System

Abstract

A system is provided.SOLUTION: A system comprising: means for recording a user's voice; means for converting voice data into text data; means for extracting medical information from the text data; means for automatically describing the extracted medical information in an electronic medical record; means for recommending a suspected disease, a necessary examination, and a therapeutic agent; means for automatically executing an order of the recommended examination and therapeutic agent; and means for automatically creating a medical certificate.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] Currently, doctors and other medical professionals in the medical field are tasked with a large amount of administrative work, which leads to a decline in the quality of medical care and patient satisfaction. While there is a demand for the widespread use of electronic medical records, the administrative burden is significant and their effective use is difficult. Tasks such as recording information during consultations, ordering tests and medications, creating medical certificates, and handling accounting are particularly time-consuming. As a result, doctors have less time to spend with patients, leading to a decline in the efficiency of medical care. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for recording a user's voice, a means for converting voice data into text data, a means for extracting medical information from the text data, a means for automatically recording the extracted medical information in an electronic medical record, a means for recommending suspected diseases and necessary tests and therapeutic drugs, a means for automatically ordering the recommended tests and therapeutic drugs, a means for automatically creating a medical certificate, a means for inputting insurance information and automatically calculating billing amounts based on the medical treatment details, and a means for analyzing past medical record information and automatically creating a medical summary for returning patients. This system reduces the administrative burden on medical professionals, allowing them to focus on treating patients. It also improves medical efficiency and patient satisfaction.

[0006] A "user" is a physician or medical professional who operates on the system.

[0007] "Audio data" refers to digitally recorded data of a conversation between a user and a patient.

[0008] "Text data" refers to data obtained by converting voice data into character information.

[0009] "Medical information" refers to detailed information such as a patient's symptoms, medical history, and medication information obtained through medical examinations.

[0010] An "electronic medical record" is an electronic system for recording and managing patient medical information in digital form.

[0011] An "order" is an instruction to perform an examination, prescribe a medication, etc.

[0012] "Automatic execution" refers to the system performing a specific operation based on pre-defined rules without user intervention.

[0013] A "medical certificate" is an official document in which a doctor records the results of a patient's diagnosis.

[0014] "Insurance information" refers to information regarding the medical insurance to which the patient is enrolled.

[0015] "Amount billed" refers to the amount billed to the patient as the cost of medical treatment or procedure.

[0016] A "medical summary" is summary information compiled at the time of a follow-up visit based on past medical record information.

[0017] "Server" means a centralized device that performs the primary data processing and management of the system.

[0018] A "terminal" is a device that constitutes part of a system and is primarily operated by a user. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

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

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system for automating administrative tasks in an electronic medical record system to reduce the burden on medical professionals. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[0041] 1. Speech Recognition and Text Conversion

[0042] The device records the conversation between the doctor and the patient during the consultation. This recorded voice data is sent in real time to a server. The server receives this voice data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0043] 2. Extraction of medical information and entry into electronic medical records

[0044] The server analyzes the text data and extracts medical information from it. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter information into the medical record.

[0045] 3. Automatic ordering of necessary tests and medications

[0046] The server identifies suspected diseases based on the extracted medical information and uses an AI model to recommend necessary tests and medications. For example, if a patient complains of a cough and fever, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication. The user can review this, make any necessary corrections, and finally confirm the order. The server then automatically executes the confirmed order and updates the relevant systems.

[0047] 4. Automatic generation of medical certificates

[0048] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, etc. The user can check the certificate and make corrections as necessary, significantly reducing the effort required to create the certificate.

[0049] 5. Automated accounting

[0050] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0051] 6. Automatic generation of summaries for returning patients

[0052] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[0053] Specific examples

[0054] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test, and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user reviews and completes. Through this series of processes, the user can complete many administrative tasks without any hassle.

[0055] As described above, the present invention enables efficient operation of an electronic medical record system and provides specific means for reducing the administrative work of medical personnel as much as possible.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The device records the conversation between the doctor and the patient during the consultation, and is designed to record high-quality audio data.

[0059] Step 2:

[0060] The device sends the recorded audio data to the server in real time, and the communication is encrypted to ensure security.

[0061] Step 3:

[0062] The server inputs the received voice data into a speech recognition model that is specifically trained to accurately recognize medical terminology and converts it into text.

[0063] Step 4:

[0064] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[0065] Step 5:

[0066] The server automatically records the extracted medical information in the electronic medical record, entering the information according to pre-defined templates.

[0067] Step 6:

[0068] The server identifies suspected illnesses based on the analysis results and recommends necessary tests and medications. For example, in the case of a cough and fever, it would recommend a chest X-ray, blood tests, and antipyretic and analgesic medications.

[0069] Step 7:

[0070] The user checks the recommendations and makes any necessary corrections. The server automatically orders the confirmed tests and medications, and the results are reflected in the electronic medical records and testing system.

[0071] Step 8:

[0072] The server automatically generates a medical report that includes the patient's symptoms, diagnosis, and recommended treatment.

[0073] Step 9:

[0074] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[0075] Step 10:

[0076] The terminal scans the patient's insurance card and reads the insurance information.

[0077] Step 11:

[0078] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[0079] Step 12:

[0080] The server analyzes past medical records and automatically creates a medical summary for returning patients. When a patient returns to the hospital, treatment is based on this summary.

[0081] Step 13:

[0082] The user reviews and corrects the automatically generated medical summary and completes the final summary.

[0083] Example 1

[0084] 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."

[0085] Medical institutions face a problem of a heavy administrative burden related to medical treatment and diagnosis, preventing medical professionals from concentrating on their primary medical activities. In particular, tasks such as filling out medical records, creating medical certificates, and processing insurance claims are time-consuming and labor-intensive, requiring efficient operations. It is also difficult to quickly grasp past medical information for returning patients and determine the necessary tests and medications. To solve these issues, a system that highly automates administrative tasks and reduces the burden on medical professionals is needed.

[0086] 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.

[0087] In this invention, the server includes means for recording a user's voice, means for converting voice data into text data, means for extracting medical information from the text data, means for automatically recording the extracted medical information in a record, means for recommending suspected diseases and necessary tests and medications, means for automatically executing instructions for the recommended tests and medications, means for automatically generating reports, means for inputting insurance information and automatically calculating billing amounts based on the medical treatment details, means for analyzing past medical information and automatically creating medical summaries for returning patients, means for transmitting voice data to the server in real time, means for analyzing text data using natural language processing technology, means for generating recommendations using an AI model, and means for extracting text data from image data using OCR technology. This automates administrative tasks such as filling out medical charts, creating medical certificates, and processing insurance claims, enabling medical professionals to focus on their medical activities.

[0088] "User" refers to the medical professional or doctor in charge of medical treatment.

[0089] "Audio data" refers to data in which audio is recorded in digital format.

[0090] "Text data" refers to data that includes character information converted from audio data.

[0091] "Medical information" refers to information about a patient's chief complaint, symptoms, medical history, and diagnosis.

[0092] "Record" refers to documents containing patient medical information, such as electronic medical records and medical notes.

[0093] "Suspected disease" refers to a potential disease that is suspected based on medical information.

[0094] "Test" means a medical procedure to confirm or diagnose a suspected illness.

[0095] "Medication" means a medicine prescribed for medical treatment.

[0096] "Recommendation" refers to proposing optimal testing and treatment options derived from AI models, etc.

[0097] "Instructions" refer to medical procedures that are ultimately approved by the user.

[0098] A "report" refers to a document that summarizes diagnostic results, treatment plans, etc.

[0099] "Insurance Information" refers to information regarding a patient's health insurance.

[0100] "Billed amount" refers to the amount of medical expenses calculated based on the medical treatment.

[0101] "Medical summary" refers to a summary document that compiles past medical information for returning patients.

[0102] A "server" refers to a computer system that analyzes voice data and manages medical information.

[0103] "Natural language processing technology" is a technology for analyzing text data and is used to extract useful information from text data.

[0104] "AI model" refers to a predictive model built using machine learning algorithms.

[0105] "OCR technology" is a technology that optically reads character information and converts it into digital data.

[0106] This invention relates to an electronic medical record system that automates administrative tasks in medical institutions to reduce the burden on medical staff. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[0107] Speech recognition and text conversion

[0108] The device records the conversation between the doctor and the patient during the consultation. The recorded audio data is sent to a server in real time. The server then converts the audio data into text using a speech recognition model such as Google Cloud Speech-to-Text or IBM Watson Speech to Text. The converted text data includes information such as the patient's chief complaint, symptoms, and medical history.

[0109] Extraction of medical information and entry into electronic medical records

[0110] The server uses natural language processing (NLP) technology to analyze the text data and extract medical information from it. Software such as SpaCy and Stanford NLP are used. The extracted medical information is automatically entered into an electronic medical record template and stored in an SQL database.

[0111] Automatic ordering of necessary tests and medications

[0112] The server uses the extracted medical information to make inferences to identify suspected illnesses. AI models built with TensorFlow and PyTorch are used for inference. For example, if a patient complains of a cough and fever, the server recommends a chest X-ray, blood tests, and prescriptions for antipyretics and analgesics. The user can review these recommendations and make corrections as necessary. Once the final order is confirmed, the server updates the relevant systems and automatically executes it.

[0113] Automatic generation of medical certificates

[0114] The server automatically generates a medical certificate using a medical certificate template based on the details of the examination and the patient's medical record. The medical certificate includes the patient's symptoms, diagnosis, and recommended treatment. The user can review the medical certificate and make any necessary corrections.

[0115] Automating accounting processes

[0116] The terminal scans the patient's insurance card and sends the information to the server. The server extracts the insurance information using OCR technology (e.g., Tesseract OCR). The server then automatically calculates the billing amount based on the insurance information and the medical treatment details, and automatically updates the accounting system. Finally, a bill is issued to the patient.

[0117] Automatic summary generation for returning patients

[0118] The server analyzes the past medical records of returning patients and automatically generates a medical summary that will be useful for the next visit. The user can then check the summary and make any necessary corrections.

[0119] Specific examples

[0120] Consider the case of a 40-year-old male patient who complains of a persistent cough for the past few days and a high fever of 38 degrees since yesterday. In this case, the device records the conversation, and the server converts the audio into text using Google Cloud Speech-to-Text. The converted text is analyzed using SpaCy to extract the patient's symptom information. Based on the extracted information, the server recommends a chest X-ray and blood tests, and suggests a prescription for antipyretic and analgesic medication. Once the user confirms the order, the server automatically generates a medical certificate, which is ultimately saved and distributed in PDF format.

[0121] Prompt Sentence Examples

[0122] The following prompt sentence can be input into the generative AI model to automatically generate medical documents:

[0123] A 40-year-old male patient comes to the clinic complaining, "I've had a cough that hasn't stopped for the past few days. I've had a high fever of 38 degrees since yesterday." Based on the consultation, please write about the patient's symptoms, the recommended tests, and the prescribed medications.

[0124] These procedures allow users to efficiently complete many administrative tasks without any hassle.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] The device records the conversation between the doctor and the patient during the consultation. The device's microphone is used to collect the conversation audio in WAV file format and save it as a file. The input is the conversation audio during the consultation, and the output is the recorded WAV file.

[0128] Step 2:

[0129] The device transmits the recorded audio data to the server in real time. The saved WAV file is uploaded to the server using the HTTP protocol. The input is the WAV file, and the output is the audio data transferred to the server.

[0130] Step 3:

[0131] The server calls the Google Cloud Speech-to-Text API to convert the received voice data into text data. It sends an API request and performs speech analysis. The input is the voice data, and the output is the converted text data.

[0132] Step 4:

[0133] The server analyzes the text data using natural language processing (NLP) technology. The software used is SpaCy or Stanford NLP. Important keywords (e.g., fever, cough, etc.) are extracted from the text data. The input is the text data, and the output is JSON data containing the extracted medical information.

[0134] Step 5:

[0135] The server stores the extracted medical information in an SQL database and automatically records it in an electronic medical record template. The input is medical information in JSON format, and the output is the information automatically recorded in the electronic medical record.

[0136] Step 6:

[0137] The server uses an AI model (using TensorFlow or PyTorch) to identify suspected diseases based on the extracted information and recommend necessary tests and treatments. Input data is provided to the AI ​​model, and an inference result is obtained. The input is medical information, and the output is a list of recommended tests and treatments.

[0138] Step 7:

[0139] The user reviews the recommended tests and medications on the web interface, makes any necessary modifications, and clicks a button on the UI to confirm the final order. The input is the recommendations and any modifications made by the user, and the output is the confirmed order.

