor's) emotions, and collects voice and facial expression data when the user operates the device.

[0843] Step 9:

[0844] The emotion engine analyzes the collected emotion data (e.g., stress, fatigue, impatience) to determine the user's current emotional state.

[0845] Step 10:

[0846] The server takes into account the emotional data recognized by the emotion engine and applies emotion-based adjustments to the recommended medication list.

[0847] Step 11:

[0848] The server transmits the adjusted recommended medication list to the terminal.

[0849] Step 12:

[0850] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[0851] Step 13:

[0852] The user (doctor) checks the adjusted list of recommended medications displayed on the terminal and selects the appropriate medication for the patient.

[0853] Step 14:

[0854] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[0855] Example 2

[0856] 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."

[0857] Conventional drug recommendation systems did not take into account the emotional state of the doctor when recommending drugs using clinical test data and medical record information. As a result, the doctor's judgment could be affected by fatigue or stress, and the optimal drug could not be prescribed. Furthermore, recommendations were made without verifying the consistency and completeness of the data, which created a risk of selecting the wrong drug. The present invention aims to solve these problems.

[0858] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for checking the consistency and completeness of the received data, a means for acquiring drug information from a drug database, a means for classifying data using a specific algorithm and extracting features, a means for recommending optimal drugs based on the extracted features, a means for generating and transmitting a recommended drug list, and a means for recognizing the user's emotions, analyzing the emotion data, and reflecting the analysis results in the recommendation list. This enables highly accurate drug recommendations that take the doctor's emotional state into consideration.

[0859] "Clinical test data" refers to information resulting from analyses of samples such as blood, urine, and tissue of patients conducted at medical institutions such as hospitals and clinics.

[0860] "Medical record information" refers to a set of information that a doctor needs when treating a patient, such as the patient's medical history, current symptoms, and prescribed medications.

[0861] "Consistency" means that data is consistent in context and maintains logical consistency.

[0862] "Completeness" means that all data is included without any missing or incorrect information.

[0863] A "pharmaceutical database" is a database system that systematically collects and organizes information on various pharmaceuticals and stores it in a searchable and accessible format.

[0864] An "algorithm" is a procedure or computational sequence designed to solve a particular problem.

[0865] "Feature extraction" is the process of identifying and extracting important information and patterns from data.

[0866] A "recommendation" is a presentation of an option that is considered optimal based on specific conditions and information.

[0867] "Emotion recognition" is the process of detecting and evaluating a user's emotional state using sensors and analytical techniques.

[0868] "Emotion data" refers to observed and analyzed data such as numerical values ​​and categorical information related to the user's emotional state.

[0869] This paper describes in detail the configuration and operation of a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[0870] The server plays a central role in the system and provides multiple functions. First, the server receives clinical test data and medical record information sent from the terminal using the HTTPS protocol. The received data is checked for consistency and completeness. If the data is inconsistent or missing, the server detects this and performs appropriate error handling.

[0871] The server then accesses the drug database to retrieve the latest drug information and statistical data. This process is performed using a database management system, for example, MongoDB or MySQL. The retrieved data is cached internally on the server for efficient access.

[0872] The server then uses specific algorithms, such as Python's Scikit-learn library, to classify and extract features from the received lab test data and medical records. This feature extraction process involves using, for example, decision tree algorithms to classify the data based on the patient's medical history and current clinical data.

[0873] Based on the results of feature extraction, the server recommends the most appropriate medication. This recommendation takes into account side effect risk information and includes a detailed risk assessment, including pre-existing conditions and interactions with other medications. Before the recommended medication list is finally sent to the device, an emotion engine analyzes the collected user (doctor) emotion data and reflects it in the recommendation list. This emotion engine is implemented, for example, using the Affectiva API.

[0874] The terminal functions as a device operated by the user (doctor), and inputs and checks data through a GUI (graphical user interface). The user (doctor) inputs the patient's clinical test data and medical record information into the terminal and sends this to the server. When the terminal receives a list of recommended medications from the server, it displays this list on the GUI. The user (doctor) checks the displayed list and, if necessary, conducts further research or consideration.

[0875] As a concrete example, consider a diabetic patient undergoing a medical examination. The user (doctor) enters clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into a terminal and sends them to the server. The server receives this data and checks its consistency and completeness. The server then retrieves the latest drug information from a pharmaceutical database and classifies the data and extracts features using a specific algorithm. It then generates a list of recommended optimal medications, such as "metformin" and "insulin," and analyzes the user's (doctor's) emotional data (e.g., fatigue), using an emotion engine to reflect this in the recommendation list. This list of recommended medications is sent to the terminal and reviewed by the user (doctor). The user (doctor) then decides on "metformin" as the final prescription medication and records it in the patient's medical record.

[0876] As an example of a prompt, give the generative AI model the following input:

[0877] "Please recommend an appropriate medication based on the clinical data and medical record information of a diabetic patient (blood glucose level 180 mg / dL, no medical history). Also, please display the following recommended medication assuming it is used by a doctor who is feeling fatigued."

[0878] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0879] Step 1:

[0880] The terminal collects the patient's clinical test data and medical record information entered by the user (doctor) through an input device (e.g., keyboard or tablet). The input data is information such as blood glucose levels and medical history. This is converted into JSON format and sent to the server using the HTTPS protocol. The input is the clinical test data and medical record information entered by the user (doctor), and the output is JSON format data sent to the server.

[0881] Step 2:

[0882] The server receives clinical test data and medical record information in JSON format from the terminal. The received data is checked for consistency and completeness within the system. Specifically, it checks whether each field of the data has been entered properly and whether there are any inconsistencies. The input is the JSON data received from the terminal, and the output is the checked data.

[0883] Step 3:

[0884] The server uses the validated data to issue a search query to the drug database. For example, it uses an SQL query to retrieve the latest drug information from the database. This process uses a database management system such as MongoDB or MySQL. Specifically, it establishes a database connection and executes the appropriate query. The input is the validated data, and the output is the retrieved drug information.

[0885] Step 4:

[0886] The server uses a specific algorithm to classify data and extract features based on the acquired drug information, clinical test data, and medical record information. For example, it applies a decision tree algorithm using Python's Scikit-learn library. Specifically, it performs analysis based on the patient's medical history and test results. The input is the acquired drug information and confirmed data, and the output is classified feature data.

[0887] Step 5:

[0888] The server recommends the most appropriate medication based on the extracted feature data, taking into account the risk of side effects and drug interactions. The recommendation list is generated based on internal rules. The input is the classified feature data, and the output is a list of recommended medications.

[0889] Step 6:

[0890] The server uses an emotion engine based on the generated recommended drug list to analyze the user's (doctor's) emotional data. This process uses, for example, the Affectiva API. Specifically, it acquires the user's emotional data and reflects it in the recommendation list. The input is the recommended drug list and emotional data, and the output is a recommended drug list that reflects the emotional data.

[0891] Step 7:

[0892] The server sends the final recommended drug list to the terminal using the HTTPS protocol. Specifically, it formats the list and transfers it to the terminal. The input is the recommendation list that reflects the emotion data, and the output is the recommendation list sent to the terminal.

[0893] Step 8:

[0894] The terminal displays the recommended drug list received from the server on a GUI. The user (doctor) checks this list and selects the most appropriate drug based on the options presented. Specifically, the user selects an item on the list and operates the UI to check detailed information. The input is the recommended list received from the server, and the output is the drug selected by the user.

[0895] Step 9:

[0896] The user (doctor) decides on the selected medication as the final prescription and records it in the patient's chart. This adds the prescription information to the electronic medical record system, making it available for future reference. The specific operation involves inputting and saving the prescription information. The input is the medication selected by the user, and the output is the prescription information recorded in the patient's chart.

[0897] (Application example 2)

[0898] 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."

[0899] In modern medical settings, doctors are required to write prescriptions efficiently and with high accuracy. However, they need to process a large amount of information in a short amount of time, and their own emotions and fatigue can sometimes affect their judgment. Furthermore, selecting medications requires assessing the risk of pre-existing conditions and drug interactions, and it is difficult to perform these tasks consistently in a single system.

[0900] Furthermore, efficient information processing and display is required when pharmacists select the most appropriate medication based on conversations with patients in physical stores such as pharmacies. To address these issues, a system is needed that processes information holistically and efficiently, reducing the burden on doctors and pharmacists.

[0901] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, and a means for displaying the list of recommended drugs on a wearable display device. This enables doctors and pharmacists to select drugs efficiently and with high accuracy and provide patients with prompt and appropriate treatment.

[0902] "Clinical test data" refers to medical data obtained as a result of a patient's blood test, urine test, diagnostic imaging, etc.

[0903] "Medical record information" refers to medical records necessary for medical treatment, such as a patient's medical history, medical history, medication information, and allergy information.

[0904] A "drug database" is a database that contains information about drug ingredients, effects, side effects, and interactions with other drugs.

[0905] A "specific algorithm" is a mathematical or statistical procedure used to classify data or extract features.

[0906] A "feature extraction method" is a technique or method for extracting important patterns or information from data.

[0907] The "medication recommendation method" is a process for selecting the most suitable medication for a patient based on the extracted features.

[0908] A "recommended drug list" is a list of drugs selected based on specific conditions or characteristics.

[0909] A "wearable display device" is a display device worn by doctors and pharmacists, such as glasses or a head-mounted display.

[0910] An "emotion engine" is a technology or software that recognizes and analyzes a user's emotional state and reflects it in the system's recommendations.

[0911] This invention is a system that efficiently processes clinical test data and medical record information, allowing pharmacists to select prescription drugs quickly and accurately in physical stores. The system of this invention is composed of a server, a terminal, a user (pharmacist), an emotion engine, and a wearable display device.

[0912] Server Processing

[0913] The server plays a central role in the system and performs the following processes:

[0914] 1. The server receives the clinical test data and medical record information sent from the terminal.

[0915] 2. The server checks the received data for consistency and integrity.

[0916] 3. The server accesses the drug database and obtains the latest drug information.

[0917] 4. The server uses specific algorithms to classify and extract features from the received clinical test data and medical record information.

[0918] 5. The server generates a list of optimal drug recommendations based on the extracted features.

[0919] 6. The server uses an emotion engine to recognize the user's (pharmacist's) emotional data and reflects it in the recommended medication list.

[0920] 7. The server sends the generated recommended medication list to the terminal.

[0921] Terminal handling

[0922] The terminal is a device operated by a pharmacist and performs the following processes:

[0923] 1. The terminal receives the patient's clinical test data and medical record information from the pharmacist via the wearable display device.

[0924] 2. The terminal formats the input data and sends it to the server.

[0925] 3. The terminal receives the recommended medication list sent from the server.

[0926] 4. The terminal displays the received list of recommended medications to the pharmacist via the wearable display device.

[0927] User (pharmacist) processing

[0928] The user (pharmacist) performs the following processes through the system.

[0929] 1. The user (pharmacist) uses the wearable display device to input the patient's clinical test data and medical record information into the terminal.

[0930] 2. The user (pharmacist) checks the list of recommended medications displayed on the terminal and selects the appropriate medication.

[0931] 3. The user (pharmacist) decides on the final prescription, taking into account the emotional data provided by the emotion engine.

[0932] 4. The user (pharmacist) prescribes the selected medication to the patient and records it in the patient's medical record.

[0933] Specific examples

[0934] For example, consider the case where a diabetic patient visits a drugstore for a consultation.

[0935] 1. The user (pharmacist) uses the wearable display device to input the diabetic patient's clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[0936] 2. The device sends this data to the server.

[0937] 3. The server checks the consistency and completeness of the received data, then classifies the data and extracts features using specific algorithms.

[0938] 4. The server generates a list of recommendations for optimal medications, such as metformin and insulin, based on the extracted features.

[0939] 5. Analyze the user's (pharmacist's) emotional data (e.g., fatigue, impatience) collected by the emotion engine and reflect it in the recommended medication list.

[0940] 6. The server sends the final recommended medication list to the terminal.

[0941] 7. The terminal receives the list of recommended medications and displays it to the user (pharmacist) via the wearable display device.

[0942] 8. The user (pharmacist) checks the list of recommended medications and selects "metformin," which is suitable for the diabetic patient. The user decides on the prescription, taking into consideration feedback from the emotion engine.