[0140] Step 8:

[0141] The server sends the confirmed order in HL7 message format to the related systems (test order system, medication management system) and executes it automatically. The input is the confirmed order data, and the output is the order message sent to the related systems.

[0142] Step 9:

[0143] The server automatically generates a medical certificate using a LaTeX template based on the information in the medical record. The generated medical certificate is saved in PDF format and a download link is provided to the user. The input is the medical record information, and the output is a medical certificate in PDF format.

[0144] Step 10:

[0145] The terminal uses a scanner to scan the patient's insurance card and generate an image file. The input is the actual insurance card, and the output is the scanned image file.

[0146] Step 11:

[0147] The device sends the image file to the server and converts it into text data using OCR technology (using Tesseract OCR). The input is the scanned image file, and the output is text data containing insurance information.

[0148] Step 12:

[0149] The server automatically calculates the billing amount based on the insurance information and medical information using a rule engine (such as Drools). The input is the insurance information and medical information, and the output is the calculated billing amount.

[0150] Step 13:

[0151] The server updates the calculated billing amount to an accounting system such as SAP, generates a PDF invoice, and emails it to the patient. The input is the calculated billing amount, and the output is the PDF invoice sent.

[0152] Step 14:

[0153] The server analyzes the past medical records of returning patients and processes the data on a Hadoop cluster to extract key medical information. The input is the past medical records, and the output is the extracted medical information.

[0154] Step 15:

[0155] The server automatically generates a medical summary of the returning patient in Markdown format based on the extracted information. The input is the extracted medical information, and the output is the generated medical summary.

[0156] Step 16:

[0157] The user can check the generated medical summary through the web interface, and modify and save it as necessary. The input is the generated medical summary, and the output is the finalized medical summary.

[0158] (Application example 1)

[0159] 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."

[0160] In today's medical field, the administrative work involved in managing electronic medical records and creating medical records is increasing, placing a heavy burden on medical professionals. Providing appropriate diagnoses and treatments requires fast and accurate information entry and analysis, but doing this manually is inefficient and carries the risk of errors. Furthermore, with the spread of online medical consultations, a similarly efficient management system is required for consultations from remote locations. A system is needed to solve these issues and improve efficiency in the medical field.

[0161] 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.

[0162] In this invention, the server includes a means for converting voice data into text data, a means for extracting information from the text data, and a means for automatically recording the extracted information in a recording system. This allows voice data recorded during medical treatment to be converted into text data in real time, and necessary medical information can be quickly extracted. The extracted information is automatically recorded in an electronic medical record, and appropriate diagnoses and treatment recommendations are provided, significantly reducing administrative work in medical settings. Furthermore, past records are analyzed and information is automatically generated during follow-up visits, improving the efficiency of medical treatment. Furthermore, information analysis is possible via an external API, and the results are reflected in medical certificates and other record documents, enabling more accurate medical treatment.

[0163] "Audio data" refers to data in which an audio signal is recorded in digital format.

[0164] "Text data" refers to data in which character information is recorded in digital format.

[0165] "Information extraction" is the process of selecting necessary information from data based on a specific purpose.

[0166] A "system of record" is a computer system for storing and managing data.

[0167] A "disease" is a state of deviation from the normal physiological function of an organism, or a pathological process leading to that state.

[0168] A "test" is a method or procedure for making a medically necessary diagnosis or evaluation.

[0169] A "therapeutic procedure" is a method for treating, improving, or alleviating a specific disease or disorder.

[0170] A "recommendation" is a suggestion or recommendation based on specific conditions.

[0171] An "external API" is a mechanism that allows programs to exchange data and functions using interfaces provided by external applications and services.

[0172] "Analysis" is the process of examining data in detail to understand and evaluate its structure and content.

[0173] A "medical certificate" is an official document that lists the diagnosis and treatment plan.

[0174] "Insurance Information" means data and records relating to health insurance.

[0175] "Amount Due" means the amount due for services or goods.

[0176] A "revisit" is a consultation for additional treatment or evaluation after the initial visit.

[0177] The present invention provides a system for supporting the work of medical professionals in a virtual medical environment. This system converts voice data into text data, extracts medical information from the text data, and automatically creates various recommendations and records. Specific embodiments of the system are described below.

[0178] Speech recognition and text conversion

[0179] The conversation between the patient and doctor during the consultation is recorded using a device such as a smartphone or head-mounted display. The recorded voice data is sent to a server in real time. The server then uses voice recognition software (e.g., Google Speech Recognition API) to convert this voice data into text data. Through this process, the patient's chief complaint, symptoms, medical history, etc. are recorded in text format.

[0180] Extraction of medical information and entry into electronic medical records

[0181] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from the converted text data. This extraction includes information provided by the patient and treatment details provided by the doctor. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter medical records.

[0182] Automated Recommendations and Ordering

[0183] The server estimates the diagnosis based on the extracted medical information and recommends the necessary tests and treatments. The recommended tests and treatments are then automatically ordered after the user confirms and modifies them as necessary. For example, if a patient complains of a persistent cough and high fever for the past few days, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication.

[0184] Automated medical certificate and accounting procedures

[0185] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The user can review the certificate and make corrections as necessary, reducing the effort required to create the certificate. The server also automatically calculates the billing amount based on the patient's insurance information and details of the treatment, and updates the accounting system. The calculated billing amount is then issued to the patient.

[0186] Automatic summary generation for returning patients

[0187] The server analyzes past medical records and automatically generates medical summaries for returning patients. By providing medical treatment based on these summaries, users can improve their work efficiency. For example, if a patient who was previously diagnosed with pneumonia returns for a follow-up visit, a summary of their past treatment history, medication prescription history, and other information is automatically generated, allowing users to easily check it.

[0188] Examples and prompts

[0189] A specific example would be a case where a 40-year-old male patient complains, "I haven't had a cough for several days and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user confirms and completes.

[0190] An example of a prompt to input to a generative AI model is as follows:

[0191] Extract medical information from the following text:

[0192] A 40-year-old male patient has had a persistent cough for the past few days and has had a high fever of 38 degrees since yesterday. A chest X-ray will be performed and we are considering prescribing antipyretics and analgesics.

[0193] In this way, the present invention is a system that reduces the burden on medical professionals in a virtual medical environment and enables efficient and accurate medical treatment.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] Recording and transmitting audio data

[0197] The terminal records the conversation between the patient and the doctor during the consultation. This voice data is input and the recorded voice data is sent to the server in real time. The specific operation of the terminal is to capture the voice through the microphone and transfer it to the server via the network.

[0198] Step 2:

[0199] Converting audio data to text

[0200] The server converts the received voice data into text data using voice recognition software such as the Google Speech Recognition API. The input in this process is the voice data, and the output is the corresponding text data. Specifically, the server calls the voice recognition API, analyzes the voice signal, and outputs the corresponding string of characters.

[0201] Step 3:

[0202] Extracting medical information from text data

[0203] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from text data. The input to this process is text data, and the output is the extracted medical information. Specifically, the server sends the prompt "Please extract medical information from the following text:" and the text data to the GPT-3 model, and receives the returned information as medical information.

[0204] Step 4:

[0205] Automatic recording of medical information in electronic medical records

[0206] The server automatically enters the extracted medical information into the electronic medical record template. In this step, the input is medical information and the output is an updated electronic medical record. Specifically, the server calls the API of the electronic medical record system and automatically enters the information into the corresponding fields in the medical record.

[0207] Step 5:

[0208] Automated recommendation and order fulfillment

[0209] The server predicts the diagnosis based on the medical information and recommends the necessary tests and treatments. After the user confirms and modifies the order, it automatically executes the order. The input is the extracted medical information and the order data modified by the user, and the output is the executed order. Specifically, the server uses the AI ​​model to predict the diagnosis, creates an appropriate order, and reflects it in the electronic medical record system and the testing institution's system.

[0210] Step 6:

[0211] Automatic generation of medical certificates

[0212] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record information. The input to this process is the details of the medical treatment and the medical record information, and the output is the generated medical certificate. Specifically, the server embeds the details of the medical treatment into a medical certificate template and generates the medical certificate in PDF format or other format.

[0213] Step 7:

[0214] Automating accounting processes

[0215] The server automatically calculates the billing amount based on the insurance information and medical details, and reflects this in the accounting system. The input for this step is the insurance information and medical details, and the output is the calculated billing amount. Specifically, the server collates the medical details with the insurance information, generates a bill, and sends the information to the accounting system.

[0216] Step 8:

[0217] Automatic summary generation for returning patients

[0218] The server analyzes past medical record information for returning patients and automatically generates a medical summary. The input to this process is past medical record information, and the output is the generated medical summary. Specifically, the server searches the medical record database and creates a summary based on the past medical history.

[0219] 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.

[0220] This invention is a system that highly automates administrative tasks in an electronic medical record system and improves medical treatment efficiency by recognizing and adapting to the user's emotions. This system is composed of a user, a terminal, and a server, and its specific operation and program processing are described below.

[0221] 1. Speech Recognition and Text Conversion

[0222] The device records the conversation between the doctor and the patient during the consultation. The audio data is designed to be recorded at high quality. The recorded audio data is sent to the server in real time. The server receives this audio data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0223] 2. Emotion recognition and information regulation

[0224] The device sends recorded voice data to the emotion engine, which recognizes the emotions of the user (doctor or patient). The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[0225] 3. Extraction of medical information and entry into electronic medical records

[0226] The server analyzes the text data using natural language processing (NLP) technology. As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[0227] 4. Automatic ordering of necessary tests and medications

[0228] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[0229] 5. Automatic generation of medical certificates

[0230] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[0231] 6. Automating accounting processes

[0232] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0233] 7. Automatic generation of summaries for returning patients

[0234] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[0235] Specific examples

[0236] For example, consider the case of a 40-year-old male patient who complains, "I haven't had a cough for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice into text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate support. For example, if the patient is feeling anxious, the system will display detailed explanations and help the doctor explain things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[0237] As described above, the present invention enables efficient operation of electronic medical record systems, minimizes administrative work for medical professionals, and provides a better medical environment by recognizing and adapting to user emotions.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] The device records the conversation between the doctor and the patient during the consultation. The recording function is designed to capture high-quality audio data, which is then sent to the server in real time.

[0241] Step 2:

[0242] The device sends the recorded voice data to the emotion engine, which recognizes the emotions of the user and patient. The emotion engine analyzes the voice features and identifies emotions such as tension, anger, and joy.

[0243] Step 3:

[0244] The server inputs the received voice data into a speech recognition model and converts it into text data, which then contains the patient's complaint, symptoms, medical history, and other information contained in the conversation.

[0245] Step 4:

[0246] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[0247] Step 5:

[0248] The server automatically fills the extracted medical information into an electronic medical record template, adjusting the filling based on the emotional data identified from the emotion engine. For example, if the doctor is tired, a concise presentation of information is preferred.

[0249] Step 6:

[0250] The server identifies suspected diseases based on the analysis results and emotional data, and recommends necessary tests and treatments. If the patient is in a high state of anxiety, detailed explanations of the tests and treatments will be automatically displayed.

[0251] Step 7:

[0252] The user checks the recommended tests and medications and makes any necessary changes. Once the final order is confirmed, the server automatically executes the order and updates the relevant systems.

[0253] Step 8:

[0254] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The content and format of the certificate are adjusted based on data from the emotion engine. For example, if the patient is feeling anxious, advice on how to relieve stress is added.

[0255] Step 9:

[0256] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[0257] Step 10:

[0258] The device scans the patient's insurance card and sends the information to the server, where it is automatically updated in the system.

[0259] Step 11:

[0260] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[0261] Step 12:

[0262] The server analyzes past medical records and automatically creates a medical summary for returning patients. This summary can be used to provide treatment at the time of the return visit, making treatment more efficient.

[0263] Step 13:

[0264] The user reviews the automatically generated medical summary and corrects it if necessary, resulting in the final summary.

[0265] Example 2

[0266] 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."

[0267] In today's medical field, doctors and nurses are overwhelmed with a large amount of administrative work, which reduces the efficiency of medical treatment. It is also difficult to appropriately recognize and respond to patients' emotions, which affects patient satisfaction and the effectiveness of treatment. Furthermore, processing medical treatment details and insurance information is time-consuming, and past information cannot be efficiently utilized even during follow-up visits. This increases the burden on medical professionals and poses the issue of a decline in the quality of medical treatment.