[0943] 9. The user (pharmacist) determines "metformin" as the final prescription and records it in the patient's chart.

[0944] Prompt Sentence Examples

[0945] "A user inputs the test results of a diabetic patient into the smart glasses. The emotion engine detects the user's emotions based on the results and sends them to the server."

[0946] In this way, the system of the present invention comprehensively utilizes clinical test data, medical record information, and emotional data to achieve more accurate prescription drug recommendations.

[0947] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0948] Step 1:

[0949] The user uses the wearable display device to input the patient's clinical test data and medical record information into the terminal by voice. The terminal formats the input clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) and sends them to the server.

[0950] Step 2:

[0951] The server receives the clinical test data and medical record information sent from the terminal. The server checks the consistency and completeness of the received data, specifically checking the data format and missing values, and generates warning messages if necessary.

[0952] Step 3:

[0953] The server compares the received clinical test data and medical record information with a drug database to obtain relevant and up-to-date drug information. In this process, it extracts the effects, side effects, and interactions of the corresponding drugs from the database.

[0954] Step 4:

[0955] The server uses a specific algorithm to classify the received data and extract features. For example, if a diabetic patient's blood sugar level exceeds the normal range, the server classifies the data as "hyperglycemia." The extracted features, such as diabetes and hyperglycemia, are listed.

[0956] Step 5:

[0957] The server generates a list of optimal medication recommendations based on the extracted features. For example, based on the features of hyperglycemia, drugs such as "metformin" and "insulin" are added to the recommendation list. Side effect risk information based on chronic illnesses and interactions with other drugs is also reflected.

[0958] Step 6:

[0959] The server recognizes the user's (pharmacist's) emotional data using an emotion engine. The emotion engine analyzes data obtained from sensors installed in the wearable display device and detects the user's emotional state (e.g., fatigue, impatience).

[0960] Step 7:

[0961] The server analyzes the emotion data collected by the emotion engine and reflects it in the recommended medication list. For example, for a user who is fatigued, medications that are easy to select are displayed preferentially on the list.

[0962] Step 8:

[0963] The server transmits the generated recommended medication list to the terminal. For example, data including detailed information on "metformin" and "insulin" is transmitted to the terminal as the recommended medication list.

[0964] Step 9:

[0965] The terminal displays the list of recommended medications sent from the server on the wearable display device. The user (pharmacist) checks the displayed list of medications and selects the appropriate medication. For example, specific information about "metformin" (efficacy, side effects, drug interactions) is displayed.

[0966] Step 10:

[0967] The user (pharmacist) decides on the final prescription while referring to the recommended medication list. The selected medication (e.g., metformin) is recorded in the patient's medical record and prescribed to the patient. In some cases, feedback from the emotion engine is also used to help with the prescription decision.

[0968] In this way, the system comprehensively utilizes clinical test data, medical record information, and emotional data to achieve efficient and highly accurate drug selection.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] [Third embodiment]

[0973] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0974] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0975] 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).

[0976] 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.

[0977] 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.

[0978] 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).

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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.

[0983] 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.

[0984] 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."

[0985] The present invention is a system that enables doctors to prepare prescriptions efficiently and with high accuracy, and an embodiment of the system will be described in detail below. This system is composed of a server, a terminal, and a user (doctor).

[0986] Server Processing

[0987] The server plays a central role in the system and performs the following processes:

[0988] 1. Data Reception

[0989] The server receives the clinical test data and medical record information sent from the terminal.

[0990] Check the consistency and completeness of the data received.

[0991] 2. Database Reference

[0992] The server accesses a drug database to obtain the latest drug information and statistical data.

[0993] 3. Data Classification and Feature Extraction

[0994] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[0995] 4. Generating medication recommendations

[0996] The server generates a list of optimal drug recommendations based on the extracted features.

[0997] This list also reflects the risk of side effects based on pre-existing conditions and interactions with other medications.

[0998] 5. Sending the results

[0999] The server transmits the recommended medication list to the terminal.

[1000] Terminal handling

[1001] The terminal is a device operated by a doctor and performs the following processes:

[1002] 1. Data entry and submission

[1003] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[1004] The terminal formats the input data and sends it to the server.

[1005] 2. Receive a list of recommended medications

[1006] The terminal receives the recommended medication list sent from the server.

[1007] 3. Display and confirmation

[1008] The terminal displays the received recommended drug list to the user (doctor).

[1009] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[1010] User (doctor) processing

[1011] The user (doctor) performs the following processes through the system.

[1012] 1. Data Entry

[1013] The user (doctor) inputs clinical test data and medical record information into the terminal.

[1014] 2. Check recommended medications

[1015] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[1016] 3. Final formulation decision

[1017] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[1018] Record the medication selected and the reason for it in the patient's chart.

[1019] Specific examples

[1020] For example, consider the case where a patient has diabetes.

[1021] 1. Data entry and submission

[1022] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[1023] The terminal transmits this data to the server.

[1024] 2. Server Processing

[1025] The server checks the received data for consistency and completeness.

[1026] The server accesses the drug database to obtain the latest drug information.

[1027] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[1028] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[1029] The list takes into account the risk of side effects and sends a list of recommended medications to the terminal.

[1030] 3. Receive and review the recommended medication list

[1031] The terminal receives the recommended medication list and displays it to the user (doctor).

[1032] The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[1033] 4. Final formulation decision

[1034] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[1035] In this way, the system of the present invention efficiently processes clinical test data and medical record information and recommends optimal medications, thereby reducing the burden on doctors and helping to provide prompt and appropriate treatment to patients.

[1036] The processing flow will be explained below.

[1037] Step 1:

[1038] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[1039] Step 2:

[1040] The terminal formats the entered clinical test data and medical record information and generates a data transmission request to be sent to the server.

[1041] Step 3:

[1042] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[1043] Step 4:

[1044] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[1045] Step 5:

[1046] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[1047] Step 6:

[1048] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[1049] Step 7:

[1050] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[1051] Step 8:

[1052] The server transmits the generated recommended drug list to the terminal.

[1053] Step 9:

[1054] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[1055] Step 10:

[1056] The user (doctor) checks the list of recommended medications displayed on the terminal and selects the medication appropriate for the patient.

[1057] Step 11:

[1058] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[1059] Example 1

[1060] 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."

[1061] Conventional medical systems have issues with the accuracy and speed with which they can efficiently process clinical test data and medical record information and recommend optimal medications to doctors. Furthermore, they lack a mechanism for effectively assessing the risk of side effects due to chronic illnesses or interactions with other medications, placing a heavy burden on doctors and making it difficult to provide appropriate treatment to patients promptly. To address these issues, the present invention aims to provide a more efficient and accurate prescription preparation system.

[1062] 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.

[1063] In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, a means for formatting data entered by a user on a terminal and transmitting the data to the server, and a means for displaying the list of recommended drugs transmitted from the server. This enables rapid and accurate drug recommendations based on the clinical test data and medical record information, and allows appropriate evaluation of the risk of side effects due to chronic illnesses and drug interactions. It also reduces the burden on doctors and enables prompt and accurate treatment for patients.

[1064] "Laboratory data" refers to the results of various tests performed to assess a patient's health, including blood tests, urine tests, and diagnostic imaging.

[1065] "Medical record information" refers to the comprehensive medical record of a patient, including medical records, medical history, current medication status, allergy information, etc.

[1066] The "drug database" is a database that collects information about various drugs, including drug efficacy, side effects, drug interactions, and the latest clinical research results.

[1067] A "specific algorithm" refers to a computational method that analyzes input data and extracts certain patterns or characteristics, using machine learning and statistical analysis techniques.

[1068] "Feature extraction" is the process of finding important information and patterns in input data, which allows us to understand the essence of the data.

[1069] "Recommending" means showing the best option based on specific conditions and data. This system plays a role in suggesting the best medication to doctors.

[1070] The "recommended drug list" is a list of drugs selected based on data analyzed by the system, including information on efficacy, side effects, and risks.

[1071] A "terminal" is a device used by a physician, including a desktop computer, notebook, tablet, etc.

[1072] "Formatting" is the process of converting data into a specific structure or form, which improves data compatibility and processing efficiency.

[1073] "User" refers to anyone who operates this system, especially a doctor who uses this system in the medical field.

[1074] The "server" is the central computer in this system, which handles data transfer and processing.

[1075] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of three elements: a server, a terminal, and a user (doctor).

[1076] Server Processing

[1077] The server plays a central role in this system and performs the following processes:

[1078] Data reception

[1079] The server receives the clinical test data and medical record information sent from the terminal. After receiving the data, the server checks the consistency and completeness of the data. This check process includes checking the data structure and format. The server receives the data securely using the HTTPS protocol.

[1080] Database Reference

[1081] The server accesses the drug database to retrieve the latest drug information and statistical data. This process uses SQL queries. The drug database can be a relational database such as MySQL or PostgreSQL.

[1082] Data Classification and Feature Extraction

[1083] The server classifies the received data using a specific algorithm and extracts features. It does this using machine learning algorithms (e.g., random forests and support vector machines).

[1084] Generate medication recommendations

[1085] The server generates a list of optimal medication recommendations based on the extracted features, taking into account pre-existing conditions and the risk of side effects due to interactions with other medications.

[1086] Sending the results

[1087] The server converts the recommended medication list into JSON format and sends it to the terminal using the HTTPS protocol.

[1088] Terminal handling

[1089] The terminal is a device operated by a doctor and performs the following processes:

[1090] Data entry and submission

[1091] The user (doctor) enters the patient's laboratory test data and medical record information into the terminal, which formats and transmits this data to the server using the HTTPS protocol.

[1092] Receive a list of recommended medications

[1093] The terminal receives the recommended drug list sent from the server and converts the received data into an internal data structure.

[1094] Display and confirmation

[1095] The terminal displays the received list of recommended medications to the user (doctor). The user (doctor) checks the displayed list and, if necessary, conducts further research and consideration. The terminal also has an interface for providing detailed information.

[1096] User (doctor) processing

[1097] The user (doctor) performs the following processes through the system.

[1098] Data Entry

[1099] The user (physician) enters laboratory test data and medical record information into the terminal, either manually using an input form or by importing data from an existing electronic medical record system.

[1100] Check recommended medications

[1101] The user (doctor) checks the list of recommended medications displayed on the device and selects the appropriate medication. Detailed information on each medication can also be viewed.

[1102] Final formulation decision

[1103] The user (doctor) selects the most appropriate medication and decides on the final prescription. The information on the selected medication is recorded in the patient's chart.

[1104] Specific examples

[1105] For example, consider the case where a patient has diabetes.

[1106] Data entry and submission

[1107] The user (doctor) inputs the clinical test data (e.g., blood glucose level 180 mg / dL) of a diabetic patient and medical record information (e.g., medical history, no current medication) into the terminal. The terminal converts this data into JSON format and sends it to the server as an HTTPS POST request.

[1108] Server Processing

[1109] The server checks the received data for consistency and completeness. Next, it accesses a drug database and executes SQL queries to obtain the latest drug information. It then uses machine learning algorithms to classify the data and extract features related to diabetes. It then lists the most suitable drugs (e.g., metformin, insulin) and finalizes the list by taking into account the risk of side effects. Finally, it sends the recommended drug list in JSON format to the device.

[1110] Receive and review recommended medication lists

[1111] The device receives the list of recommended medications and displays it to the user (doctor). The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[1112] Final formulation decision

[1113] The user (doctor) decides on "metformin" as the final prescribed medication and records that information in the patient's chart.

[1114] Prompt Sentence Examples

[1115] "Please explain in natural language the process by which a doctor uses the system to determine a prescription for a diabetic patient."

[1116] As described above, the system of the present invention efficiently processes clinical test data and medical record information and makes highly accurate drug recommendations, thereby reducing the burden on doctors and providing patients with prompt and appropriate treatment.

[1117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1118] Step 1: Enter and submit data

[1119] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal. Specifically, the user records blood glucose levels, medical history, current medication status, etc. in the input form on the terminal.

[1120] The terminal formats the entered data into JSON format and sends it to the server using the HTTPS protocol.

[1121] Input: Laboratory test data and medical record information (e.g., blood glucose level, medical history)

[1122] Output: Formatted JSON data sent to the server

[1123] Step 2: Receiving data

[1124] The server receives the JSON formatted clinical test data and medical record information sent from the terminal via the HTTPS protocol.

[1125] Upon receipt, the server checks the data for consistency and completeness, specifically verifying that the data structure and format are correct.

[1126] Input: JSON data sent from the terminal

[1127] Output: Verified laboratory data and medical record information

[1128] Step 3: Database Reference

[1129] The server accesses the drug database and executes SQL queries to retrieve the latest drug information.

[1130] The acquired information includes drug efficacy, side effects, and drug interaction information.

[1131] Input: Validated data stored on the server

[1132] Output: Drug information retrieved from the drug database

[1133] Step 4: Data classification and feature extraction

[1134] The server uses specific machine learning algorithms (e.g., random forests or support vector machines) to classify the data and extract features.

[1135] This allows for the extraction of important health conditions such as diabetes and hyperglycemia.

[1136] Input: Validated data and drug database information

[1137] Output: Extracted features (e.g., diabetes, hyperglycemia)

[1138] Step 5: Generate drug recommendations

[1139] The server generates a list of recommended optimal medications based on the extracted features, and a recommendation engine ranks the medications based on each feature, taking into account the risk of side effects.

[1140] A list of recommended medications is completed, including information on the efficacy, side effects, and risks of each recommended medication.

[1141] Input: Extracted features

[1142] Output: Recommended medication list

[1143] Step 6: Sending the results

[1144] The server converts the generated list of recommended medications into JSON format and sends it to the terminal using the HTTPS protocol.

[1145] Input: Recommended medication list

[1146] Output: JSON data sent to the terminal

[1147] Step 7: Receive a list of recommended medications

[1148] The terminal receives the recommended drug list in JSON format sent from the server.

[1149] Converts received data into an internal data structure.

[1150] Input: JSON data sent from the server

[1151] Output: Recommended medication list converted into internal data structure

[1152] Step 8: View and verify

[1153] The terminal displays the recommended medication list to the user (doctor) on a GUI, and the doctor can also access detailed information.

[1154] Input: Recommended medication list converted into internal data structure

[1155] Output: A list of recommended medications that is displayed to the user

[1156] Step 9: Selecting a recommended medication

[1157] The user (doctor) checks the displayed list of recommended medications and selects an appropriate medication.

[1158] View details to investigate further if needed.

[1159] Input: Recommended medication list shown to user

[1160] Output: Selected drug information

[1161] Step 10: Finalize the formula

[1162] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[1163] Record the final prescription information in the patient's chart.

[1164] Input: Selected drug information

[1165] Output: Prescription information recorded in the patient record

[1166] By using the specific processing steps described above, the system of the present invention can reduce the burden on doctors and provide prompt and appropriate treatment to patients.

[1167] (Application example 1)

[1168] 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."

[1169] In modern autonomous vehicles, it is difficult to monitor the health status of passengers in real time and take necessary measures promptly. Especially when clinical testing equipment is not installed in the vehicle, it is important to respond quickly when a passenger suddenly becomes ill. Furthermore, there is a need for a system that can recommend optimal medications based on medical history and current medication status, and can take emergency action after an abnormality is discovered. Ensuring consistency and completeness when handling large amounts of data is also a challenge.

[1170] 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.

[1171] In this invention, the server includes means for receiving clinical test data and medical record information, means for acquiring drug information from a drug database, means for classifying data using a specific algorithm and extracting features, means for recommending optimal drugs based on the features, means for generating and transmitting a list of recommended drugs, means for collecting and analyzing biometric data of the passenger, means for constantly monitoring health data and detecting abnormalities, and means for automatically guiding the passenger to the nearest medical institution in an emergency. This makes it possible to monitor the passenger's biometric data in real time, quickly recommend optimal drugs, and navigate to an appropriate medical institution in an emergency.

[1172] "Laboratory data" refers to numerical information obtained from tests performed by medical institutions to assess a patient's health status.

[1173] "Medical record information" is data that includes medical records such as a patient's medical history and prescription history.

[1174] A "drug database" is a digital database that stores information about various drugs.

[1175] An "algorithm" is a set of rules and procedures for processing data and performing classification and feature extraction.

[1176] "Drug recommendation" is the process of selecting the most appropriate medication based on a patient's specific symptoms and clinical test data.

[1177] A "recommended drug list" is a list of drugs suitable for a patient generated by an AI model or algorithm.

[1178] "Passenger" refers to a person riding in an autonomous vehicle.

[1179] "Biometric data" is digital information obtained from the human body, such as heart rate, blood pressure, and blood sugar levels.

[1180] "Anomaly detection" is the process of detecting biometric data that deviates from the normal range.

[1181] "Emergency Navigation" is a function that automatically guides passengers to the nearest medical institution if an abnormality in their health condition is detected.

[1182] The present invention is a system that monitors the health status of passengers in autonomous vehicles in real time and recommends appropriate medications when necessary. This system operates based on three main components: a server, a terminal, and a user (vehicle passenger).

[1183] Server Processing

[1184] The server plays a central role in the entire system and performs the following processes:

[1185] Data receipt and confirmation:

[1186] The server receives the lab test data and medical record information sent from the device and checks its consistency and completeness. This data includes heart rate, blood pressure, blood glucose level, etc. The server then verifies the received data with an integrity check algorithm.

[1187] Database Reference:

[1188] The server accesses the drug database to obtain the latest drug information, allowing the information on drugs suitable for each patient to be updated as needed.

[1189] Data classification and feature extraction:

[1190] Data analysis algorithms are used to classify incoming data and extract key features, which allow for drug recommendations tailored to specific diseases and health conditions.

[1191] Generate drug recommendations:

[1192] Based on the extracted features, the system generates a list of optimal drug recommendations. It also evaluates the risk of side effects based on pre-existing conditions and drug interactions and reflects this in the recommendation list.

[1193] Sending results:

[1194] A list of recommended medications is sent to the terminal and displayed to the passenger.

[1195] Terminal handling

[1196] The terminal is a device such as a tablet or smartphone installed inside the autonomous vehicle, and performs the following processes.

[1197] Data entry and submission:

[1198] Passengers input biometric data measured using sensors such as a heart rate monitor, blood pressure monitor, and blood glucose monitor into a terminal, which then transmits this data to a server.

[1199] Receive and view recommended medication lists:

[1200] The terminal receives the list of recommended medications sent from the server and displays it to the passenger.

[1201] Anomaly detection and emergency response:

[1202] The device constantly monitors biometric data and, if it detects an abnormality, quickly directs the user to the nearest medical institution.

[1203] User (vehicle passenger) processing

[1204] The user (vehicle passenger) performs the following processes through the system.

[1205] Data Entry:

[1206] The user measures his / her own biometric data and inputs it into the terminal.

[1207] Check recommended medications:

[1208] The user checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[1209] Take necessary action:

[1210] The user then goes to the indicated medical facility in case of an emergency or takes the recommended medication.

[1211] For example, the following prompt sentence can be input into a generative AI model to recommend an appropriate medication:

[1212] Example input:

[1213] "The patient is 50 years old, has a blood pressure of 160 / 100 mmHg, and a blood glucose level of 150 mg / dL. Please recommend the appropriate medication for this patient."

[1214] This prompt may recommend, for example, an ACE inhibitor (e.g., losartan) as an antihypertensive drug or metformin as a hypoglycemic drug. In this way, the system of the present invention can efficiently monitor the passenger's health status and provide prompt and appropriate responses.

[1215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1216] Step 1:

[1217] Data collection

[1218] The device measures biometric data such as heart rate, blood pressure, and blood glucose level from passengers in the vehicle. This data is acquired using sensors such as a blood pressure monitor, heart rate sensor, and blood glucose meter. The input is biometric data obtained from various sensors, and the output is the measured biometric data.

[1219] Step 2:

[1220] Data transmission

[1221] The device sends the biometric data acquired in step 1 to the server. The protocol used for data transmission is HTTP or HTTPS. The input is the measured biometric data, and the output is the biometric data formatted to be received by the server.

[1222] Step 3:

[1223] Data Receipt and Confirmation

[1224] The server receives the biometric data received from the terminal and checks its consistency and completeness. It uses a data integrity check algorithm to detect missing or outlier values. The input is the biometric data received by the server, and the output is the biometric data that has been checked for consistency and completeness.

[1225] Step 4:

[1226] Database Reference

[1227] The server accesses the drug database to obtain the latest drug information. It then executes a database query to obtain drug information appropriate for the current condition. The input is the confirmed biometric data, and the output is the corresponding drug information.

[1228] Step 5:

[1229] Data Classification and Feature Extraction

[1230] The server uses a specific algorithm to classify the received data and extract features. This uses a data analysis algorithm. The input is the drug information and biometric data obtained from the drug database, and the output is the extracted feature data.

[1231] Step 6:

[1232] Generate medication recommendations

[1233] The server generates a list of optimal medication recommendations based on the extracted feature data. It also evaluates the risk of side effects due to chronic illnesses and drug interactions and reflects this in the list. The input is feature data and drug data, and the output is a list of recommended medications. At this time, it is also possible to create prompt sentences using a generative AI model. Example: "The patient is 50 years old, his blood pressure is 160 / 100 mmHg, and his blood sugar level is 150 mg / dL. Please recommend the appropriate medication for this patient."

[1234] Step 7:

[1235] Sending the results

[1236] The server sends the generated recommended medication list to the terminal. The input is the recommended medication list, and the output is the recommended medication list formatted to be received by the terminal.

[1237] Step 8:

[1238] Results display

[1239] The terminal displays the recommended medication list received from the server to the passenger. The display is on a tablet or smartphone. The input is the recommended medication list, and the output is a list displayed in a format that can be viewed by the passenger.

[1240] Step 9:

[1241] Anomaly detection and emergency response

[1242] The device constantly monitors vital signs and guides the user to the nearest medical facility if an abnormality is detected. It uses a GPS module and a navigation system to provide prompt guidance. The input is real-time vital signs, and the output is emergency response alerts and navigation information if an abnormality is detected.

[1243] 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.

[1244] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy, and its configuration and operation method will be described in detail. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[1245] Server Processing

[1246] The server plays a central role in the system and performs the following processes:

[1247] 1. Data Reception

[1248] The server receives the clinical test data and medical record information sent from the terminal.

[1249] Check the consistency and completeness of the data received.

[1250] 2. Database Reference

[1251] The server accesses a drug database to obtain the latest drug information and statistical data.

[1252] 3. Data Classification and Feature Extraction

[1253] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[1254] 4. Generating medication recommendations

[1255] The server generates a list of optimal drug recommendations based on the extracted features.

[1256] This list also reflects information on the risk of side effects based on pre-existing conditions and interactions with other medications.

[1257] 5. Use of Emotion Engine

[1258] The server uses an emotion engine to recognize the user's (doctor's) emotions.

[1259] The emotional data collected by the emotion engine is analyzed and reflected in the recommended medication list.

[1260] 6. Submitting the results

[1261] The server transmits the recommended medication list to the terminal.

[1262] Terminal handling

[1263] The terminal is a device operated by a doctor and performs the following processes:

[1264] 1. Data entry and submission

[1265] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[1266] The terminal formats the input data and sends it to the server.

[1267] 2. Receive a list of recommended medications

[1268] The terminal receives the recommended medication list sent from the server.

[1269] 3. Display and confirmation

[1270] The terminal displays the received recommended drug list to the user (doctor).

[1271] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[1272] User (doctor) processing

[1273] The user (doctor) performs the following processes through the system.

[1274] 1. Data Entry

[1275] The user (doctor) inputs clinical test data and medical record information into the terminal.

[1276] 2. Check recommended medications

[1277] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[1278] The final prescription is determined with reference to the emotional data provided by the emotion engine.

[1279] 3. Final formulation decision

[1280] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[1281] Specific examples

[1282] For example, consider the process when a diabetic patient visits a doctor.

[1283] 1. Data entry and submission

[1284] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[1285] The terminal transmits this data to the server.

[1286] 2. Server Processing

[1287] The server checks the consistency and integrity of the data received.

[1288] The server accesses the drug database to obtain the latest drug information.

[1289] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[1290] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[1291] The emotion engine analyzes the user's (doctor's) emotional data (e.g., fatigue, impatience) collected and reflects it in the recommended medication list.