[0268] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0269] In this invention, the server includes means for converting voice data into text data, means for using natural language processing technology to extract medical information from the text data, and means for recognizing the user's emotions and adjusting the way information is displayed and the content of recommendations. This significantly automates the administrative work of doctors and nurses during medical treatment, and by appropriately recognizing and responding to patients' emotions, it improves the efficiency and quality of medical treatment, reduces the burden on medical professionals, and improves patient satisfaction.

[0270] "Users" are medical professionals such as doctors and nurses who use the system.

[0271] "Audio data" is digital information that is a recording of the conversation between the user and the patient.

[0272] "Text data" refers to voice data converted into text information.

[0273] An "electronic medical record" is a system for electronically recording and managing a patient's medical information.

[0274] "Natural language processing technology" refers to the general technology that enables computers to understand, analyze, and generate human language.

[0275] An "emotion engine" is software or algorithms that analyze and recognize the emotions of users or patients.

[0276] "Recommendation of tests and treatments" is a function in which the system suggests appropriate tests and treatments based on the analysis results.

[0277] A "medical certificate" is an official document that lists medical examination results and treatment plans.

[0278] "Insurance Information" refers to data relating to a patient's health insurance.

[0279] "Billed amount" is the total amount calculated based on the medical treatment.

[0280] A "medical summary" is summary information created based on past medical information.

[0281] The present invention is an electronic medical record system that significantly improves the efficiency of medical treatment in medical settings. This system is composed of a user, a terminal, and a server, and utilizes speech recognition, emotion recognition, natural language processing (NLP), and data analysis technologies in an integrated manner. Specific embodiments are described below.

[0282] Speech recognition and text conversion

[0283] The device records the conversation between the doctor and the patient during the consultation. The recording device is equipped with a high-quality microphone and dedicated recording software. The recorded audio data is sent to a server in real time. The server receives this audio data and converts it into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0284] Emotion recognition and information regulation

[0285] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[0286] Extraction of medical information and entry into electronic medical records

[0287] The server analyzes the text data using natural language processing (NLP) techniques (e.g., SpaCy or BERT). As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[0288] Automatic ordering of necessary tests and medications

[0289] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[0290] Automatic generation of medical certificates

[0291] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[0292] Automating accounting processes

[0293] The device scans the patient's insurance card and sends the information to the server, which then automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0294] Automatic summary generation for returning patients

[0295] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing medical treatment based on this summary during the return visit, the user's work efficiency is improved. The user can then review the summary and make any necessary corrections.

[0296] Specific examples

[0297] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate responses. For example, if the patient is feeling anxious, the system will display detailed explanations and support the patient in explaining things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[0298] Example of input prompt for generative AI model

[0299] Below is an example of an input prompt for the generative AI model based on the case of a 40-year-old male patient who complained of a persistent cough for the past few days and a high fever of 38 degrees Celsius since yesterday.

[0300] "A 40-year-old male patient has had a persistent cough for the past few days, and has had a high fever of 38 degrees since yesterday. Based on this information, please perform speech recognition, sentiment analysis, and natural language processing, record it in the electronic medical record, and generate a processing code that will recommend appropriate tests and treatments."

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Step 1:

[0303] The user begins a consultation. The device records the conversation between the doctor and the patient in high-quality format. Specifically, a microphone installed in the examination room captures the audio, and the audio data is stored in the device. The input is the audio of the conversation between the doctor and the patient, and the output is the recorded audio data.

[0304] Step 2:

[0305] The device transmits the recorded audio data to the server in real time using a secure protocol over an internet connection. The input is the recorded audio data, and the output is the audio data transmitted to the server.

[0306] Step 3:

[0307] The server converts the received voice data into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). Specifically, the speech recognition algorithm analyzes the voice signal and converts it into text information. The input is the voice data sent to the server, and the output is text data.

[0308] Step 4:

[0309] The server analyzes the text data and uses natural language processing (NLP) techniques (e.g., SpaCy or BERT) to extract medical information such as the patient's chief complaint, symptoms, and medical history. The input is text data generated by speech recognition, and the output is the extracted medical information. Specifically, the NLP engine analyzes the text and identifies important medical information.

[0310] Step 5:

[0311] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The input is the recorded voice data, and the output is the recognized emotion data. Specifically, the emotion engine analyzes the voice data and identifies the user's emotional state.

[0312] Step 6:

[0313] The server analyzes the text data and emotion data and adjusts the extracted medical information and the content to be recorded in the electronic medical record. The input is text data and emotion data, and the output is adjusted medical information. Specifically, the system changes the way information is displayed and the recommended content based on the emotion data.

[0314] Step 7:

[0315] The server automatically enters the extracted medical information into an electronic medical record template. The input is the adjusted medical information, and the output is the data recorded in the electronic medical record. The specific operation is to embed the data into the template and complete the medical record.

[0316] Step 8:

[0317] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. The input is medical information recorded in the electronic medical record, and the output is the recommended tests and medications. Specifically, the diagnostic algorithm suggests the optimal tests and treatments.

[0318] Step 9:

[0319] The server automatically executes the order for the recommended tests and medications. The input is the recommended tests and medications, and the output is the executed test and treatment order. Specific operations include sending the necessary information to the ordering system.

[0320] Step 10:

[0321] The server automatically generates a medical certificate. The input is the data recorded in the electronic medical record and examination and treatment information, and the output is the completed medical certificate. Specifically, the data is embedded in a medical certificate template and an official medical certificate is generated.

[0322] Step 11:

[0323] The terminal scans the patient's insurance card and sends the information to the server. The input is the scanned data of the insurance card, and the output is the insurance information sent to the server. Specifically, the scanned image is converted into digital data and sent to the server.

[0324] Step 12:

[0325] The server automatically calculates the billing amount based on the insurance information and medical treatment details, and reflects this in the accounting system. The input is the medical treatment details and insurance information, and the output is the calculated billing amount. Specifically, the amount is calculated using the medical treatment details and insurance information, and registered in the accounting system.

[0326] Step 13:

[0327] The server analyzes past medical record information and automatically creates medical summaries for returning patients. The input is past medical record data, and the output is a medical summary for the returning patient. Specifically, the server analyzes the medical record data, extracts important medical information, and compiles it into a summary.

[0328] Step 14:

[0329] The user reviews the generated summary and corrects it if necessary. The input is the automatically generated medical summary, and the output is the reviewed and corrected summary. Specific operations involve the user viewing the summary and manually correcting any inaccuracies.

[0330] (Application example 2)

[0331] 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."

[0332] With conventional customer service systems, it is difficult for store staff to accurately understand customer feedback in real time and respond appropriately in an instant. Furthermore, while flexible responses based on customer emotions are required, there is a lack of means to achieve this. As a result, customer satisfaction declines and purchasing motivation decreases.

[0333] 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 means for recording the user's voice, means for converting voice data into text data, means for extracting information from the text data, means for automatically recording the extracted information in an electronic record, means for making necessary suggestions and recommendations, means for automatically implementing the recommended content, means for automatically creating a report, means for inputting transaction information and automatically calculating the billing amount based on the usage details, means for analyzing past information and automatically creating a summary of repeat users, and means for recognizing emotions from the user's voice and adjusting the response. This enables store clerks to accurately understand customer voices and respond appropriately and flexibly in real time according to their emotions.

[0334] "User" refers to the entity that uses the system, including store clerks and customers.

[0335] "Voice data" refers to digital audio signals recorded from users or customers.

[0336] "Text data" is voice data converted into character information.

[0337] "Information" refers to important content and elements extracted from the statements of users and customers.

[0338] An "electronic record" is a digital file or database that stores information extracted from audio data.

[0339] "Suggestions and recommendations" refer to appropriate products, services, and methods of response that the system presents based on the needs of the user or customer.

[0340] "Execution" refers to specific actions or operations that are carried out based on the proposed content.

[0341] A "report" is a document automatically created by the system that details the proposal and the results of its implementation.

[0342] "Transaction information" is detailed data relating to transactions with customers, including purchased items, quantities, amounts, etc.

[0343] "Amount Due" means the amount due calculated based on a Transaction.

[0344] "Historical information" refers to historical data stored in the system, such as previous transactions and records.

[0345] "Re-users" are customers or users who have used the system in the past and will use it again.

[0346] The "Summary" is a report document that briefly summarizes the past usage and transaction history of the repeat user.

[0347] "Emotion" refers to the emotional state or mood of a user or customer as recognized from their voice data.

[0348] "Adjustment" is the process of changing and optimizing suggestions and responses based on emotions.

[0349] This invention relates to a "smart customer service system" that improves the efficiency and quality of customer service in brick-and-mortar stores. The system analyzes conversations between users (store clerks) and customers in real time, and provides appropriate product suggestions and services based on the customer's emotions. This is realized by using "smart glasses."

[0350] Hardware and software used

[0351] Hardware:

[0352] Smart glasses (e.g. Google Glass)

[0353] server

[0354] software:

[0355] Speech recognition engine (e.g. Google Cloud Speech-to-Text)

[0356] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[0357] NLP engine (e.g. OpenAI GPT-3)

[0358] Database (e.g. MySQL)

[0359] Data processing and calculation flow

[0360] 1. Speech recognition and text conversion:

[0361] The smart glasses record conversations between store clerks and customers in real time, and the recorded data is sent from the smart glasses to a server where it is converted into text using a voice recognition engine.

[0362] 2. Emotion recognition and information regulation:

[0363] The server passes the text data to an emotion recognition engine to analyze the customer's emotions (e.g., desire, anxiety, interest). This emotion data is used to tailor suggestions and recommendations.

[0364] 3. Appropriate product recommendations:

[0365] As part of its task, the server uses an NLP engine to extract customer intent and requests from the text data, and based on this, it searches for the most suitable product and service information from a database and displays the selected product information on the smart glasses in real time.

[0366] 4. Real-time feedback:

[0367] By combining customer sentiment data with product suggestions, the smart glasses display the most appropriate suggestions and explanations to the salesperson. For example, if a customer shows interest, the smart glasses will provide detailed information about the latest popular products.

[0368] Specific examples

[0369] Consider a scenario in which a store clerk wearing smart glasses is having a conversation with a customer. For example, if the customer says, "I want to know about the latest popular products," the following sequence of events will take place.

[0370] 1. The voice recognition engine converts the customer's speech into text data.

[0371] 2. The emotion recognition engine analyzes the customer's emotions and determines that they are highly interested.

[0372] 3. The NLP engine extracts the latest popular product information from the database.

[0373] 4. The extracted information is displayed on the smart glasses, allowing the store clerk to introduce the latest products.

[0374] Prompt Sentence Examples

[0375] An example of a prompt is shown below.

[0376] The customer seems interested in the latest popular products. His words and facial expressions suggest curiosity and interest. Introduce the latest popular products and explain their features and recommended points. Adjust your speaking style and tempo according to the customer's emotions.

[0377] This system allows for flexible responses tailored to customer emotions, which is expected to improve customer satisfaction and promote sales.

[0378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0379] Step 1: Record the user's voice

[0380] The smart glasses record conversations between store clerks and customers in real time. The recorded data (audio data) is stored in the smart glasses. The user's conversation data is input and output as audio data.

[0381] Step 2: Send the audio data to the server

[0382] The audio data recorded on the device is sent from the smart glasses to the server in real time. The input is the audio data, and the output is the audio data sent to the server.

[0383] Step 3: Convert audio data to text data

[0384] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). At this time, voice data is taken as input and output as text data.

[0385] Step 4: Send the text data to the emotion recognition engine

[0386] The server then sends the converted text data to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the customer's emotions. The input is text data, and the output is emotion data.

[0387] Step 5: Integrate emotion data and text data

[0388] The server integrates the emotional data and text data to generate data corresponding to the customer's emotional state. As a result, the input is text data and emotional data, and the output is the integrated data.

[0389] Step 6: Extract information with an NLP engine

[0390] The server sends the integrated data to an NLP engine (e.g., OpenAI GPT-3) to extract the necessary information from what the customer said. This process takes the integrated data as input and produces the extracted information as output.

[0391] Step 7: Product recommendations based on extracted information

[0392] The server accesses a database (e.g. MySQL) and searches for the appropriate product data based on the extracted information. The input is the extracted information and the output is the product data.

[0393] Step 8: Submit your product data

[0394] The server sends the searched product data to the smart glasses, and the salesperson makes a suggestion to the customer. The input is the product data, and the output is the display data on the smart glasses.