[1292] A list of recommended medications is sent to the terminal.

[1293] 3. Receive and review the recommended medication list

[1294] The terminal receives the recommended medication list and displays it to the user (doctor).

[1295] The user (doctor) checks the list and selects "metformin," which is suitable for diabetic patients.

[1296] The prescription is decided taking into consideration feedback from the emotion engine.

[1297] 4. Final formulation decision

[1298] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[1299] In this way, the system of the present invention, which combines an emotion engine, can recommend prescription drugs with greater accuracy by taking into account the user's (doctor's) emotional data in addition to clinical test data and medical record information. This reduces the burden on doctors and enables them to provide patients with prompt and accurate treatment.

[1300] The processing flow will be explained below.

[1301] Step 1:

[1302] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[1303] Step 2:

[1304] The terminal formats the input clinical test data and medical record information and generates a data transmission request to be transmitted to the server.

[1305] Step 3:

[1306] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[1307] Step 4:

[1308] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[1309] Step 5:

[1310] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[1311] Step 6:

[1312] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[1313] Step 7:

[1314] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[1315] Step 8:

[1316] The server uses an emotion engine to recognize the user's (doctor's) emotions, and collects voice and facial expression data when the user operates the device.

[1317] Step 9:

[1318] The emotion engine analyzes the collected emotion data (e.g., stress, fatigue, impatience) to determine the user's current emotional state.

[1319] Step 10:

[1320] The server takes into account the emotional data recognized by the emotion engine and applies emotion-based adjustments to the recommended medication list.

[1321] Step 11:

[1322] The server transmits the adjusted recommended medication list to the terminal.

[1323] Step 12:

[1324] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[1325] Step 13:

[1326] The user (doctor) checks the adjusted list of recommended medications displayed on the terminal and selects the appropriate medication for the patient.

[1327] Step 14:

[1328] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[1329] Example 2

[1330] 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."

[1331] Conventional drug recommendation systems did not take into account the emotional state of the doctor when recommending drugs using clinical test data and medical record information. As a result, the doctor's judgment could be affected by fatigue or stress, and the optimal drug could not be prescribed. Furthermore, recommendations were made without verifying the consistency and completeness of the data, which created a risk of selecting the wrong drug. The present invention aims to solve these problems.

[1332] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for checking the consistency and completeness of the received data, a means for acquiring drug information from a drug database, a means for classifying data using a specific algorithm and extracting features, a means for recommending optimal drugs based on the extracted features, a means for generating and transmitting a recommended drug list, and a means for recognizing the user's emotions, analyzing the emotion data, and reflecting the analysis results in the recommendation list. This enables highly accurate drug recommendations that take the doctor's emotional state into consideration.

[1333] "Clinical test data" refers to information resulting from analyses of samples such as blood, urine, and tissue of patients conducted at medical institutions such as hospitals and clinics.

[1334] "Medical record information" refers to a set of information that a doctor needs when treating a patient, such as the patient's medical history, current symptoms, and prescribed medications.

[1335] "Consistency" means that data is consistent in context and maintains logical consistency.

[1336] "Completeness" means that all data is included without any missing or incorrect information.

[1337] A "pharmaceutical database" is a database system that systematically collects and organizes information on various pharmaceuticals and stores it in a searchable and accessible format.

[1338] An "algorithm" is a procedure or computational sequence designed to solve a particular problem.

[1339] "Feature extraction" is the process of identifying and extracting important information and patterns from data.

[1340] A "recommendation" is a presentation of an option that is considered optimal based on specific conditions and information.

[1341] "Emotion recognition" is the process of detecting and evaluating a user's emotional state using sensors and analytical techniques.

[1342] "Emotion data" refers to observed and analyzed data such as numerical values ​​and categorical information related to the user's emotional state.

[1343] This paper describes in detail the configuration and operation of a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[1344] The server plays a central role in the system and provides multiple functions. First, the server receives clinical test data and medical record information sent from the terminal using the HTTPS protocol. The received data is checked for consistency and completeness. If the data is inconsistent or missing, the server detects this and performs appropriate error handling.

[1345] The server then accesses the drug database to retrieve the latest drug information and statistical data. This process is performed using a database management system, for example, MongoDB or MySQL. The retrieved data is cached internally on the server for efficient access.

[1346] The server then uses specific algorithms, such as Python's Scikit-learn library, to classify and extract features from the received lab test data and medical records. This feature extraction process involves using, for example, decision tree algorithms to classify the data based on the patient's medical history and current clinical data.

[1347] Based on the results of feature extraction, the server recommends the most appropriate medication. This recommendation takes into account side effect risk information and includes a detailed risk assessment, including pre-existing conditions and interactions with other medications. Before the recommended medication list is finally sent to the device, an emotion engine analyzes the collected user (doctor) emotion data and reflects it in the recommendation list. This emotion engine is implemented, for example, using the Affectiva API.

[1348] The terminal functions as a device operated by the user (doctor), and inputs and checks data through a GUI (graphical user interface). The user (doctor) inputs the patient's clinical test data and medical record information into the terminal and sends this to the server. When the terminal receives a list of recommended medications from the server, it displays this list on the GUI. The user (doctor) checks the displayed list and, if necessary, conducts further research or consideration.

[1349] As a concrete example, consider a diabetic patient undergoing a medical examination. The user (doctor) enters clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into a terminal and sends them to the server. The server receives this data and checks its consistency and completeness. The server then retrieves the latest drug information from a pharmaceutical database and classifies the data and extracts features using a specific algorithm. It then generates a list of recommended optimal medications, such as "metformin" and "insulin," and analyzes the user's (doctor's) emotional data (e.g., fatigue), using an emotion engine to reflect this in the recommendation list. This list of recommended medications is sent to the terminal and reviewed by the user (doctor). The user (doctor) then decides on "metformin" as the final prescription medication and records it in the patient's medical record.

[1350] As an example of a prompt, give the generative AI model the following input:

[1351] "Please recommend an appropriate medication based on the clinical data and medical record information of a diabetic patient (blood glucose level 180 mg / dL, no medical history). Also, please display the following recommended medication assuming it is used by a doctor who is feeling fatigued."

[1352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1353] Step 1:

[1354] The terminal collects the patient's clinical test data and medical record information entered by the user (doctor) through an input device (e.g., keyboard or tablet). The input data is information such as blood glucose levels and medical history. This is converted into JSON format and sent to the server using the HTTPS protocol. The input is the clinical test data and medical record information entered by the user (doctor), and the output is JSON format data sent to the server.

[1355] Step 2:

[1356] The server receives clinical test data and medical record information in JSON format from the terminal. The received data is checked for consistency and completeness within the system. Specifically, it checks whether each field of the data has been entered properly and whether there are any inconsistencies. The input is the JSON data received from the terminal, and the output is the checked data.

[1357] Step 3:

[1358] The server uses the validated data to issue a search query to the drug database. For example, it uses an SQL query to retrieve the latest drug information from the database. This process uses a database management system such as MongoDB or MySQL. Specifically, it establishes a database connection and executes the appropriate query. The input is the validated data, and the output is the retrieved drug information.

[1359] Step 4:

[1360] The server uses a specific algorithm to classify data and extract features based on the acquired drug information, clinical test data, and medical record information. For example, it applies a decision tree algorithm using Python's Scikit-learn library. Specifically, it performs analysis based on the patient's medical history and test results. The input is the acquired drug information and confirmed data, and the output is classified feature data.

[1361] Step 5:

[1362] The server recommends the most appropriate medication based on the extracted feature data, taking into account the risk of side effects and drug interactions. The recommendation list is generated based on internal rules. The input is the classified feature data, and the output is a list of recommended medications.

[1363] Step 6:

[1364] The server uses an emotion engine based on the generated recommended drug list to analyze the user's (doctor's) emotional data. This process uses, for example, the Affectiva API. Specifically, it acquires the user's emotional data and reflects it in the recommendation list. The input is the recommended drug list and emotional data, and the output is a recommended drug list that reflects the emotional data.

[1365] Step 7:

[1366] The server sends the final recommended drug list to the terminal using the HTTPS protocol. Specifically, it formats the list and transfers it to the terminal. The input is the recommendation list that reflects the emotion data, and the output is the recommendation list sent to the terminal.

[1367] Step 8:

[1368] The terminal displays the recommended drug list received from the server on a GUI. The user (doctor) checks this list and selects the most appropriate drug based on the options presented. Specifically, the user selects an item on the list and operates the UI to check detailed information. The input is the recommended list received from the server, and the output is the drug selected by the user.

[1369] Step 9:

[1370] The user (doctor) decides on the selected medication as the final prescription and records it in the patient's chart. This adds the prescription information to the electronic medical record system, making it available for future reference. The specific operation involves inputting and saving the prescription information. The input is the medication selected by the user, and the output is the prescription information recorded in the patient's chart.

[1371] (Application example 2)

[1372] 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."

[1373] In modern medical settings, doctors are required to write prescriptions efficiently and with high accuracy. However, they need to process a large amount of information in a short amount of time, and their own emotions and fatigue can sometimes affect their judgment. Furthermore, selecting medications requires assessing the risk of pre-existing conditions and drug interactions, and it is difficult to perform these tasks consistently in a single system.

[1374] Furthermore, efficient information processing and display is required when pharmacists select the most appropriate medication based on conversations with patients in physical stores such as pharmacies. To address these issues, a system is needed that processes information holistically and efficiently, reducing the burden on doctors and pharmacists.

[1375] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, and a means for displaying the list of recommended drugs on a wearable display device. This enables doctors and pharmacists to select drugs efficiently and with high accuracy and provide patients with prompt and appropriate treatment.

[1376] "Clinical test data" refers to medical data obtained as a result of a patient's blood test, urine test, diagnostic imaging, etc.

[1377] "Medical record information" refers to medical records necessary for medical treatment, such as a patient's medical history, medical history, medication information, and allergy information.

[1378] A "drug database" is a database that contains information about drug ingredients, effects, side effects, and interactions with other drugs.

[1379] A "specific algorithm" is a mathematical or statistical procedure used to classify data or extract features.

[1380] A "feature extraction method" is a technique or method for extracting important patterns or information from data.

[1381] The "medication recommendation method" is a process for selecting the most suitable medication for a patient based on the extracted features.

[1382] A "recommended drug list" is a list of drugs selected based on specific conditions or characteristics.

[1383] A "wearable display device" is a display device worn by doctors and pharmacists, such as glasses or a head-mounted display.

[1384] An "emotion engine" is a technology or software that recognizes and analyzes a user's emotional state and reflects it in the system's recommendations.

[1385] This invention is a system that efficiently processes clinical test data and medical record information, allowing pharmacists to select prescription drugs quickly and accurately in physical stores. The system of this invention is composed of a server, a terminal, a user (pharmacist), an emotion engine, and a wearable display device.

[1386] Server Processing

[1387] The server plays a central role in the system and performs the following processes:

[1388] 1. The server receives the clinical test data and medical record information sent from the terminal.

[1389] 2. The server checks the received data for consistency and integrity.

[1390] 3. The server accesses the drug database and obtains the latest drug information.

[1391] 4. The server uses specific algorithms to classify and extract features from the received clinical test data and medical record information.

[1392] 5. The server generates a list of optimal drug recommendations based on the extracted features.

[1393] 6. The server uses an emotion engine to recognize the user's (pharmacist's) emotional data and reflects it in the recommended medication list.

[1394] 7. The server sends the generated recommended medication list to the terminal.

[1395] Terminal handling

[1396] The terminal is a device operated by a pharmacist and performs the following processes:

[1397] 1. The terminal receives the patient's clinical test data and medical record information from the pharmacist via the wearable display device.

[1398] 2. The terminal formats the input data and sends it to the server.

[1399] 3. The terminal receives the recommended medication list sent from the server.

[1400] 4. The terminal displays the received list of recommended medications to the pharmacist via the wearable display device.

[1401] User (pharmacist) processing

[1402] The user (pharmacist) performs the following processes through the system.

[1403] 1. The user (pharmacist) uses the wearable display device to input the patient's clinical test data and medical record information into the terminal.

[1404] 2. The user (pharmacist) checks the list of recommended medications displayed on the terminal and selects the appropriate medication.