[0395] Step 9: Real-time feedback

[0396] The smart glasses display the proposed product information to the salesperson in real time, helping them to respond to the customer. The salesperson then looks at the displayed data and provides a detailed explanation of the product to the customer. The input is product data, and the output is display data.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] [Second embodiment]

[0401] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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. 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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."

[0413] This invention is a system for automating administrative tasks in an electronic medical record system to reduce the burden on medical professionals. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[0414] 1. Speech Recognition and Text Conversion

[0415] The device records the conversation between the doctor and the patient during the consultation. This recorded voice data is sent in real time to a server. The server receives this voice data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0416] 2. Extraction of medical information and entry into electronic medical records

[0417] The server analyzes the text data and extracts medical information from it. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter information into the medical record.

[0418] 3. Automatic ordering of necessary tests and medications

[0419] The server identifies suspected diseases based on the extracted medical information and uses an AI model to recommend necessary tests and medications. For example, if a patient complains of a cough and fever, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication. The user can review this, make any necessary corrections, and finally confirm the order. The server then automatically executes the confirmed order and updates the relevant systems.

[0420] 4. Automatic generation of medical certificates

[0421] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, etc. The user can check the certificate and make corrections as necessary, significantly reducing the effort required to create the certificate.

[0422] 5. Automated accounting

[0423] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0424] 6. Automatic generation of summaries for returning patients

[0425] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[0426] Specific examples

[0427] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test, and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user reviews and completes. Through this series of processes, the user can complete many administrative tasks without any hassle.

[0428] As described above, the present invention enables efficient operation of an electronic medical record system and provides specific means for reducing the administrative work of medical personnel as much as possible.

[0429] The processing flow will be explained below.

[0430] Step 1:

[0431] The device records the conversation between the doctor and the patient during the consultation, and is designed to record high-quality audio data.

[0432] Step 2:

[0433] The device sends the recorded audio data to the server in real time, and the communication is encrypted to ensure security.

[0434] Step 3:

[0435] The server inputs the received voice data into a speech recognition model that is specifically trained to accurately recognize medical terminology and converts it into text.

[0436] Step 4:

[0437] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[0438] Step 5:

[0439] The server automatically records the extracted medical information in the electronic medical record, entering the information according to pre-defined templates.

[0440] Step 6:

[0441] The server identifies suspected illnesses based on the analysis results and recommends necessary tests and medications. For example, in the case of a cough and fever, it would recommend a chest X-ray, blood tests, and antipyretic and analgesic medications.

[0442] Step 7:

[0443] The user checks the recommendations and makes any necessary corrections. The server automatically orders the confirmed tests and medications, and the results are reflected in the electronic medical records and testing system.

[0444] Step 8:

[0445] The server automatically generates a medical report that includes the patient's symptoms, diagnosis, and recommended treatment.

[0446] Step 9:

[0447] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[0448] Step 10:

[0449] The terminal scans the patient's insurance card and reads the insurance information.

[0450] Step 11:

[0451] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[0452] Step 12:

[0453] The server analyzes past medical records and automatically creates a medical summary for returning patients. When a patient returns to the hospital, treatment is based on this summary.

[0454] Step 13:

[0455] The user reviews and corrects the automatically generated medical summary and completes the final summary.

[0456] Example 1

[0457] 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."

[0458] Medical institutions face a problem of a heavy administrative burden related to medical treatment and diagnosis, preventing medical professionals from concentrating on their primary medical activities. In particular, tasks such as filling out medical records, creating medical certificates, and processing insurance claims are time-consuming and labor-intensive, requiring efficient operations. It is also difficult to quickly grasp past medical information for returning patients and determine the necessary tests and medications. To solve these issues, a system that highly automates administrative tasks and reduces the burden on medical professionals is needed.

[0459] 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.

[0460] In this invention, the server includes means for recording a user's voice, means for converting voice data into text data, means for extracting medical information from the text data, means for automatically recording the extracted medical information in a record, means for recommending suspected diseases and necessary tests and medications, means for automatically executing instructions for the recommended tests and medications, means for automatically generating reports, means for inputting insurance information and automatically calculating billing amounts based on the medical treatment details, means for analyzing past medical information and automatically creating medical summaries for returning patients, means for transmitting voice data to the server in real time, means for analyzing text data using natural language processing technology, means for generating recommendations using an AI model, and means for extracting text data from image data using OCR technology. This automates administrative tasks such as filling out medical charts, creating medical certificates, and processing insurance claims, enabling medical professionals to focus on their medical activities.

[0461] "User" refers to the medical professional or doctor in charge of medical treatment.

[0462] "Audio data" refers to data in which audio is recorded in digital format.

[0463] "Text data" refers to data that includes character information converted from audio data.

[0464] "Medical information" refers to information about a patient's chief complaint, symptoms, medical history, and diagnosis.

[0465] "Record" refers to documents containing patient medical information, such as electronic medical records and medical notes.

[0466] "Suspected disease" refers to a potential disease that is suspected based on medical information.

[0467] "Test" means a medical procedure to confirm or diagnose a suspected illness.

[0468] "Medication" means a medicine prescribed for medical treatment.

[0469] "Recommendation" refers to proposing optimal testing and treatment options derived from AI models, etc.

[0470] "Instructions" refer to medical procedures that are ultimately approved by the user.

[0471] A "report" refers to a document that summarizes diagnostic results, treatment plans, etc.

[0472] "Insurance Information" refers to information regarding a patient's health insurance.

[0473] "Billed amount" refers to the amount of medical expenses calculated based on the medical treatment.

[0474] "Medical summary" refers to a summary document that compiles past medical information for returning patients.

[0475] A "server" refers to a computer system that analyzes voice data and manages medical information.

[0476] "Natural language processing technology" is a technology for analyzing text data and is used to extract useful information from text data.

[0477] "AI model" refers to a predictive model built using machine learning algorithms.

[0478] "OCR technology" is a technology that optically reads character information and converts it into digital data.

[0479] This invention relates to an electronic medical record system that automates administrative tasks in medical institutions to reduce the burden on medical staff. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[0480] Speech recognition and text conversion

[0481] The device records the conversation between the doctor and the patient during the consultation. The recorded audio data is sent to a server in real time. The server then converts the audio data into text using a speech recognition model such as Google Cloud Speech-to-Text or IBM Watson Speech to Text. The converted text data includes information such as the patient's chief complaint, symptoms, and medical history.

[0482] Extraction of medical information and entry into electronic medical records

[0483] The server uses natural language processing (NLP) technology to analyze the text data and extract medical information from it. Software such as SpaCy and Stanford NLP are used. The extracted medical information is automatically entered into an electronic medical record template and stored in an SQL database.

[0484] Automatic ordering of necessary tests and medications

[0485] The server uses the extracted medical information to make inferences to identify suspected illnesses. AI models built with TensorFlow and PyTorch are used for inference. For example, if a patient complains of a cough and fever, the server recommends a chest X-ray, blood tests, and prescriptions for antipyretics and analgesics. The user can review these recommendations and make corrections as necessary. Once the final order is confirmed, the server updates the relevant systems and automatically executes it.

[0486] Automatic generation of medical certificates

[0487] The server automatically generates a medical certificate using a medical certificate template based on the details of the examination and the patient's medical record. The medical certificate includes the patient's symptoms, diagnosis, and recommended treatment. The user can review the medical certificate and make any necessary corrections.

[0488] Automating accounting processes

[0489] The terminal scans the patient's insurance card and sends the information to the server. The server extracts the insurance information using OCR technology (e.g., Tesseract OCR). The server then automatically calculates the billing amount based on the insurance information and the medical treatment details, and automatically updates the accounting system. Finally, a bill is issued to the patient.

[0490] Automatic summary generation for returning patients

[0491] The server analyzes the past medical records of returning patients and automatically generates a medical summary that will be useful for the next visit. The user can then check the summary and make any necessary corrections.

[0492] Specific examples

[0493] Consider the case of a 40-year-old male patient who complains of a persistent cough for the past few days and a high fever of 38 degrees since yesterday. In this case, the device records the conversation, and the server converts the audio into text using Google Cloud Speech-to-Text. The converted text is analyzed using SpaCy to extract the patient's symptom information. Based on the extracted information, the server recommends a chest X-ray and blood tests, and suggests a prescription for antipyretic and analgesic medication. Once the user confirms the order, the server automatically generates a medical certificate, which is ultimately saved and distributed in PDF format.

[0494] Prompt Sentence Examples

[0495] The following prompt sentence can be input into the generative AI model to automatically generate medical documents:

[0496] A 40-year-old male patient comes to the clinic complaining, "I've had a cough that hasn't stopped for the past few days. I've had a high fever of 38 degrees since yesterday." Based on the consultation, please write about the patient's symptoms, the recommended tests, and the prescribed medications.

[0497] These procedures allow users to efficiently complete many administrative tasks without any hassle.

[0498] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0499] Step 1:

[0500] The device records the conversation between the doctor and the patient during the consultation. The device's microphone is used to collect the conversation audio in WAV file format and save it as a file. The input is the conversation audio during the consultation, and the output is the recorded WAV file.

[0501] Step 2:

[0502] The device transmits the recorded audio data to the server in real time. The saved WAV file is uploaded to the server using the HTTP protocol. The input is the WAV file, and the output is the audio data transferred to the server.

[0503] Step 3:

[0504] The server calls the Google Cloud Speech-to-Text API to convert the received voice data into text data. It sends an API request and performs speech analysis. The input is the voice data, and the output is the converted text data.

[0505] Step 4:

[0506] The server analyzes the text data using natural language processing (NLP) technology. The software used is SpaCy or Stanford NLP. Important keywords (e.g., fever, cough, etc.) are extracted from the text data. The input is the text data, and the output is JSON data containing the extracted medical information.

[0507] Step 5:

[0508] The server stores the extracted medical information in an SQL database and automatically records it in an electronic medical record template. The input is medical information in JSON format, and the output is the information automatically recorded in the electronic medical record.

[0509] Step 6:

[0510] The server uses an AI model (using TensorFlow or PyTorch) to identify suspected diseases based on the extracted information and recommend necessary tests and treatments. Input data is provided to the AI ​​model, and an inference result is obtained. The input is medical information, and the output is a list of recommended tests and treatments.

[0511] Step 7:

[0512] The user reviews the recommended tests and medications on the web interface, makes any necessary modifications, and clicks a button on the UI to confirm the final order. The input is the recommendations and any modifications made by the user, and the output is the confirmed order.

[0513] Step 8:

[0514] The server sends the confirmed order in HL7 message format to the related systems (test order system, medication management system) and executes it automatically. The input is the confirmed order data, and the output is the order message sent to the related systems.

[0515] Step 9:

[0516] The server automatically generates a medical certificate using a LaTeX template based on the information in the medical record. The generated medical certificate is saved in PDF format and a download link is provided to the user. The input is the medical record information, and the output is a medical certificate in PDF format.

[0517] Step 10:

[0518] The terminal uses a scanner to scan the patient's insurance card and generate an image file. The input is the actual insurance card, and the output is the scanned image file.

[0519] Step 11:

[0520] The device sends the image file to the server and converts it into text data using OCR technology (using Tesseract OCR). The input is the scanned image file, and the output is text data containing insurance information.

[0521] Step 12:

[0522] The server automatically calculates the billing amount based on the insurance information and medical information using a rule engine (such as Drools). The input is the insurance information and medical information, and the output is the calculated billing amount.

[0523] Step 13:

[0524] The server updates the calculated billing amount to an accounting system such as SAP, generates a PDF invoice, and emails it to the patient. The input is the calculated billing amount, and the output is the PDF invoice sent.

[0525] Step 14:

[0526] The server analyzes the past medical records of returning patients and processes the data on a Hadoop cluster to extract key medical information. The input is the past medical records, and the output is the extracted medical information.

[0527] Step 15:

[0528] The server automatically generates a medical summary of the returning patient in Markdown format based on the extracted information. The input is the extracted medical information, and the output is the generated medical summary.

[0529] Step 16:

[0530] The user can check the generated medical summary through the web interface, and modify and save it as necessary. The input is the generated medical summary, and the output is the finalized medical summary.

[0531] (Application example 1)

[0532] 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."

[0533] In today's medical field, the administrative work involved in managing electronic medical records and creating medical records is increasing, placing a heavy burden on medical professionals. Providing appropriate diagnoses and treatments requires fast and accurate information entry and analysis, but doing this manually is inefficient and carries the risk of errors. Furthermore, with the spread of online medical consultations, a similarly efficient management system is required for consultations from remote locations. A system is needed to solve these issues and improve efficiency in the medical field.

[0534] 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.

[0535] In this invention, the server includes a means for converting voice data into text data, a means for extracting information from the text data, and a means for automatically recording the extracted information in a recording system. This allows voice data recorded during medical treatment to be converted into text data in real time, and necessary medical information can be quickly extracted. The extracted information is automatically recorded in an electronic medical record, and appropriate diagnoses and treatment recommendations are provided, significantly reducing administrative work in medical settings. Furthermore, past records are analyzed and information is automatically generated during follow-up visits, improving the efficiency of medical treatment. Furthermore, information analysis is possible via an external API, and the results are reflected in medical certificates and other record documents, enabling more accurate medical treatment.

[0536] "Audio data" refers to data in which an audio signal is recorded in digital format.

[0537] "Text data" refers to data in which character information is recorded in digital format.

[0538] "Information extraction" is the process of selecting necessary information from data based on a specific purpose.

[0539] A "system of record" is a computer system for storing and managing data.

[0540] A "disease" is a state of deviation from the normal physiological function of an organism, or a pathological process leading to that state.

[0541] A "test" is a method or procedure for making a medically necessary diagnosis or evaluation.

[0542] A "therapeutic procedure" is a method for treating, improving, or alleviating a specific disease or disorder.

[0543] A "recommendation" is a suggestion or recommendation based on specific conditions.

[0544] An "external API" is a mechanism that allows programs to exchange data and functions using interfaces provided by external applications and services.

[0545] "Analysis" is the process of examining data in detail to understand and evaluate its structure and content.

[0546] A "medical certificate" is an official document that lists the diagnosis and treatment plan.

[0547] "Insurance Information" means data and records relating to health insurance.

[0548] "Amount Due" means the amount due for services or goods.

[0549] A "revisit" is a consultation for additional treatment or evaluation after the initial visit.

[0550] The present invention provides a system for supporting the work of medical professionals in a virtual medical environment. This system converts voice data into text data, extracts medical information from the text data, and automatically creates various recommendations and records. Specific embodiments of the system are described below.

[0551] Speech recognition and text conversion

[0552] The conversation between the patient and doctor during the consultation is recorded using a device such as a smartphone or head-mounted display. The recorded voice data is sent to a server in real time. The server then uses voice recognition software (e.g., Google Speech Recognition API) to convert this voice data into text data. Through this process, the patient's chief complaint, symptoms, medical history, etc. are recorded in text format.

[0553] Extraction of medical information and entry into electronic medical records

[0554] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from the converted text data. This extraction includes information provided by the patient and treatment details provided by the doctor. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter medical records.

[0555] Automated Recommendations and Ordering

[0556] The server estimates the diagnosis based on the extracted medical information and recommends the necessary tests and treatments. The recommended tests and treatments are then automatically ordered after the user confirms and modifies them as necessary. For example, if a patient complains of a persistent cough and high fever for the past few days, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication.

[0557] Automated medical certificate and accounting procedures

[0558] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The user can review the certificate and make corrections as necessary, reducing the effort required to create the certificate. The server also automatically calculates the billing amount based on the patient's insurance information and details of the treatment, and updates the accounting system. The calculated billing amount is then issued to the patient.

[0559] Automatic summary generation for returning patients

[0560] The server analyzes past medical records and automatically generates medical summaries for returning patients. By providing medical treatment based on these summaries, users can improve their work efficiency. For example, if a patient who was previously diagnosed with pneumonia returns for a follow-up visit, a summary of their past treatment history, medication prescription history, and other information is automatically generated, allowing users to easily check it.

[0561] Examples and prompts

[0562] A specific example would be a case where a 40-year-old male patient complains, "I haven't had a cough for several days and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user confirms and completes.

[0563] An example of a prompt to input to a generative AI model is as follows:

[0564] Extract medical information from the following text:

[0565] A 40-year-old male patient has had a persistent cough for the past few days and has had a high fever of 38 degrees since yesterday. A chest X-ray will be performed and we are considering prescribing antipyretics and analgesics.

[0566] In this way, the present invention is a system that reduces the burden on medical professionals in a virtual medical environment and enables efficient and accurate medical treatment.

[0567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0568] Step 1:

[0569] Recording and transmitting audio data

[0570] The terminal records the conversation between the patient and the doctor during the consultation. This voice data is input and the recorded voice data is sent to the server in real time. The specific operation of the terminal is to capture the voice through the microphone and transfer it to the server via the network.

[0571] Step 2:

[0572] Converting audio data to text

[0573] The server converts the received voice data into text data using voice recognition software such as the Google Speech Recognition API. The input in this process is the voice data, and the output is the corresponding text data. Specifically, the server calls the voice recognition API, analyzes the voice signal, and outputs the corresponding string of characters.

[0574] Step 3:

[0575] Extracting medical information from text data

[0576] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from text data. The input to this process is text data, and the output is the extracted medical information. Specifically, the server sends the prompt "Please extract medical information from the following text:" and the text data to the GPT-3 model, and receives the returned information as medical information.

[0577] Step 4:

[0578] Automatic recording of medical information in electronic medical records

[0579] The server automatically enters the extracted medical information into the electronic medical record template. In this step, the input is medical information and the output is an updated electronic medical record. Specifically, the server calls the API of the electronic medical record system and automatically enters the information into the corresponding fields in the medical record.

[0580] Step 5:

[0581] Automated recommendation and order fulfillment

[0582] The server predicts the diagnosis based on the medical information and recommends the necessary tests and treatments. After the user confirms and modifies the order, it automatically executes the order. The input is the extracted medical information and the order data modified by the user, and the output is the executed order. Specifically, the server uses the AI ​​model to predict the diagnosis, creates an appropriate order, and reflects it in the electronic medical record system and the testing institution's system.

[0583] Step 6:

[0584] Automatic generation of medical certificates

[0585] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record information. The input to this process is the details of the medical treatment and the medical record information, and the output is the generated medical certificate. Specifically, the server embeds the details of the medical treatment into a medical certificate template and generates the medical certificate in PDF format or other format.

[0586] Step 7:

[0587] Automating accounting processes

[0588] The server automatically calculates the billing amount based on the insurance information and medical details, and reflects this in the accounting system. The input for this step is the insurance information and medical details, and the output is the calculated billing amount. Specifically, the server collates the medical details with the insurance information, generates a bill, and sends the information to the accounting system.

[0589] Step 8:

[0590] Automatic summary generation for returning patients

[0591] The server analyzes past medical record information for returning patients and automatically generates a medical summary. The input to this process is past medical record information, and the output is the generated medical summary. Specifically, the server searches the medical record database and creates a summary based on the past medical history.

[0592] 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.

[0593] This invention is a system that highly automates administrative tasks in an electronic medical record system and improves medical treatment efficiency by recognizing and adapting to the user's emotions. This system is composed of a user, a terminal, and a server, and its specific operation and program processing are described below.

[0594] 1. Speech Recognition and Text Conversion

[0595] The device records the conversation between the doctor and the patient during the consultation. The audio data is designed to be recorded at high quality. The recorded audio data is sent to the server in real time. The server receives this audio data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0596] 2. Emotion recognition and information regulation

[0597] The device sends recorded voice data to the emotion engine, which recognizes the emotions of the user (doctor or patient). The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[0598] 3. Extraction of medical information and entry into electronic medical records

[0599] The server analyzes the text data using natural language processing (NLP) technology. As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[0600] 4. Automatic ordering of necessary tests and medications

[0601] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[0602] 5. Automatic generation of medical certificates

[0603] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[0604] 6. Automating accounting processes

[0605] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0606] 7. Automatic generation of summaries for returning patients

[0607] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[0608] Specific examples

[0609] For example, consider the case of a 40-year-old male patient who complains, "I haven't had a cough for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice into text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate support. For example, if the patient is feeling anxious, the system will display detailed explanations and help the doctor explain things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[0610] As described above, the present invention enables efficient operation of electronic medical record systems, minimizes administrative work for medical professionals, and provides a better medical environment by recognizing and adapting to user emotions.

[0611] The processing flow will be explained below.

[0612] Step 1:

[0613] The device records the conversation between the doctor and the patient during the consultation. The recording function is designed to capture high-quality audio data, which is then sent to the server in real time.

[0614] Step 2:

[0615] The device sends the recorded voice data to the emotion engine, which recognizes the emotions of the user and patient. The emotion engine analyzes the voice features and identifies emotions such as tension, anger, and joy.

[0616] Step 3:

[0617] The server inputs the received voice data into a speech recognition model and converts it into text data, which then contains the patient's complaint, symptoms, medical history, and other information contained in the conversation.

[0618] Step 4:

[0619] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[0620] Step 5:

[0621] The server automatically fills the extracted medical information into an electronic medical record template, adjusting the filling based on the emotional data identified from the emotion engine. For example, if the doctor is tired, a concise presentation of information is preferred.

[0622] Step 6:

[0623] The server identifies suspected diseases based on the analysis results and emotional data, and recommends necessary tests and treatments. If the patient is in a high state of anxiety, detailed explanations of the tests and treatments will be automatically displayed.

[0624] Step 7:

[0625] The user checks the recommended tests and medications and makes any necessary changes. Once the final order is confirmed, the server automatically executes the order and updates the relevant systems.

[0626] Step 8:

[0627] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The content and format of the certificate are adjusted based on data from the emotion engine. For example, if the patient is feeling anxious, advice on how to relieve stress is added.

[0628] Step 9:

[0629] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[0630] Step 10:

[0631] The device scans the patient's insurance card and sends the information to the server, where it is automatically updated in the system.

[0632] Step 11:

[0633] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[0634] Step 12:

[0635] The server analyzes past medical records and automatically creates a medical summary for returning patients. This summary can be used to provide treatment at the time of the return visit, making treatment more efficient.

[0636] Step 13:

[0637] The user reviews the automatically generated medical summary and corrects it if necessary, resulting in the final summary.

[0638] Example 2

[0639] 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."

[0640] In today's medical field, doctors and nurses are overwhelmed with a large amount of administrative work, which reduces the efficiency of medical treatment. It is also difficult to appropriately recognize and respond to patients' emotions, which affects patient satisfaction and the effectiveness of treatment. Furthermore, processing medical treatment details and insurance information is time-consuming, and past information cannot be efficiently utilized even during follow-up visits. This increases the burden on medical professionals and poses the issue of a decline in the quality of medical treatment.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0642] In this invention, the server includes means for converting voice data into text data, means for using natural language processing technology to extract medical information from the text data, and means for recognizing the user's emotions and adjusting the way information is displayed and the content of recommendations. This significantly automates the administrative work of doctors and nurses during medical treatment, and by appropriately recognizing and responding to patients' emotions, it improves the efficiency and quality of medical treatment, reduces the burden on medical professionals, and improves patient satisfaction.

[0643] "Users" are medical professionals such as doctors and nurses who use the system.

[0644] "Audio data" is digital information that is a recording of the conversation between the user and the patient.

[0645] "Text data" refers to voice data converted into text information.

[0646] An "electronic medical record" is a system for electronically recording and managing a patient's medical information.

[0647] "Natural language processing technology" refers to the general technology that enables computers to understand, analyze, and generate human language.

[0648] An "emotion engine" is software or algorithms that analyze and recognize the emotions of users or patients.

[0649] "Recommendation of tests and treatments" is a function in which the system suggests appropriate tests and treatments based on the analysis results.

[0650] A "medical certificate" is an official document that lists medical examination results and treatment plans.

[0651] "Insurance Information" refers to data relating to a patient's health insurance.

[0652] "Billed amount" is the total amount calculated based on the medical treatment.

[0653] A "medical summary" is summary information created based on past medical information.

[0654] The present invention is an electronic medical record system that significantly improves the efficiency of medical treatment in medical settings. This system is composed of a user, a terminal, and a server, and utilizes speech recognition, emotion recognition, natural language processing (NLP), and data analysis technologies in an integrated manner. Specific embodiments are described below.

[0655] Speech recognition and text conversion

[0656] The device records the conversation between the doctor and the patient during the consultation. The recording device is equipped with a high-quality microphone and dedicated recording software. The recorded audio data is sent to a server in real time. The server receives this audio data and converts it into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0657] Emotion recognition and information regulation

[0658] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[0659] Extraction of medical information and entry into electronic medical records

[0660] The server analyzes the text data using natural language processing (NLP) techniques (e.g., SpaCy or BERT). As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[0661] Automatic ordering of necessary tests and medications

[0662] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[0663] Automatic generation of medical certificates

[0664] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[0665] Automating accounting processes

[0666] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0667] Automatic summary generation for returning patients

[0668] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[0669] Specific examples

[0670] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate responses. For example, if the patient is feeling anxious, the system will display detailed explanations and support the patient in explaining things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[0671] Example of input prompt for generative AI model

[0672] Below is an example of an input prompt for the generative AI model based on the case of a 40-year-old male patient who complained of a persistent cough for the past few days and a high fever of 38 degrees Celsius since yesterday.