[1405] 3. The user (pharmacist) decides on the final prescription, taking into account the emotional data provided by the emotion engine.

[1406] 4. The user (pharmacist) prescribes the selected medication to the patient and records it in the patient's medical record.

[1407] Specific examples

[1408] For example, consider the case where a diabetic patient visits a drugstore for a consultation.

[1409] 1. The user (pharmacist) uses the wearable display device to input the diabetic patient's clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[1410] 2. The device sends this data to the server.

[1411] 3. The server checks the consistency and completeness of the received data, then classifies the data and extracts features using specific algorithms.

[1412] 4. The server generates a list of recommendations for optimal medications, such as metformin and insulin, based on the extracted features.

[1413] 5. Analyze the user's (pharmacist's) emotional data (e.g., fatigue, impatience) collected by the emotion engine and reflect it in the recommended medication list.

[1414] 6. The server sends the final recommended medication list to the terminal.

[1415] 7. The terminal receives the list of recommended medications and displays it to the user (pharmacist) via the wearable display device.

[1416] 8. The user (pharmacist) checks the list of recommended medications and selects "metformin," which is suitable for the diabetic patient. The user decides on the prescription, taking into consideration feedback from the emotion engine.

[1417] 9. The user (pharmacist) determines "metformin" as the final prescription and records it in the patient's chart.

[1418] Prompt Sentence Examples

[1419] "A user inputs the test results of a diabetic patient into the smart glasses. The emotion engine detects the user's emotions based on the results and sends them to the server."

[1420] In this way, the system of the present invention comprehensively utilizes clinical test data, medical record information, and emotional data to achieve more accurate prescription drug recommendations.

[1421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1422] Step 1:

[1423] The user uses the wearable display device to input the patient's clinical test data and medical record information into the terminal by voice. The terminal formats the input clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) and sends them to the server.

[1424] Step 2:

[1425] The server receives the clinical test data and medical record information sent from the terminal. The server checks the consistency and completeness of the received data, specifically checking the data format and missing values, and generates warning messages if necessary.

[1426] Step 3:

[1427] The server compares the received clinical test data and medical record information with a drug database to obtain relevant and up-to-date drug information. In this process, it extracts the effects, side effects, and interactions of the corresponding drugs from the database.

[1428] Step 4:

[1429] The server uses a specific algorithm to classify the received data and extract features. For example, if a diabetic patient's blood sugar level exceeds the normal range, the server classifies the data as "hyperglycemia." The extracted features, such as diabetes and hyperglycemia, are listed.

[1430] Step 5:

[1431] The server generates a list of optimal medication recommendations based on the extracted features. For example, based on the features of hyperglycemia, drugs such as "metformin" and "insulin" are added to the recommendation list. Side effect risk information based on chronic illnesses and interactions with other drugs is also reflected.

[1432] Step 6:

[1433] The server recognizes the user's (pharmacist's) emotional data using an emotion engine. The emotion engine analyzes data obtained from sensors installed in the wearable display device and detects the user's emotional state (e.g., fatigue, impatience).

[1434] Step 7:

[1435] The server analyzes the emotion data collected by the emotion engine and reflects it in the recommended medication list. For example, for a user who is fatigued, medications that are easy to select are displayed preferentially on the list.

[1436] Step 8:

[1437] The server transmits the generated recommended medication list to the terminal. For example, data including detailed information on "metformin" and "insulin" is transmitted to the terminal as the recommended medication list.

[1438] Step 9:

[1439] The terminal displays the list of recommended medications sent from the server on the wearable display device. The user (pharmacist) checks the displayed list of medications and selects the appropriate medication. For example, specific information about "metformin" (efficacy, side effects, drug interactions) is displayed.

[1440] Step 10:

[1441] The user (pharmacist) decides on the final prescription while referring to the recommended medication list. The selected medication (e.g., metformin) is recorded in the patient's medical record and prescribed to the patient. In some cases, feedback from the emotion engine is also used to help with the prescription decision.

[1442] In this way, the system comprehensively utilizes clinical test data, medical record information, and emotional data to achieve efficient and highly accurate drug selection.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] [Fourth embodiment]

[1447] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1448] 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.

[1449] 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).

[1450] 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.

[1451] 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.

[1452] 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).

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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."

[1460] The present invention is a system that enables doctors to prepare prescriptions efficiently and with high accuracy, and an embodiment of the system will be described in detail below. This system is composed of a server, a terminal, and a user (doctor).

[1461] Server Processing

[1462] The server plays a central role in the system and performs the following processes:

[1463] 1. Data Reception

[1464] The server receives the clinical test data and medical record information sent from the terminal.

[1465] Check the consistency and completeness of the data received.

[1466] 2. Database Reference

[1467] The server accesses a drug database to obtain the latest drug information and statistical data.

[1468] 3. Data Classification and Feature Extraction

[1469] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[1470] 4. Generating medication recommendations

[1471] The server generates a list of optimal drug recommendations based on the extracted features.

[1472] This list also reflects the risk of side effects based on pre-existing conditions and interactions with other medications.

[1473] 5. Sending the results

[1474] The server transmits the recommended medication list to the terminal.

[1475] Terminal handling

[1476] The terminal is a device operated by a doctor and performs the following processes:

[1477] 1. Data entry and submission

[1478] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[1479] The terminal formats the input data and sends it to the server.

[1480] 2. Receive a list of recommended medications

[1481] The terminal receives the recommended medication list sent from the server.

[1482] 3. Display and confirmation

[1483] The terminal displays the received recommended drug list to the user (doctor).

[1484] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[1485] User (doctor) processing

[1486] The user (doctor) performs the following processes through the system.

[1487] 1. Data Entry

[1488] The user (doctor) inputs clinical test data and medical record information into the terminal.

[1489] 2. Check recommended medications

[1490] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[1491] 3. Final formulation decision

[1492] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[1493] Record the medication selected and the reason for it in the patient's chart.

[1494] Specific examples

[1495] For example, consider the case where a patient has diabetes.

[1496] 1. Data entry and submission

[1497] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[1498] The terminal transmits this data to the server.

[1499] 2. Server Processing

[1500] The server checks the received data for consistency and completeness.

[1501] The server accesses the drug database to obtain the latest drug information.

[1502] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[1503] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[1504] The list takes into account the risk of side effects and sends a list of recommended medications to the terminal.

[1505] 3. Receive and review the recommended medication list

[1506] The terminal receives the recommended medication list and displays it to the user (doctor).

[1507] The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[1508] 4. Final formulation decision

[1509] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[1510] In this way, the system of the present invention efficiently processes clinical test data and medical record information and recommends optimal medications, thereby reducing the burden on doctors and helping to provide prompt and appropriate treatment to patients.

[1511] The processing flow will be explained below.

[1512] Step 1:

[1513] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[1514] Step 2:

[1515] The terminal formats the entered clinical test data and medical record information and generates a data transmission request to be sent to the server.

[1516] Step 3:

[1517] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[1518] Step 4:

[1519] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[1520] Step 5:

[1521] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[1522] Step 6:

[1523] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[1524] Step 7:

[1525] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[1526] Step 8:

[1527] The server transmits the generated recommended drug list to the terminal.

[1528] Step 9:

[1529] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[1530] Step 10:

[1531] The user (doctor) checks the list of recommended medications displayed on the terminal and selects the medication appropriate for the patient.

[1532] Step 11:

[1533] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[1534] Example 1

[1535] 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."

[1536] Conventional medical systems have issues with the accuracy and speed with which they can efficiently process clinical test data and medical record information and recommend optimal medications to doctors. Furthermore, they lack a mechanism for effectively assessing the risk of side effects due to chronic illnesses or interactions with other medications, placing a heavy burden on doctors and making it difficult to provide appropriate treatment to patients promptly. To address these issues, the present invention aims to provide a more efficient and accurate prescription preparation system.

[1537] 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.

[1538] In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, a means for formatting data entered by a user on a terminal and transmitting the data to the server, and a means for displaying the list of recommended drugs transmitted from the server. This enables rapid and accurate drug recommendations based on the clinical test data and medical record information, and allows appropriate evaluation of the risk of side effects due to chronic illnesses and drug interactions. It also reduces the burden on doctors and enables prompt and accurate treatment for patients.

[1539] "Laboratory data" refers to the results of various tests performed to assess a patient's health, including blood tests, urine tests, and diagnostic imaging.

[1540] "Medical record information" refers to the comprehensive medical record of a patient, including medical records, medical history, current medication status, allergy information, etc.

[1541] The "drug database" is a database that collects information about various drugs, including drug efficacy, side effects, drug interactions, and the latest clinical research results.

[1542] A "specific algorithm" refers to a computational method that analyzes input data and extracts certain patterns or characteristics, using machine learning and statistical analysis techniques.

[1543] "Feature extraction" is the process of finding important information and patterns in input data, which allows us to understand the essence of the data.

[1544] "Recommending" means showing the best option based on specific conditions and data. This system plays a role in suggesting the best medication to doctors.

[1545] The "recommended drug list" is a list of drugs selected based on data analyzed by the system, including information on efficacy, side effects, and risks.

[1546] A "terminal" is a device used by a physician, including a desktop computer, notebook, tablet, etc.

[1547] "Formatting" is the process of converting data into a specific structure or form, which improves data compatibility and processing efficiency.

[1548] "User" refers to anyone who operates this system, especially a doctor who uses this system in the medical field.

[1549] The "server" is the central computer in this system, which handles data transfer and processing.

[1550] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of three elements: a server, a terminal, and a user (doctor).

[1551] Server Processing

[1552] The server plays a central role in this system and performs the following processes:

[1553] Data reception

[1554] The server receives the clinical test data and medical record information sent from the terminal. After receiving the data, the server checks the consistency and completeness of the data. This check process includes checking the data structure and format. The server receives the data securely using the HTTPS protocol.

[1555] Database Reference

[1556] The server accesses the drug database to retrieve the latest drug information and statistical data. This process uses SQL queries. The drug database can be a relational database such as MySQL or PostgreSQL.

[1557] Data Classification and Feature Extraction

[1558] The server classifies the received data using a specific algorithm and extracts features. It does this using machine learning algorithms (e.g., random forests and support vector machines).

[1559] Generate medication recommendations

[1560] The server generates a list of optimal medication recommendations based on the extracted features, taking into account pre-existing conditions and the risk of side effects due to interactions with other medications.

[1561] Sending the results

[1562] The server converts the recommended medication list into JSON format and sends it to the terminal using the HTTPS protocol.

[1563] Terminal handling

[1564] The terminal is a device operated by a doctor and performs the following processes:

[1565] Data entry and submission

[1566] The user (doctor) enters the patient's laboratory test data and medical record information into the terminal, which formats and transmits this data to the server using the HTTPS protocol.

[1567] Receive a list of recommended medications

[1568] The terminal receives the recommended drug list sent from the server and converts the received data into an internal data structure.

[1569] Display and confirmation

[1570] The terminal displays the received list of recommended medications to the user (doctor). The user (doctor) checks the displayed list and, if necessary, conducts further research and consideration. The terminal also has an interface for providing detailed information.

[1571] User (doctor) processing

[1572] The user (doctor) performs the following processes through the system.

[1573] Data Entry

[1574] The user (physician) enters laboratory test data and medical record information into the terminal, either manually using an input form or by importing data from an existing electronic medical record system.

[1575] Check recommended medications

[1576] The user (doctor) checks the list of recommended medications displayed on the device and selects the appropriate medication. Detailed information on each medication can also be viewed.

[1577] Final formulation decision

[1578] The user (doctor) selects the most appropriate medication and decides on the final prescription. The information on the selected medication is recorded in the patient's chart.

[1579] Specific examples

[1580] For example, consider the case where a patient has diabetes.

[1581] Data entry and submission

[1582] The user (doctor) inputs the clinical test data (e.g., blood glucose level 180 mg / dL) of a diabetic patient and medical record information (e.g., medical history, no current medication) into the terminal. The terminal converts this data into JSON format and sends it to the server as an HTTPS POST request.

[1583] Server Processing

[1584] The server checks the received data for consistency and completeness. Next, it accesses a drug database and executes SQL queries to obtain the latest drug information. It then uses machine learning algorithms to classify the data and extract features related to diabetes. It then lists the most suitable drugs (e.g., metformin, insulin) and finalizes the list by taking into account the risk of side effects. Finally, it sends the recommended drug list in JSON format to the device.

[1585] Receive and review recommended medication lists

[1586] The device receives the list of recommended medications and displays it to the user (doctor). The user (doctor) checks the list and selects "metformin," which is suitable for diabetes.

[1587] Final formulation decision

[1588] The user (doctor) decides on "metformin" as the final prescribed medication and records that information in the patient's chart.

[1589] Prompt Sentence Examples

[1590] "Please explain in natural language the process by which a doctor uses the system to determine a prescription for a diabetic patient."

[1591] As described above, the system of the present invention efficiently processes clinical test data and medical record information and makes highly accurate drug recommendations, thereby reducing the burden on doctors and providing patients with prompt and appropriate treatment.

[1592] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1593] Step 1: Enter and submit data

[1594] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal. Specifically, the user records blood glucose levels, medical history, current medication status, etc. in the input form on the terminal.

[1595] The terminal formats the entered data into JSON format and sends it to the server using the HTTPS protocol.

[1596] Input: Laboratory test data and medical record information (e.g., blood glucose level, medical history)

[1597] Output: Formatted JSON data sent to the server

[1598] Step 2: Receiving data

[1599] The server receives the JSON formatted clinical test data and medical record information sent from the terminal via the HTTPS protocol.

[1600] Upon receipt, the server checks the data for consistency and completeness, specifically verifying that the data structure and format are correct.

[1601] Input: JSON data sent from the terminal

[1602] Output: Verified laboratory data and medical record information

[1603] Step 3: Database Reference

[1604] The server accesses the drug database and executes SQL queries to retrieve the latest drug information.

[1605] The acquired information includes drug efficacy, side effects, and drug interaction information.

[1606] Input: Validated data stored on the server

[1607] Output: Drug information retrieved from the drug database

[1608] Step 4: Data classification and feature extraction

[1609] The server uses specific machine learning algorithms (e.g., random forests or support vector machines) to classify the data and extract features.

[1610] This allows for the extraction of important health conditions such as diabetes and hyperglycemia.

[1611] Input: Validated data and drug database information

[1612] Output: Extracted features (e.g., diabetes, hyperglycemia)

[1613] Step 5: Generate drug recommendations

[1614] The server generates a list of recommended optimal medications based on the extracted features, and a recommendation engine ranks the medications based on each feature, taking into account the risk of side effects.

[1615] A list of recommended medications is completed, including information on the efficacy, side effects, and risks of each recommended medication.

[1616] Input: Extracted features

[1617] Output: Recommended medication list

[1618] Step 6: Sending the results

[1619] The server converts the generated list of recommended medications into JSON format and sends it to the terminal using the HTTPS protocol.

[1620] Input: Recommended medication list

[1621] Output: JSON data sent to the terminal

[1622] Step 7: Receive a list of recommended medications

[1623] The terminal receives the recommended drug list in JSON format sent from the server.

[1624] Converts received data into an internal data structure.

[1625] Input: JSON data sent from the server

[1626] Output: Recommended medication list converted into internal data structure

[1627] Step 8: View and verify

[1628] The terminal displays the recommended medication list to the user (doctor) on a GUI, and the doctor can also access detailed information.

[1629] Input: Recommended medication list converted into internal data structure

[1630] Output: A list of recommended medications that is displayed to the user

[1631] Step 9: Selecting a recommended medication

[1632] The user (doctor) checks the displayed list of recommended medications and selects an appropriate medication.

[1633] View details to investigate further if needed.

[1634] Input: Recommended medication list shown to user

[1635] Output: Selected drug information

[1636] Step 10: Finalize the formula

[1637] The user (doctor) selects the most appropriate medication and decides on the final prescription.

[1638] Record the final prescription information in the patient's chart.

[1639] Input: Selected drug information

[1640] Output: Prescription information recorded in the patient record

[1641] By using the specific processing steps described above, the system of the present invention can reduce the burden on doctors and provide prompt and appropriate treatment to patients.

[1642] (Application example 1)

[1643] 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."

[1644] In modern autonomous vehicles, it is difficult to monitor the health status of passengers in real time and take necessary measures promptly. Especially when clinical testing equipment is not installed in the vehicle, it is important to respond quickly when a passenger suddenly becomes ill. Furthermore, there is a need for a system that can recommend optimal medications based on medical history and current medication status, and can take emergency action after an abnormality is discovered. Ensuring consistency and completeness when handling large amounts of data is also a challenge.

[1645] 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.

[1646] In this invention, the server includes means for receiving clinical test data and medical record information, means for acquiring drug information from a drug database, means for classifying data using a specific algorithm and extracting features, means for recommending optimal drugs based on the features, means for generating and transmitting a list of recommended drugs, means for collecting and analyzing biometric data of the passenger, means for constantly monitoring health data and detecting abnormalities, and means for automatically guiding the passenger to the nearest medical institution in an emergency. This makes it possible to monitor the passenger's biometric data in real time, quickly recommend optimal drugs, and navigate to an appropriate medical institution in an emergency.

[1647] "Laboratory data" refers to numerical information obtained from tests performed by medical institutions to assess a patient's health status.

[1648] "Medical record information" is data that includes medical records such as a patient's medical history and prescription history.

[1649] A "drug database" is a digital database that stores information about various drugs.

[1650] An "algorithm" is a set of rules and procedures for processing data and performing classification and feature extraction.

[1651] "Drug recommendation" is the process of selecting the most appropriate medication based on a patient's specific symptoms and clinical test data.

[1652] A "recommended drug list" is a list of drugs suitable for a patient generated by an AI model or algorithm.

[1653] "Passenger" refers to a person riding in an autonomous vehicle.

[1654] "Biometric data" is digital information obtained from the human body, such as heart rate, blood pressure, and blood sugar levels.

[1655] "Anomaly detection" is the process of detecting biometric data that deviates from the normal range.

[1656] "Emergency Navigation" is a function that automatically guides passengers to the nearest medical institution if an abnormality in their health condition is detected.

[1657] The present invention is a system that monitors the health status of passengers in autonomous vehicles in real time and recommends appropriate medications when necessary. This system operates based on three main components: a server, a terminal, and a user (vehicle passenger).

[1658] Server Processing

[1659] The server plays a central role in the entire system and performs the following processes:

[1660] Data receipt and confirmation:

[1661] The server receives the lab test data and medical record information sent from the device and checks its consistency and completeness. This data includes heart rate, blood pressure, blood glucose level, etc. The server then verifies the received data with an integrity check algorithm.

[1662] Database Reference:

[1663] The server accesses the drug database to obtain the latest drug information, allowing the information on drugs suitable for each patient to be updated as needed.

[1664] Data classification and feature extraction:

[1665] Data analysis algorithms are used to classify incoming data and extract key features, which allow for drug recommendations tailored to specific diseases and health conditions.

[1666] Generate drug recommendations:

[1667] Based on the extracted features, the system generates a list of optimal drug recommendations. It also evaluates the risk of side effects based on pre-existing conditions and drug interactions and reflects this in the recommendation list.

[1668] Sending results:

[1669] A list of recommended medications is sent to the terminal and displayed to the passenger.

[1670] Terminal handling

[1671] The terminal is a device such as a tablet or smartphone installed inside the autonomous vehicle, and performs the following processes.

[1672] Data entry and submission:

[1673] Passengers input biometric data measured using sensors such as a heart rate monitor, blood pressure monitor, and blood glucose monitor into a terminal, which then transmits this data to a server.

[1674] Receive and view recommended medication lists:

[1675] The terminal receives the list of recommended medications sent from the server and displays it to the passenger.

[1676] Anomaly detection and emergency response:

[1677] The device constantly monitors biometric data and, if it detects an abnormality, quickly directs the user to the nearest medical institution.

[1678] User (vehicle passenger) processing

[1679] The user (vehicle passenger) performs the following processes through the system.

[1680] Data Entry:

[1681] The user measures his / her own biometric data and inputs it into the terminal.

[1682] Check recommended medications:

[1683] The user checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[1684] Take necessary action:

[1685] The user then goes to the indicated medical facility in case of an emergency or takes the recommended medication.

[1686] For example, the following prompt sentence can be input into a generative AI model to recommend an appropriate medication:

[1687] Example input:

[1688] "The patient is 50 years old, has a blood pressure of 160 / 100 mmHg, and a blood glucose level of 150 mg / dL. Please recommend the appropriate medication for this patient."

[1689] This prompt may recommend, for example, an ACE inhibitor (e.g., losartan) as an antihypertensive drug or metformin as a hypoglycemic drug. In this way, the system of the present invention can efficiently monitor the passenger's health status and provide prompt and appropriate responses.

[1690] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1691] Step 1:

[1692] Data collection

[1693] The device measures biometric data such as heart rate, blood pressure, and blood glucose level from passengers in the vehicle. This data is acquired using sensors such as a blood pressure monitor, heart rate sensor, and blood glucose meter. The input is biometric data obtained from various sensors, and the output is the measured biometric data.

[1694] Step 2:

[1695] Data transmission

[1696] The device sends the biometric data acquired in step 1 to the server. The protocol used for data transmission is HTTP or HTTPS. The input is the measured biometric data, and the output is the biometric data formatted to be received by the server.

[1697] Step 3:

[1698] Data Receipt and Confirmation

[1699] The server receives the biometric data received from the terminal and checks its consistency and completeness. It uses a data integrity check algorithm to detect missing or outlier values. The input is the biometric data received by the server, and the output is the biometric data that has been checked for consistency and completeness.

[1700] Step 4:

[1701] Database Reference

[1702] The server accesses the drug database to obtain the latest drug information. It then executes a database query to obtain drug information appropriate for the current condition. The input is the confirmed biometric data, and the output is the corresponding drug information.

[1703] Step 5:

[1704] Data Classification and Feature Extraction

[1705] The server uses a specific algorithm to classify the received data and extract features. This uses a data analysis algorithm. The input is the drug information and biometric data obtained from the drug database, and the output is the extracted feature data.

[1706] Step 6:

[1707] Generate medication recommendations

[1708] The server generates a list of optimal medication recommendations based on the extracted feature data. It also evaluates the risk of side effects due to chronic illnesses and drug interactions and reflects this in the list. The input is feature data and drug data, and the output is a list of recommended medications. At this time, it is also possible to create prompt sentences using a generative AI model. Example: "The patient is 50 years old, his blood pressure is 160 / 100 mmHg, and his blood sugar level is 150 mg / dL. Please recommend the appropriate medication for this patient."

[1709] Step 7:

[1710] Sending the results

[1711] The server sends the generated recommended medication list to the terminal. The input is the recommended medication list, and the output is the recommended medication list formatted to be received by the terminal.

[1712] Step 8:

[1713] Results display

[1714] The terminal displays the recommended medication list received from the server to the passenger. The display is on a tablet or smartphone. The input is the recommended medication list, and the output is a list displayed in a format that can be viewed by the passenger.

[1715] Step 9:

[1716] Anomaly detection and emergency response

[1717] The device constantly monitors vital signs and guides the user to the nearest medical facility if an abnormality is detected. It uses a GPS module and a navigation system to provide prompt guidance. The input is real-time vital signs, and the output is emergency response alerts and navigation information if an abnormality is detected.

[1718] 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.

[1719] This invention is a system that enables doctors to write prescriptions efficiently and with high accuracy, and its configuration and operation method will be described in detail. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[1720] Server Processing

[1721] The server plays a central role in the system and performs the following processes:

[1722] 1. Data Reception

[1723] The server receives the clinical test data and medical record information sent from the terminal.

[1724] Check the consistency and completeness of the data received.

[1725] 2. Database Reference

[1726] The server accesses a drug database to obtain the latest drug information and statistical data.

[1727] 3. Data Classification and Feature Extraction

[1728] The server uses specific algorithms to classify and extract features from the received laboratory test data and medical record information.

[1729] 4. Generating medication recommendations

[1730] The server generates a list of optimal drug recommendations based on the extracted features.

[1731] This list also reflects information on the risk of side effects based on pre-existing conditions and interactions with other medications.

[1732] 5. Use of Emotion Engine

[1733] The server uses an emotion engine to recognize the user's (doctor's) emotions.