[0673] "A 40-year-old male patient has had a persistent cough for the past few days, and has had a high fever of 38 degrees since yesterday. Based on this information, please perform speech recognition, sentiment analysis, and natural language processing, record it in the electronic medical record, and generate a processing code that will recommend appropriate tests and treatments."

[0674] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0675] Step 1:

[0676] The user begins a consultation. The device records the conversation between the doctor and the patient in high-quality format. Specifically, a microphone installed in the examination room captures the audio, and the audio data is stored in the device. The input is the audio of the conversation between the doctor and the patient, and the output is the recorded audio data.

[0677] Step 2:

[0678] The device transmits the recorded audio data to the server in real time using a secure protocol over an internet connection. The input is the recorded audio data, and the output is the audio data transmitted to the server.

[0679] Step 3:

[0680] The server converts the received voice data into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). Specifically, the speech recognition algorithm analyzes the voice signal and converts it into text information. The input is the voice data sent to the server, and the output is text data.

[0681] Step 4:

[0682] The server analyzes the text data and uses natural language processing (NLP) techniques (e.g., SpaCy or BERT) to extract medical information such as the patient's chief complaint, symptoms, and medical history. The input is text data generated by speech recognition, and the output is the extracted medical information. Specifically, the NLP engine analyzes the text and identifies important medical information.

[0683] Step 5:

[0684] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The input is the recorded voice data, and the output is the recognized emotion data. Specifically, the emotion engine analyzes the voice data and identifies the user's emotional state.

[0685] Step 6:

[0686] The server analyzes the text data and emotion data and adjusts the extracted medical information and the content to be recorded in the electronic medical record. The input is text data and emotion data, and the output is adjusted medical information. Specifically, the system changes the way information is displayed and the recommended content based on the emotion data.

[0687] Step 7:

[0688] The server automatically enters the extracted medical information into an electronic medical record template. The input is the adjusted medical information, and the output is the data recorded in the electronic medical record. The specific operation is to embed the data into the template and complete the medical record.

[0689] Step 8:

[0690] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. The input is medical information recorded in the electronic medical record, and the output is the recommended tests and medications. Specifically, the diagnostic algorithm suggests the optimal tests and treatments.

[0691] Step 9:

[0692] The server automatically executes the order for the recommended tests and medications. The input is the recommended tests and medications, and the output is the executed test and treatment order. Specific operations include sending the necessary information to the ordering system.

[0693] Step 10:

[0694] The server automatically generates a medical certificate. The input is the data recorded in the electronic medical record and examination and treatment information, and the output is the completed medical certificate. Specifically, the data is embedded in a medical certificate template and an official medical certificate is generated.

[0695] Step 11:

[0696] The terminal scans the patient's insurance card and sends the information to the server. The input is the scanned data of the insurance card, and the output is the insurance information sent to the server. Specifically, the scanned image is converted into digital data and sent to the server.

[0697] Step 12:

[0698] The server automatically calculates the billing amount based on the insurance information and medical treatment details, and reflects this in the accounting system. The input is the medical treatment details and insurance information, and the output is the calculated billing amount. Specifically, the amount is calculated using the medical treatment details and insurance information, and registered in the accounting system.

[0699] Step 13:

[0700] The server analyzes past medical record information and automatically creates medical summaries for returning patients. The input is past medical record data, and the output is a medical summary for the returning patient. Specifically, the server analyzes the medical record data, extracts important medical information, and compiles it into a summary.

[0701] Step 14:

[0702] The user reviews the generated summary and corrects it if necessary. The input is the automatically generated medical summary, and the output is the reviewed and corrected summary. Specific operations involve the user viewing the summary and manually correcting any inaccuracies.

[0703] (Application example 2)

[0704] 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."

[0705] With conventional customer service systems, it is difficult for store staff to accurately understand customer feedback in real time and respond appropriately in an instant. Furthermore, while flexible responses based on customer emotions are required, there is a lack of means to achieve this. As a result, customer satisfaction declines and purchasing motivation decreases.

[0706] 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 means for recording the user's voice, means for converting voice data into text data, means for extracting information from the text data, means for automatically recording the extracted information in an electronic record, means for making necessary suggestions and recommendations, means for automatically implementing the recommended content, means for automatically creating a report, means for inputting transaction information and automatically calculating the billing amount based on the usage details, means for analyzing past information and automatically creating a summary of repeat users, and means for recognizing emotions from the user's voice and adjusting the response. This enables store clerks to accurately understand customer voices and respond appropriately and flexibly in real time according to their emotions.

[0707] "User" refers to the entity that uses the system, including store clerks and customers.

[0708] "Voice data" refers to digital audio signals recorded from users or customers.

[0709] "Text data" is voice data converted into character information.

[0710] "Information" refers to important content and elements extracted from the statements of users and customers.

[0711] An "electronic record" is a digital file or database that stores information extracted from audio data.

[0712] "Suggestions and recommendations" refer to appropriate products, services, and methods of response that the system presents based on the needs of the user or customer.

[0713] "Execution" refers to specific actions or operations that are carried out based on the proposed content.

[0714] A "report" is a document automatically created by the system that details the proposal and the results of its implementation.

[0715] "Transaction information" is detailed data relating to transactions with customers, including purchased items, quantities, amounts, etc.

[0716] "Amount Due" means the amount due calculated based on a Transaction.

[0717] "Historical information" refers to historical data stored in the system, such as previous transactions and records.

[0718] "Re-users" are customers or users who have used the system in the past and will use it again.

[0719] The "Summary" is a report document that briefly summarizes the past usage and transaction history of the repeat user.

[0720] "Emotion" refers to the emotional state or mood of a user or customer as recognized from their voice data.

[0721] "Adjustment" is the process of changing and optimizing suggestions and responses based on emotions.

[0722] This invention relates to a "smart customer service system" that improves the efficiency and quality of customer service in brick-and-mortar stores. The system analyzes conversations between users (store clerks) and customers in real time, and provides appropriate product suggestions and services based on the customer's emotions. This is realized by using "smart glasses."

[0723] Hardware and software used

[0724] Hardware:

[0725] Smart glasses (e.g. Google Glass)

[0726] server

[0727] software:

[0728] Speech recognition engine (e.g. Google Cloud Speech-to-Text)

[0729] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[0730] NLP engine (e.g. OpenAI GPT-3)

[0731] Database (e.g. MySQL)

[0732] Data processing and calculation flow

[0733] 1. Speech recognition and text conversion:

[0734] The smart glasses record conversations between store clerks and customers in real time, and the recorded data is sent from the smart glasses to a server where it is converted into text using a voice recognition engine.

[0735] 2. Emotion recognition and information regulation:

[0736] The server passes the text data to an emotion recognition engine to analyze the customer's emotions (e.g., desire, anxiety, interest). This emotion data is used to tailor suggestions and recommendations.

[0737] 3. Appropriate product recommendations:

[0738] As part of its task, the server uses an NLP engine to extract customer intent and requests from the text data, and based on this, it searches for the most suitable product and service information from a database and displays the selected product information on the smart glasses in real time.

[0739] 4. Real-time feedback:

[0740] By combining customer sentiment data with product suggestions, the smart glasses display the most appropriate suggestions and explanations to the salesperson. For example, if a customer shows interest, the smart glasses will provide detailed information about the latest popular products.

[0741] Specific examples

[0742] Consider a scenario in which a store clerk wearing smart glasses is having a conversation with a customer. For example, if the customer says, "I want to know about the latest popular products," the following sequence of events will take place.

[0743] 1. The voice recognition engine converts the customer's speech into text data.

[0744] 2. The emotion recognition engine analyzes the customer's emotions and determines that they are highly interested.

[0745] 3. The NLP engine extracts the latest popular product information from the database.

[0746] 4. The extracted information is displayed on the smart glasses, allowing the store clerk to introduce the latest products.

[0747] Prompt Sentence Examples

[0748] An example of a prompt is shown below.

[0749] The customer seems interested in the latest popular products. His words and facial expressions suggest curiosity and interest. Introduce the latest popular products and explain their features and recommended points. Adjust your speaking style and tempo according to the customer's emotions.

[0750] This system allows for flexible responses tailored to customer emotions, which is expected to improve customer satisfaction and promote sales.

[0751] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0752] Step 1: Record the user's voice

[0753] The smart glasses record conversations between store clerks and customers in real time. The recorded data (audio data) is stored in the smart glasses. The user's conversation data is input and output as audio data.

[0754] Step 2: Send the audio data to the server

[0755] The audio data recorded on the device is sent from the smart glasses to the server in real time. The input is the audio data, and the output is the audio data sent to the server.

[0756] Step 3: Convert audio data to text data

[0757] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). At this time, voice data is taken as input and output as text data.

[0758] Step 4: Send the text data to the emotion recognition engine

[0759] The server then sends the converted text data to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the customer's emotions. The input is text data, and the output is emotion data.

[0760] Step 5: Integrate emotion data and text data

[0761] The server integrates the emotional data and text data to generate data corresponding to the customer's emotional state. As a result, the input is text data and emotional data, and the output is the integrated data.

[0762] Step 6: Extract information with an NLP engine

[0763] The server sends the integrated data to an NLP engine (e.g., OpenAI GPT-3) to extract the necessary information from what the customer said. This process takes the integrated data as input and produces the extracted information as output.

[0764] Step 7: Product recommendations based on extracted information

[0765] The server accesses a database (e.g. MySQL) and searches for the appropriate product data based on the extracted information. The input is the extracted information and the output is the product data.

[0766] Step 8: Submit your product data

[0767] The server sends the searched product data to the smart glasses, and the salesperson makes a suggestion to the customer. The input is the product data, and the output is the display data on the smart glasses.

[0768] Step 9: Real-time feedback

[0769] The smart glasses display the proposed product information to the salesperson in real time, helping them to respond to the customer. The salesperson then looks at the displayed data and provides a detailed explanation of the product to the customer. The input is product data, and the output is display data.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] [Third embodiment]

[0774] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0775] 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.

[0776] 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).

[0777] 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.

[0778] 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.

[0779] 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).

[0780] 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. 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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."

[0786] This invention is a system for automating administrative tasks in an electronic medical record system to reduce the burden on medical professionals. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[0787] 1. Speech Recognition and Text Conversion

[0788] The device records the conversation between the doctor and the patient during the consultation. This recorded voice data is sent in real time to a server. The server receives this voice data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0789] 2. Extraction of medical information and entry into electronic medical records

[0790] The server analyzes the text data and extracts medical information from it. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter information into the medical record.

[0791] 3. Automatic ordering of necessary tests and medications

[0792] The server identifies suspected diseases based on the extracted medical information and uses an AI model to recommend necessary tests and medications. For example, if a patient complains of a cough and fever, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication. The user can review this, make any necessary corrections, and finally confirm the order. The server then automatically executes the confirmed order and updates the relevant systems.

[0793] 4. Automatic generation of medical certificates

[0794] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, etc. The user can check the certificate and make corrections as necessary, significantly reducing the effort required to create the certificate.

[0795] 5. Automated accounting

[0796] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0797] 6. Automatic generation of summaries for returning patients

[0798] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[0799] Specific examples

[0800] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test, and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user reviews and completes. Through this series of processes, the user can complete many administrative tasks without any hassle.

[0801] As described above, the present invention enables efficient operation of an electronic medical record system and provides specific means for reducing the administrative work of medical personnel as much as possible.

[0802] The processing flow will be explained below.

[0803] Step 1:

[0804] The device records the conversation between the doctor and the patient during the consultation, and is designed to record high-quality audio data.

[0805] Step 2:

[0806] The device sends the recorded audio data to the server in real time, and the communication is encrypted to ensure security.

[0807] Step 3:

[0808] The server inputs the received voice data into a speech recognition model that is specifically trained to accurately recognize medical terminology and converts it into text.

[0809] Step 4:

[0810] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[0811] Step 5:

[0812] The server automatically records the extracted medical information in the electronic medical record, entering the information according to pre-defined templates.