[1734] The emotional data collected by the emotion engine is analyzed and reflected in the recommended medication list.

[1735] 6. Submitting the results

[1736] The server transmits the recommended medication list to the terminal.

[1737] Terminal handling

[1738] The terminal is a device operated by a doctor and performs the following processes:

[1739] 1. Data entry and submission

[1740] The user (doctor) inputs the patient's clinical test data and medical record information into the terminal.

[1741] The terminal formats the input data and sends it to the server.

[1742] 2. Receive a list of recommended medications

[1743] The terminal receives the recommended medication list sent from the server.

[1744] 3. Display and confirmation

[1745] The terminal displays the received recommended drug list to the user (doctor).

[1746] The user (doctor) checks the displayed list and, if necessary, conducts further investigation and review.

[1747] User (doctor) processing

[1748] The user (doctor) performs the following processes through the system.

[1749] 1. Data Entry

[1750] The user (doctor) inputs clinical test data and medical record information into the terminal.

[1751] 2. Check recommended medications

[1752] The user (doctor) checks the list of recommended medications displayed on the terminal and selects an appropriate medication.

[1753] The final prescription is determined with reference to the emotional data provided by the emotion engine.

[1754] 3. Final formulation decision

[1755] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[1756] Specific examples

[1757] For example, consider the process when a diabetic patient visits a doctor.

[1758] 1. Data entry and submission

[1759] The user (doctor) inputs the clinical test data of a diabetic patient (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[1760] The terminal transmits this data to the server.

[1761] 2. Server Processing

[1762] The server checks the consistency and integrity of the data received.

[1763] The server accesses the drug database to obtain the latest drug information.

[1764] Specific algorithms are used to classify the received data and extract features (e.g., diabetes, hyperglycemia).

[1765] Based on the extracted features, a list is generated recommending metformin or insulin as the most appropriate medication.

[1766] The emotion engine analyzes the user's (doctor's) emotional data (e.g., fatigue, impatience) collected and reflects it in the recommended medication list.

[1767] A list of recommended medications is sent to the terminal.

[1768] 3. Receive and review the recommended medication list

[1769] The terminal receives the recommended medication list and displays it to the user (doctor).

[1770] The user (doctor) checks the list and selects "metformin," which is suitable for diabetic patients.

[1771] The prescription is decided taking into consideration feedback from the emotion engine.

[1772] 4. Final formulation decision

[1773] The user (doctor) decides on "metformin" as the final prescribed medication and records it in the patient's chart.

[1774] In this way, the system of the present invention, which combines an emotion engine, can recommend prescription drugs with greater accuracy by taking into account the user's (doctor's) emotional data in addition to clinical test data and medical record information. This reduces the burden on doctors and enables them to provide patients with prompt and accurate treatment.

[1775] The processing flow will be explained below.

[1776] Step 1:

[1777] The user (doctor) inputs the patient's clinical test data (e.g., blood glucose level, blood pressure) and medical record information (e.g., medical history, current medication status) into the terminal.

[1778] Step 2:

[1779] The terminal formats the input clinical test data and medical record information and generates a data transmission request to be transmitted to the server.

[1780] Step 3:

[1781] The server receives the data transmission request sent from the terminal and analyzes the clinical test data and medical record information.

[1782] Step 4:

[1783] The server checks the received data for consistency and completeness and accepts it as properly formatted data.

[1784] Step 5:

[1785] The server accesses the drug database and sends queries to obtain the latest drug information and statistics.

[1786] Step 6:

[1787] The server uses a specific algorithm to classify the received laboratory test data and medical record information and extract their respective features (e.g., diabetes, hyperglycemia).

[1788] Step 7:

[1789] The server then searches a drug database based on the extracted features and generates a list of recommended medications, including information on side effect risks based on pre-existing conditions and interactions with other medications.

[1790] Step 8:

[1791] The server uses an emotion engine to recognize the user's (doctor's) emotions, and collects voice and facial expression data when the user operates the device.

[1792] Step 9:

[1793] The emotion engine analyzes the collected emotion data (e.g., stress, fatigue, impatience) to determine the user's current emotional state.

[1794] Step 10:

[1795] The server takes into account the emotional data recognized by the emotion engine and applies emotion-based adjustments to the recommended medication list.

[1796] Step 11:

[1797] The server transmits the adjusted recommended medication list to the terminal.

[1798] Step 12:

[1799] The terminal analyzes the recommended drug list received from the server, formats it, and displays it to the user (doctor).

[1800] Step 13:

[1801] The user (doctor) checks the adjusted list of recommended medications displayed on the terminal and selects the appropriate medication for the patient.

[1802] Step 14:

[1803] The user (doctor) decides on the selected drug as the final prescription drug and records it in the patient's chart.

[1804] Example 2

[1805] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1806] Conventional drug recommendation systems did not take into account the emotional state of the doctor when recommending drugs using clinical test data and medical record information. As a result, the doctor's judgment could be affected by fatigue or stress, and the optimal drug could not be prescribed. Furthermore, recommendations were made without verifying the consistency and completeness of the data, which created a risk of selecting the wrong drug. The present invention aims to solve these problems.

[1807] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for checking the consistency and completeness of the received data, a means for acquiring drug information from a drug database, a means for classifying data using a specific algorithm and extracting features, a means for recommending optimal drugs based on the extracted features, a means for generating and transmitting a recommended drug list, and a means for recognizing the user's emotions, analyzing the emotion data, and reflecting the analysis results in the recommendation list. This enables highly accurate drug recommendations that take the doctor's emotional state into consideration.

[1808] "Clinical test data" refers to information resulting from analyses of samples such as blood, urine, and tissue of patients conducted at medical institutions such as hospitals and clinics.

[1809] "Medical record information" refers to a set of information that a doctor needs when treating a patient, such as the patient's medical history, current symptoms, and prescribed medications.

[1810] "Consistency" means that data is consistent in context and maintains logical consistency.

[1811] "Completeness" means that all data is included without any missing or incorrect information.

[1812] A "pharmaceutical database" is a database system that systematically collects and organizes information on various pharmaceuticals and stores it in a searchable and accessible format.

[1813] An "algorithm" is a procedure or computational sequence designed to solve a particular problem.

[1814] "Feature extraction" is the process of identifying and extracting important information and patterns from data.

[1815] A "recommendation" is a presentation of an option that is considered optimal based on specific conditions and information.

[1816] "Emotion recognition" is the process of detecting and evaluating a user's emotional state using sensors and analytical techniques.

[1817] "Emotion data" refers to observed and analyzed data such as numerical values ​​and categorical information related to the user's emotional state.

[1818] This paper describes in detail the configuration and operation of a system that enables doctors to write prescriptions efficiently and with high accuracy. This system is composed of a server, a terminal, a user (doctor), and an emotion engine.

[1819] The server plays a central role in the system and provides multiple functions. First, the server receives clinical test data and medical record information sent from the terminal using the HTTPS protocol. The received data is checked for consistency and completeness. If the data is inconsistent or missing, the server detects this and performs appropriate error handling.

[1820] The server then accesses the drug database to retrieve the latest drug information and statistical data. This process is performed using a database management system, for example, MongoDB or MySQL. The retrieved data is cached internally on the server for efficient access.

[1821] The server then uses specific algorithms, such as Python's Scikit-learn library, to classify and extract features from the received lab test data and medical records. This feature extraction process involves using, for example, decision tree algorithms to classify the data based on the patient's medical history and current clinical data.

[1822] Based on the results of feature extraction, the server recommends the most appropriate medication. This recommendation takes into account side effect risk information and includes a detailed risk assessment, including pre-existing conditions and interactions with other medications. Before the recommended medication list is finally sent to the device, an emotion engine analyzes the collected user (doctor) emotion data and reflects it in the recommendation list. This emotion engine is implemented, for example, using the Affectiva API.

[1823] The terminal functions as a device operated by the user (doctor), and inputs and checks data through a GUI (graphical user interface). The user (doctor) inputs the patient's clinical test data and medical record information into the terminal and sends this to the server. When the terminal receives a list of recommended medications from the server, it displays this list on the GUI. The user (doctor) checks the displayed list and, if necessary, conducts further research or consideration.

[1824] As a concrete example, consider a diabetic patient undergoing a medical examination. The user (doctor) enters clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into a terminal and sends them to the server. The server receives this data and checks its consistency and completeness. The server then retrieves the latest drug information from a pharmaceutical database and classifies the data and extracts features using a specific algorithm. It then generates a list of recommended optimal medications, such as "metformin" and "insulin," and analyzes the user's (doctor's) emotional data (e.g., fatigue), using an emotion engine to reflect this in the recommendation list. This list of recommended medications is sent to the terminal and reviewed by the user (doctor). The user (doctor) then decides on "metformin" as the final prescription medication and records it in the patient's medical record.

[1825] As an example of a prompt, give the generative AI model the following input:

[1826] "Please recommend an appropriate medication based on the clinical data and medical record information of a diabetic patient (blood glucose level 180 mg / dL, no medical history). Also, please display the following recommended medication assuming it is used by a doctor who is feeling fatigued."

[1827] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1828] Step 1:

[1829] The terminal collects the patient's clinical test data and medical record information entered by the user (doctor) through an input device (e.g., keyboard or tablet). The input data is information such as blood glucose levels and medical history. This is converted into JSON format and sent to the server using the HTTPS protocol. The input is the clinical test data and medical record information entered by the user (doctor), and the output is JSON format data sent to the server.

[1830] Step 2:

[1831] The server receives clinical test data and medical record information in JSON format from the terminal. The received data is checked for consistency and completeness within the system. Specifically, it checks whether each field of the data has been entered properly and whether there are any inconsistencies. The input is the JSON data received from the terminal, and the output is the checked data.

[1832] Step 3:

[1833] The server uses the validated data to issue a search query to the drug database. For example, it uses an SQL query to retrieve the latest drug information from the database. This process uses a database management system such as MongoDB or MySQL. Specifically, it establishes a database connection and executes the appropriate query. The input is the validated data, and the output is the retrieved drug information.

[1834] Step 4:

[1835] The server uses a specific algorithm to classify data and extract features based on the acquired drug information, clinical test data, and medical record information. For example, it applies a decision tree algorithm using Python's Scikit-learn library. Specifically, it performs analysis based on the patient's medical history and test results. The input is the acquired drug information and confirmed data, and the output is classified feature data.

[1836] Step 5:

[1837] The server recommends the most appropriate medication based on the extracted feature data, taking into account the risk of side effects and drug interactions. The recommendation list is generated based on internal rules. The input is the classified feature data, and the output is a list of recommended medications.

[1838] Step 6:

[1839] The server uses an emotion engine based on the generated recommended drug list to analyze the user's (doctor's) emotional data. This process uses, for example, the Affectiva API. Specifically, it acquires the user's emotional data and reflects it in the recommendation list. The input is the recommended drug list and emotional data, and the output is a recommended drug list that reflects the emotional data.

[1840] Step 7:

[1841] The server sends the final recommended drug list to the terminal using the HTTPS protocol. Specifically, it formats the list and transfers it to the terminal. The input is the recommendation list that reflects the emotion data, and the output is the recommendation list sent to the terminal.

[1842] Step 8:

[1843] The terminal displays the recommended drug list received from the server on a GUI. The user (doctor) checks this list and selects the most appropriate drug based on the options presented. Specifically, the user selects an item on the list and operates the UI to check detailed information. The input is the recommended list received from the server, and the output is the drug selected by the user.

[1844] Step 9:

[1845] The user (doctor) decides on the selected medication as the final prescription and records it in the patient's chart. This adds the prescription information to the electronic medical record system, making it available for future reference. The specific operation involves inputting and saving the prescription information. The input is the medication selected by the user, and the output is the prescription information recorded in the patient's chart.

[1846] (Application example 2)

[1847] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1848] In modern medical settings, doctors are required to write prescriptions efficiently and with high accuracy. However, they need to process a large amount of information in a short amount of time, and their own emotions and fatigue can sometimes affect their judgment. Furthermore, selecting medications requires assessing the risk of pre-existing conditions and drug interactions, and it is difficult to perform these tasks consistently in a single system.