[0813] Step 6:

[0814] The server identifies suspected illnesses based on the analysis results and recommends necessary tests and medications. For example, in the case of a cough and fever, it would recommend a chest X-ray, blood tests, and antipyretic and analgesic medications.

[0815] Step 7:

[0816] The user checks the recommendations and makes any necessary corrections. The server automatically orders the confirmed tests and medications, and the results are reflected in the electronic medical records and testing system.

[0817] Step 8:

[0818] The server automatically generates a medical report that includes the patient's symptoms, diagnosis, and recommended treatment.

[0819] Step 9:

[0820] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[0821] Step 10:

[0822] The terminal scans the patient's insurance card and reads the insurance information.

[0823] Step 11:

[0824] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[0825] Step 12:

[0826] The server analyzes past medical records and automatically creates a medical summary for returning patients. When a patient returns to the hospital, treatment is based on this summary.

[0827] Step 13:

[0828] The user reviews and corrects the automatically generated medical summary and completes the final summary.

[0829] Example 1

[0830] 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."

[0831] Medical institutions face a problem of a heavy administrative burden related to medical treatment and diagnosis, preventing medical professionals from concentrating on their primary medical activities. In particular, tasks such as filling out medical records, creating medical certificates, and processing insurance claims are time-consuming and labor-intensive, requiring efficient operations. It is also difficult to quickly grasp past medical information for returning patients and determine the necessary tests and medications. To solve these issues, a system that highly automates administrative tasks and reduces the burden on medical professionals is needed.

[0832] 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.

[0833] In this invention, the server includes means for recording a user's voice, means for converting voice data into text data, means for extracting medical information from the text data, means for automatically recording the extracted medical information in a record, means for recommending suspected diseases and necessary tests and medications, means for automatically executing instructions for the recommended tests and medications, means for automatically generating reports, means for inputting insurance information and automatically calculating billing amounts based on the medical treatment details, means for analyzing past medical information and automatically creating medical summaries for returning patients, means for transmitting voice data to the server in real time, means for analyzing text data using natural language processing technology, means for generating recommendations using an AI model, and means for extracting text data from image data using OCR technology. This automates administrative tasks such as filling out medical charts, creating medical certificates, and processing insurance claims, enabling medical professionals to focus on their medical activities.

[0834] "User" refers to the medical professional or doctor in charge of medical treatment.

[0835] "Audio data" refers to data in which audio is recorded in digital format.

[0836] "Text data" refers to data that includes character information converted from audio data.

[0837] "Medical information" refers to information about a patient's chief complaint, symptoms, medical history, and diagnosis.

[0838] "Record" refers to documents containing patient medical information, such as electronic medical records and medical notes.

[0839] "Suspected disease" refers to a potential disease that is suspected based on medical information.

[0840] "Test" means a medical procedure to confirm or diagnose a suspected illness.

[0841] "Medication" means a medicine prescribed for medical treatment.

[0842] "Recommendation" refers to proposing optimal testing and treatment options derived from AI models, etc.

[0843] "Instructions" refer to medical procedures that are ultimately approved by the user.

[0844] A "report" refers to a document that summarizes diagnostic results, treatment plans, etc.

[0845] "Insurance Information" refers to information regarding a patient's health insurance.

[0846] "Billed amount" refers to the amount of medical expenses calculated based on the medical treatment.

[0847] "Medical summary" refers to a summary document that compiles past medical information for returning patients.

[0848] A "server" refers to a computer system that analyzes voice data and manages medical information.

[0849] "Natural language processing technology" is a technology for analyzing text data and is used to extract useful information from text data.

[0850] "AI model" refers to a predictive model built using machine learning algorithms.

[0851] "OCR technology" is a technology that optically reads character information and converts it into digital data.

[0852] This invention relates to an electronic medical record system that automates administrative tasks in medical institutions to reduce the burden on medical staff. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[0853] Speech recognition and text conversion

[0854] The device records the conversation between the doctor and the patient during the consultation. The recorded audio data is sent to a server in real time. The server then converts the audio data into text using a speech recognition model such as Google Cloud Speech-to-Text or IBM Watson Speech to Text. The converted text data includes information such as the patient's chief complaint, symptoms, and medical history.

[0855] Extraction of medical information and entry into electronic medical records

[0856] The server uses natural language processing (NLP) technology to analyze the text data and extract medical information from it. Software such as SpaCy and Stanford NLP are used. The extracted medical information is automatically entered into an electronic medical record template and stored in an SQL database.

[0857] Automatic ordering of necessary tests and medications

[0858] The server uses the extracted medical information to make inferences to identify suspected illnesses. AI models built with TensorFlow and PyTorch are used for inference. For example, if a patient complains of a cough and fever, the server recommends a chest X-ray, blood tests, and prescriptions for antipyretics and analgesics. The user can review these recommendations and make corrections as necessary. Once the final order is confirmed, the server updates the relevant systems and automatically executes it.

[0859] Automatic generation of medical certificates

[0860] The server automatically generates a medical certificate using a medical certificate template based on the details of the examination and the patient's medical record. The medical certificate includes the patient's symptoms, diagnosis, and recommended treatment. The user can review the medical certificate and make any necessary corrections.

[0861] Automating accounting processes

[0862] The terminal scans the patient's insurance card and sends the information to the server. The server extracts the insurance information using OCR technology (e.g., Tesseract OCR). The server then automatically calculates the billing amount based on the insurance information and the medical treatment details, and automatically updates the accounting system. Finally, a bill is issued to the patient.

[0863] Automatic summary generation for returning patients

[0864] The server analyzes the past medical records of returning patients and automatically generates a medical summary that will be useful for the next visit. The user can then check the summary and make any necessary corrections.

[0865] Specific examples

[0866] Consider the case of a 40-year-old male patient who complains of a persistent cough for the past few days and a high fever of 38 degrees since yesterday. In this case, the device records the conversation, and the server converts the audio into text using Google Cloud Speech-to-Text. The converted text is analyzed using SpaCy to extract the patient's symptom information. Based on the extracted information, the server recommends a chest X-ray and blood tests, and suggests a prescription for antipyretic and analgesic medication. Once the user confirms the order, the server automatically generates a medical certificate, which is ultimately saved and distributed in PDF format.

[0867] Prompt Sentence Examples

[0868] The following prompt sentence can be input into the generative AI model to automatically generate medical documents:

[0869] A 40-year-old male patient comes to the clinic complaining, "I've had a cough that hasn't stopped for the past few days. I've had a high fever of 38 degrees since yesterday." Based on the consultation, please write about the patient's symptoms, the recommended tests, and the prescribed medications.

[0870] These procedures allow users to efficiently complete many administrative tasks without any hassle.

[0871] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0872] Step 1:

[0873] The device records the conversation between the doctor and the patient during the consultation. The device's microphone is used to collect the conversation audio in WAV file format and save it as a file. The input is the conversation audio during the consultation, and the output is the recorded WAV file.

[0874] Step 2:

[0875] The device transmits the recorded audio data to the server in real time. The saved WAV file is uploaded to the server using the HTTP protocol. The input is the WAV file, and the output is the audio data transferred to the server.

[0876] Step 3:

[0877] The server calls the Google Cloud Speech-to-Text API to convert the received voice data into text data. It sends an API request and performs speech analysis. The input is the voice data, and the output is the converted text data.

[0878] Step 4:

[0879] The server analyzes the text data using natural language processing (NLP) technology. The software used is SpaCy or Stanford NLP. Important keywords (e.g., fever, cough, etc.) are extracted from the text data. The input is the text data, and the output is JSON data containing the extracted medical information.

[0880] Step 5:

[0881] The server stores the extracted medical information in an SQL database and automatically records it in an electronic medical record template. The input is medical information in JSON format, and the output is the information automatically recorded in the electronic medical record.

[0882] Step 6:

[0883] The server uses an AI model (using TensorFlow or PyTorch) to identify suspected diseases based on the extracted information and recommend necessary tests and treatments. Input data is provided to the AI ​​model, and an inference result is obtained. The input is medical information, and the output is a list of recommended tests and treatments.

[0884] Step 7:

[0885] The user reviews the recommended tests and medications on the web interface, makes any necessary modifications, and clicks a button on the UI to confirm the final order. The input is the recommendations and any modifications made by the user, and the output is the confirmed order.

[0886] Step 8:

[0887] The server sends the confirmed order in HL7 message format to the related systems (test order system, medication management system) and executes it automatically. The input is the confirmed order data, and the output is the order message sent to the related systems.

[0888] Step 9:

[0889] The server automatically generates a medical certificate using a LaTeX template based on the information in the medical record. The generated medical certificate is saved in PDF format and a download link is provided to the user. The input is the medical record information, and the output is a medical certificate in PDF format.

[0890] Step 10:

[0891] The terminal uses a scanner to scan the patient's insurance card and generate an image file. The input is the actual insurance card, and the output is the scanned image file.

[0892] Step 11:

[0893] The device sends the image file to the server and converts it into text data using OCR technology (using Tesseract OCR). The input is the scanned image file, and the output is text data containing insurance information.

[0894] Step 12:

[0895] The server automatically calculates the billing amount based on the insurance information and medical information using a rule engine (such as Drools). The input is the insurance information and medical information, and the output is the calculated billing amount.

[0896] Step 13:

[0897] The server updates the calculated billing amount to an accounting system such as SAP, generates a PDF invoice, and emails it to the patient. The input is the calculated billing amount, and the output is the PDF invoice sent.

[0898] Step 14:

[0899] The server analyzes the past medical records of returning patients and processes the data on a Hadoop cluster to extract key medical information. The input is the past medical records, and the output is the extracted medical information.

[0900] Step 15:

[0901] The server automatically generates a medical summary of the returning patient in Markdown format based on the extracted information. The input is the extracted medical information, and the output is the generated medical summary.

[0902] Step 16:

[0903] The user can check the generated medical summary through the web interface, and modify and save it as necessary. The input is the generated medical summary, and the output is the finalized medical summary.

[0904] (Application example 1)

[0905] 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."

[0906] In today's medical field, the administrative work involved in managing electronic medical records and creating medical records is increasing, placing a heavy burden on medical professionals. Providing appropriate diagnoses and treatments requires fast and accurate information entry and analysis, but doing this manually is inefficient and carries the risk of errors. Furthermore, with the spread of online medical consultations, a similarly efficient management system is required for consultations from remote locations. A system is needed to solve these issues and improve efficiency in the medical field.

[0907] 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.

[0908] In this invention, the server includes a means for converting voice data into text data, a means for extracting information from the text data, and a means for automatically recording the extracted information in a recording system. This allows voice data recorded during medical treatment to be converted into text data in real time, and necessary medical information can be quickly extracted. The extracted information is automatically recorded in an electronic medical record, and appropriate diagnoses and treatment recommendations are provided, significantly reducing administrative work in medical settings. Furthermore, past records are analyzed and information is automatically generated during follow-up visits, improving the efficiency of medical treatment. Furthermore, information analysis is possible via an external API, and the results are reflected in medical certificates and other record documents, enabling more accurate medical treatment.

[0909] "Audio data" refers to data in which an audio signal is recorded in digital format.

[0910] "Text data" refers to data in which character information is recorded in digital format.

[0911] "Information extraction" is the process of selecting necessary information from data based on a specific purpose.

[0912] A "system of record" is a computer system for storing and managing data.

[0913] A "disease" is a state of deviation from the normal physiological function of an organism, or a pathological process leading to that state.

[0914] A "test" is a method or procedure for making a medically necessary diagnosis or evaluation.

[0915] A "therapeutic procedure" is a method for treating, improving, or alleviating a specific disease or disorder.

[0916] A "recommendation" is a suggestion or recommendation based on specific conditions.

[0917] An "external API" is a mechanism that allows programs to exchange data and functions using interfaces provided by external applications and services.

[0918] "Analysis" is the process of examining data in detail to understand and evaluate its structure and content.

[0919] A "medical certificate" is an official document that lists the diagnosis and treatment plan.

[0920] "Insurance Information" means data and records relating to health insurance.

[0921] "Amount Due" means the amount due for services or goods.

[0922] A "revisit" is a consultation for additional treatment or evaluation after the initial visit.

[0923] The present invention provides a system for supporting the work of medical professionals in a virtual medical environment. This system converts voice data into text data, extracts medical information from the text data, and automatically creates various recommendations and records. Specific embodiments of the system are described below.

[0924] Speech recognition and text conversion

[0925] The conversation between the patient and doctor during the consultation is recorded using a device such as a smartphone or head-mounted display. The recorded voice data is sent to a server in real time. The server then uses voice recognition software (e.g., Google Speech Recognition API) to convert this voice data into text data. Through this process, the patient's chief complaint, symptoms, medical history, etc. are recorded in text format.