[1849] Furthermore, efficient information processing and display is required when pharmacists select the most appropriate medication based on conversations with patients in physical stores such as pharmacies. To address these issues, a system is needed that processes information holistically and efficiently, reducing the burden on doctors and pharmacists.

[1850] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for receiving clinical test data and medical record information, a means for acquiring drug information from a drug database, a means for classifying data and extracting features using a specific algorithm, a means for recommending optimal drugs based on the features, a means for generating and transmitting a list of recommended drugs, and a means for displaying the list of recommended drugs on a wearable display device. This enables doctors and pharmacists to select drugs efficiently and with high accuracy and provide patients with prompt and appropriate treatment.

[1851] "Clinical test data" refers to medical data obtained as a result of a patient's blood test, urine test, diagnostic imaging, etc.

[1852] "Medical record information" refers to medical records necessary for medical treatment, such as a patient's medical history, medical history, medication information, and allergy information.

[1853] A "drug database" is a database that contains information about drug ingredients, effects, side effects, and interactions with other drugs.

[1854] A "specific algorithm" is a mathematical or statistical procedure used to classify data or extract features.

[1855] A "feature extraction method" is a technique or method for extracting important patterns or information from data.

[1856] The "medication recommendation method" is a process for selecting the most suitable medication for a patient based on the extracted features.

[1857] A "recommended drug list" is a list of drugs selected based on specific conditions or characteristics.

[1858] A "wearable display device" is a display device worn by doctors and pharmacists, such as glasses or a head-mounted display.

[1859] An "emotion engine" is a technology or software that recognizes and analyzes a user's emotional state and reflects it in the system's recommendations.

[1860] This invention is a system that efficiently processes clinical test data and medical record information, allowing pharmacists to select prescription drugs quickly and accurately in physical stores. The system of this invention is composed of a server, a terminal, a user (pharmacist), an emotion engine, and a wearable display device.

[1861] Server Processing

[1862] The server plays a central role in the system and performs the following processes:

[1863] 1. The server receives the clinical test data and medical record information sent from the terminal.

[1864] 2. The server checks the received data for consistency and integrity.

[1865] 3. The server accesses the drug database and obtains the latest drug information.

[1866] 4. The server uses specific algorithms to classify and extract features from the received clinical test data and medical record information.

[1867] 5. The server generates a list of optimal drug recommendations based on the extracted features.

[1868] 6. The server uses an emotion engine to recognize the user's (pharmacist's) emotional data and reflects it in the recommended medication list.

[1869] 7. The server sends the generated recommended medication list to the terminal.

[1870] Terminal handling

[1871] The terminal is a device operated by a pharmacist and performs the following processes:

[1872] 1. The terminal receives the patient's clinical test data and medical record information from the pharmacist via the wearable display device.

[1873] 2. The terminal formats the input data and sends it to the server.

[1874] 3. The terminal receives the recommended medication list sent from the server.

[1875] 4. The terminal displays the received list of recommended medications to the pharmacist via the wearable display device.

[1876] User (pharmacist) processing

[1877] The user (pharmacist) performs the following processes through the system.

[1878] 1. The user (pharmacist) uses the wearable display device to input the patient's clinical test data and medical record information into the terminal.

[1879] 2. The user (pharmacist) checks the list of recommended medications displayed on the terminal and selects the appropriate medication.

[1880] 3. The user (pharmacist) decides on the final prescription, taking into account the emotional data provided by the emotion engine.

[1881] 4. The user (pharmacist) prescribes the selected medication to the patient and records it in the patient's medical record.

[1882] Specific examples

[1883] For example, consider the case where a diabetic patient visits a drugstore for a consultation.

[1884] 1. The user (pharmacist) uses the wearable display device to input the diabetic patient's clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) into the terminal.

[1885] 2. The device sends this data to the server.

[1886] 3. The server checks the consistency and completeness of the received data, then classifies the data and extracts features using specific algorithms.

[1887] 4. The server generates a list of recommendations for optimal medications, such as metformin and insulin, based on the extracted features.

[1888] 5. Analyze the user's (pharmacist's) emotional data (e.g., fatigue, impatience) collected by the emotion engine and reflect it in the recommended medication list.

[1889] 6. The server sends the final recommended medication list to the terminal.

[1890] 7. The terminal receives the list of recommended medications and displays it to the user (pharmacist) via the wearable display device.

[1891] 8. The user (pharmacist) checks the list of recommended medications and selects "metformin," which is suitable for the diabetic patient. The user decides on the prescription, taking into consideration feedback from the emotion engine.

[1892] 9. The user (pharmacist) determines "metformin" as the final prescription and records it in the patient's chart.

[1893] Prompt Sentence Examples

[1894] "A user inputs the test results of a diabetic patient into the smart glasses. The emotion engine detects the user's emotions based on the results and sends them to the server."

[1895] In this way, the system of the present invention comprehensively utilizes clinical test data, medical record information, and emotional data to achieve more accurate prescription drug recommendations.

[1896] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1897] Step 1:

[1898] The user uses the wearable display device to input the patient's clinical test data and medical record information into the terminal by voice. The terminal formats the input clinical test data (e.g., blood glucose level 180 mg / dL) and medical record information (e.g., medical history, no current medication) and sends them to the server.

[1899] Step 2:

[1900] The server receives the clinical test data and medical record information sent from the terminal. The server checks the consistency and completeness of the received data, specifically checking the data format and missing values, and generates warning messages if necessary.

[1901] Step 3:

[1902] The server compares the received clinical test data and medical record information with a drug database to obtain relevant and up-to-date drug information. In this process, it extracts the effects, side effects, and interactions of the corresponding drugs from the database.

[1903] Step 4:

[1904] The server uses a specific algorithm to classify the received data and extract features. For example, if a diabetic patient's blood sugar level exceeds the normal range, the server classifies the data as "hyperglycemia." The extracted features, such as diabetes and hyperglycemia, are listed.

[1905] Step 5:

[1906] The server generates a list of optimal medication recommendations based on the extracted features. For example, based on the features of hyperglycemia, drugs such as "metformin" and "insulin" are added to the recommendation list. Side effect risk information based on chronic illnesses and interactions with other drugs is also reflected.

[1907] Step 6:

[1908] The server recognizes the user's (pharmacist's) emotional data using an emotion engine. The emotion engine analyzes data obtained from sensors installed in the wearable display device and detects the user's emotional state (e.g., fatigue, impatience).

[1909] Step 7:

[1910] The server analyzes the emotion data collected by the emotion engine and reflects it in the recommended medication list. For example, for a user who is fatigued, medications that are easy to select are displayed preferentially on the list.

[1911] Step 8:

[1912] The server transmits the generated recommended medication list to the terminal. For example, data including detailed information on "metformin" and "insulin" is transmitted to the terminal as the recommended medication list.

[1913] Step 9:

[1914] The terminal displays the list of recommended medications sent from the server on the wearable display device. The user (pharmacist) checks the displayed list of medications and selects the appropriate medication. For example, specific information about "metformin" (efficacy, side effects, drug interactions) is displayed.

[1915] Step 10:

[1916] The user (pharmacist) decides on the final prescription while referring to the recommended medication list. The selected medication (e.g., metformin) is recorded in the patient's medical record and prescribed to the patient. In some cases, feedback from the emotion engine is also used to help with the prescription decision.

[1917] In this way, the system comprehensively utilizes clinical test data, medical record information, and emotional data to achieve efficient and highly accurate drug selection.

[1918] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1919] 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.

[1920] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1921] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1922] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1923] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1924] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1925] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1926] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1927] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1928] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1929] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1930] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1931] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1932] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1933] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1934] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1935] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1936] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1937] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1938] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1939] The following is further disclosed regarding the above embodiment.

[1940] (Claim 1)

[1941] means for receiving laboratory test data and medical record information;

[1942] means for obtaining drug information from a drug database;

[1943] A means for classifying data and extracting features using a specific algorithm;

[1944] a means for recommending an optimal medication based on said characteristics;

[1945] means for generating and transmitting a recommended medication list;

[1946] A system including:

[1947] (Claim 2)

[1948] The system according to claim 1, further comprising means for evaluating the risk of side effects based on chronic illnesses and drug interactions, and reflecting the results in a list of recommended drugs.

[1949] (Claim 3)

[1950] 10. The system of claim 1, further comprising means for verifying consistency and completeness of clinical laboratory data and medical record information.

[1951] "Example 1"

[1952] (Claim 1)

[1953] means for receiving laboratory test data and medical record information;

[1954] means for obtaining drug information from a drug database;

[1955] A means for classifying data and extracting features using a specific algorithm;

[1956] a means for recommending an optimal medication based on said characteristics;

[1957] means for generating and transmitting a recommended medication list;

[1958] means for formatting data entered by a user at the terminal and transmitting the data to a server;

[1959] a means for displaying the recommended drug list sent from the server;

[1960] A system including:

[1961] (Claim 2)

[1962] The system according to claim 1, further comprising means for evaluating the risk of side effects based on chronic illnesses and drug interactions, and reflecting the results in a list of recommended drugs.

[1963] (Claim 3)

[1964] 10. The system of claim 1, further comprising means for verifying consistency and completeness of clinical laboratory data and medical record information.

[1965] "Application Example 1"

[1966] (Claim 1)

[1967] means for receiving laboratory test data and medical record information;

[1968] means for obtaining drug information from a drug database;

[1969] A means for classifying data and extracting features using a specific algorithm;

[1970] a means for recommending an optimal medication based on said characteristics;

[1971] means for generating and transmitting a recommended medication list;

[1972] means for collecting and analyzing passenger biometric data;

[1973] A means of constantly monitoring health data and detecting abnormalities;

[1974] A means to automatically guide you to the nearest medical institution in an emergency,

[1975] A system including:

[1976] (Claim 2)

[1977] The system according to claim 1, further comprising means for evaluating the risk of side effects based on chronic illnesses and drug interactions, and reflecting the results in a list of recommended drugs.

[1978] (Claim 3)

[1979] 10. The system of claim 1, further comprising means for verifying consistency and completeness of clinical laboratory data and medical record information.

[1980] "Example 2: Combining Emotion Engines"

[1981] (Claim 1)

[1982] means for receiving laboratory test data and medical record information;

[1983] a means for verifying the consistency and integrity of the received data;

[1984] means for retrieving drug information from a drug database;

[1985] A means for classifying data and extracting features using a specific algorithm;

[1986] A means for recommending optimal medicines based on the extracted features;

[1987] a means for generating and transmitting a recommended medication list;

[1988] A means for recognizing user emotions, analyzing the emotion data, and reflecting the result in a recommendation list;

[1989] A system including:

[1990] (Claim 2)

[1991] The system according to claim 1, further comprising means for evaluating the risk of side effects based on chronic illnesses and drug interactions, and reflecting the results in a list of recommended drugs.

[1992] (Claim 3)

[1993] 10. The system of claim 1, further comprising means for verifying consistency and completeness of clinical laboratory data and medical record information.

[1994] "Application example 2 when combining emotion engines"

[1995] (Claim 1)

[1996] means for receiving laboratory test data and medical record information;

[1997] means for obtaining drug information from a drug database;

[1998] A means for classifying data and extracting features using a specific algorithm;

[1999] a means for recommending an optimal medication based on said characteristics;

[2000] means for generating and transmitting a recommended medication list;

[2001] means for displaying a list of recommended medications via a wearable display device;

[2002] A system including:

[2003] (Claim 2)

[2004] The system according to claim 1, further comprising means for evaluating the risk of side effects based on chronic illnesses and drug interactions, and reflecting the results in a list of recommended drugs.

[2005] (Claim 3)

[2006] 10. The system of claim 1, further comprising means for verifying consistency and completeness of clinical laboratory data and medical record information. [Explanation of symbols]

[2007] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving laboratory test data and medical record information; means for obtaining drug information from a drug database; A means for classifying data and extracting features using a specific algorithm; a means for recommending an optimal medication based on said characteristics; means for generating and transmitting a recommended medication list; A system including:

2. The system according to claim 1 , further comprising means for evaluating a risk of side effects based on chronic illnesses and drug interactions, and reflecting the evaluation result in a list of recommended drugs.

3. 10. The system of claim 1, further comprising means for verifying the consistency and completeness of the clinical test data and medical record information.

Images