[0926] Extraction of medical information and entry into electronic medical records

[0927] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from the converted text data. This extraction includes information provided by the patient and treatment details provided by the doctor. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter medical records.

[0928] Automated Recommendations and Ordering

[0929] The server estimates the diagnosis based on the extracted medical information and recommends the necessary tests and treatments. The recommended tests and treatments are then automatically ordered after the user confirms and modifies them as necessary. For example, if a patient complains of a persistent cough and high fever for the past few days, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication.

[0930] Automated medical certificate and accounting procedures

[0931] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The user can review the certificate and make corrections as necessary, reducing the effort required to create the certificate. The server also automatically calculates the billing amount based on the patient's insurance information and details of the treatment, and updates the accounting system. The calculated billing amount is then issued to the patient.

[0932] Automatic summary generation for returning patients

[0933] The server analyzes past medical records and automatically generates medical summaries for returning patients. By providing medical treatment based on these summaries, users can improve their work efficiency. For example, if a patient who was previously diagnosed with pneumonia returns for a follow-up visit, a summary of their past treatment history, medication prescription history, and other information is automatically generated, allowing users to easily check it.

[0934] Examples and prompts

[0935] A specific example would be a case where a 40-year-old male patient complains, "I haven't had a cough for several days and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user confirms and completes.

[0936] An example of a prompt to input to a generative AI model is as follows:

[0937] Extract medical information from the following text:

[0938] A 40-year-old male patient has had a persistent cough for the past few days and has had a high fever of 38 degrees since yesterday. A chest X-ray will be performed and we are considering prescribing antipyretics and analgesics.

[0939] In this way, the present invention is a system that reduces the burden on medical professionals in a virtual medical environment and enables efficient and accurate medical treatment.

[0940] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0941] Step 1:

[0942] Recording and transmitting audio data

[0943] The terminal records the conversation between the patient and the doctor during the consultation. This voice data is input and the recorded voice data is sent to the server in real time. The specific operation of the terminal is to capture the voice through the microphone and transfer it to the server via the network.

[0944] Step 2:

[0945] Converting audio data to text

[0946] The server converts the received voice data into text data using voice recognition software such as the Google Speech Recognition API. The input in this process is the voice data, and the output is the corresponding text data. Specifically, the server calls the voice recognition API, analyzes the voice signal, and outputs the corresponding string of characters.

[0947] Step 3:

[0948] Extracting medical information from text data

[0949] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from text data. The input to this process is text data, and the output is the extracted medical information. Specifically, the server sends the prompt "Please extract medical information from the following text:" and the text data to the GPT-3 model, and receives the returned information as medical information.

[0950] Step 4:

[0951] Automatic recording of medical information in electronic medical records

[0952] The server automatically enters the extracted medical information into the electronic medical record template. In this step, the input is medical information and the output is an updated electronic medical record. Specifically, the server calls the API of the electronic medical record system and automatically enters the information into the corresponding fields in the medical record.

[0953] Step 5:

[0954] Automated recommendation and order fulfillment

[0955] The server predicts the diagnosis based on the medical information and recommends the necessary tests and treatments. After the user confirms and modifies the order, it automatically executes the order. The input is the extracted medical information and the order data modified by the user, and the output is the executed order. Specifically, the server uses the AI ​​model to predict the diagnosis, creates an appropriate order, and reflects it in the electronic medical record system and the testing institution's system.

[0956] Step 6:

[0957] Automatic generation of medical certificates

[0958] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record information. The input to this process is the details of the medical treatment and the medical record information, and the output is the generated medical certificate. Specifically, the server embeds the details of the medical treatment into a medical certificate template and generates the medical certificate in PDF format or other format.

[0959] Step 7:

[0960] Automating accounting processes

[0961] The server automatically calculates the billing amount based on the insurance information and medical details, and reflects this in the accounting system. The input for this step is the insurance information and medical details, and the output is the calculated billing amount. Specifically, the server collates the medical details with the insurance information, generates a bill, and sends the information to the accounting system.

[0962] Step 8:

[0963] Automatic summary generation for returning patients

[0964] The server analyzes past medical record information for returning patients and automatically generates a medical summary. The input to this process is past medical record information, and the output is the generated medical summary. Specifically, the server searches the medical record database and creates a summary based on the past medical history.

[0965] 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.

[0966] This invention is a system that highly automates administrative tasks in an electronic medical record system and improves medical treatment efficiency by recognizing and adapting to the user's emotions. This system is composed of a user, a terminal, and a server, and its specific operation and program processing are described below.

[0967] 1. Speech Recognition and Text Conversion

[0968] The device records the conversation between the doctor and the patient during the consultation. The audio data is designed to be recorded at high quality. The recorded audio data is sent to the server in real time. The server receives this audio data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[0969] 2. Emotion recognition and information regulation

[0970] The device sends recorded voice data to the emotion engine, which recognizes the emotions of the user (doctor or patient). The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[0971] 3. Extraction of medical information and entry into electronic medical records

[0972] The server analyzes the text data using natural language processing (NLP) technology. As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[0973] 4. Automatic ordering of necessary tests and medications

[0974] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[0975] 5. Automatic generation of medical certificates

[0976] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[0977] 6. Automating accounting processes

[0978] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[0979] 7. Automatic generation of summaries for returning patients

[0980] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[0981] Specific examples

[0982] For example, consider the case of a 40-year-old male patient who complains, "I haven't had a cough for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice into text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate support. For example, if the patient is feeling anxious, the system will display detailed explanations and help the doctor explain things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[0983] As described above, the present invention enables efficient operation of electronic medical record systems, minimizes administrative work for medical professionals, and provides a better medical environment by recognizing and adapting to user emotions.

[0984] The processing flow will be explained below.

[0985] Step 1:

[0986] The device records the conversation between the doctor and the patient during the consultation. The recording function is designed to capture high-quality audio data, which is then sent to the server in real time.

[0987] Step 2:

[0988] The device sends the recorded voice data to the emotion engine, which recognizes the emotions of the user and patient. The emotion engine analyzes the voice features and identifies emotions such as tension, anger, and joy.

[0989] Step 3:

[0990] The server inputs the received voice data into a speech recognition model and converts it into text data, which then contains the patient's complaint, symptoms, medical history, and other information contained in the conversation.

[0991] Step 4:

[0992] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[0993] Step 5:

[0994] The server automatically fills the extracted medical information into an electronic medical record template, adjusting the filling based on the emotional data identified from the emotion engine. For example, if the doctor is tired, a concise presentation of information is preferred.

[0995] Step 6:

[0996] The server identifies suspected diseases based on the analysis results and emotional data, and recommends necessary tests and treatments. If the patient is in a high state of anxiety, detailed explanations of the tests and treatments will be automatically displayed.

[0997] Step 7:

[0998] The user checks the recommended tests and medications and makes any necessary changes. Once the final order is confirmed, the server automatically executes the order and updates the relevant systems.

[0999] Step 8:

[1000] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The content and format of the certificate are adjusted based on data from the emotion engine. For example, if the patient is feeling anxious, advice on how to relieve stress is added.

[1001] Step 9:

[1002] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[1003] Step 10:

[1004] The device scans the patient's insurance card and sends the information to the server, where it is automatically updated in the system.

[1005] Step 11:

[1006] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[1007] Step 12:

[1008] The server analyzes past medical records and automatically creates a medical summary for returning patients. This summary can be used to provide treatment at the time of the return visit, making treatment more efficient.

[1009] Step 13:

[1010] The user reviews the automatically generated medical summary and corrects it if necessary, resulting in the final summary.

[1011] Example 2

[1012] 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."

[1013] In today's medical field, doctors and nurses are overwhelmed with a large amount of administrative work, which reduces the efficiency of medical treatment. It is also difficult to appropriately recognize and respond to patients' emotions, which affects patient satisfaction and the effectiveness of treatment. Furthermore, processing medical treatment details and insurance information is time-consuming, and past information cannot be efficiently utilized even during follow-up visits. This increases the burden on medical professionals and poses the issue of a decline in the quality of medical treatment.

[1014] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1015] In this invention, the server includes means for converting voice data into text data, means for using natural language processing technology to extract medical information from the text data, and means for recognizing the user's emotions and adjusting the way information is displayed and the content of recommendations. This significantly automates the administrative work of doctors and nurses during medical treatment, and by appropriately recognizing and responding to patients' emotions, it improves the efficiency and quality of medical treatment, reduces the burden on medical professionals, and improves patient satisfaction.

[1016] "Users" are medical professionals such as doctors and nurses who use the system.

[1017] "Audio data" is digital information that is a recording of the conversation between the user and the patient.

[1018] "Text data" refers to voice data converted into text information.

[1019] An "electronic medical record" is a system for electronically recording and managing a patient's medical information.

[1020] "Natural language processing technology" refers to the general technology that enables computers to understand, analyze, and generate human language.

[1021] An "emotion engine" is software or algorithms that analyze and recognize the emotions of users or patients.

[1022] "Recommendation of tests and treatments" is a function in which the system suggests appropriate tests and treatments based on the analysis results.

[1023] A "medical certificate" is an official document that lists medical examination results and treatment plans.

[1024] "Insurance Information" refers to data relating to a patient's health insurance.

[1025] "Billed amount" is the total amount calculated based on the medical treatment.

[1026] A "medical summary" is summary information created based on past medical information.

[1027] The present invention is an electronic medical record system that significantly improves the efficiency of medical treatment in medical settings. This system is composed of a user, a terminal, and a server, and utilizes speech recognition, emotion recognition, natural language processing (NLP), and data analysis technologies in an integrated manner. Specific embodiments are described below.

[1028] Speech recognition and text conversion

[1029] The device records the conversation between the doctor and the patient during the consultation. The recording device is equipped with a high-quality microphone and dedicated recording software. The recorded audio data is sent to a server in real time. The server receives this audio data and converts it into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). The text data includes the patient's chief complaint, symptoms, medical history, etc.

[1030] Emotion recognition and information regulation

[1031] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[1032] Extraction of medical information and entry into electronic medical records

[1033] The server analyzes the text data using natural language processing (NLP) techniques (e.g., SpaCy or BERT). As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[1034] Automatic ordering of necessary tests and medications

[1035] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[1036] Automatic generation of medical certificates

[1037] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[1038] Automating accounting processes

[1039] The device scans the patient's insurance card and sends the information to the server, which then automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[1040] Automatic summary generation for returning patients

[1041] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing medical treatment based on this summary during the return visit, the user's work efficiency is improved. The user can then review the summary and make any necessary corrections.

[1042] Specific examples

[1043] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate responses. For example, if the patient is feeling anxious, the system will display detailed explanations and support the patient in explaining things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[1044] Example of input prompt for generative AI model

[1045] Below is an example of an input prompt for the generative AI model based on the case of a 40-year-old male patient who complained of a persistent cough for the past few days and a high fever of 38 degrees Celsius since yesterday.

[1046] "A 40-year-old male patient has had a persistent cough for the past few days, and has had a high fever of 38 degrees since yesterday. Based on this information, please perform speech recognition, sentiment analysis, and natural language processing, record it in the electronic medical record, and generate a processing code that will recommend appropriate tests and treatments."

[1047] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1048] Step 1:

[1049] The user begins a consultation. The device records the conversation between the doctor and the patient in high-quality format. Specifically, a microphone installed in the examination room captures the audio, and the audio data is stored in the device. The input is the audio of the conversation between the doctor and the patient, and the output is the recorded audio data.

[1050] Step 2:

[1051] The device transmits the recorded audio data to the server in real time using a secure protocol over an internet connection. The input is the recorded audio data, and the output is the audio data transmitted to the server.

[1052] Step 3:

[1053] The server converts the received voice data into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). Specifically, the speech recognition algorithm analyzes the voice signal and converts it into text information. The input is the voice data sent to the server, and the output is text data.

[1054] Step 4:

[1055] The server analyzes the text data and uses natural language processing (NLP) techniques (e.g., SpaCy or BERT) to extract medical information such as the patient's chief complaint, symptoms, and medical history. The input is text data generated by speech recognition, and the output is the extracted medical information. Specifically, the NLP engine analyzes the text and identifies important medical information.

[1056] Step 5:

[1057] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The input is the recorded voice data, and the output is the recognized emotion data. Specifically, the emotion engine analyzes the voice data and identifies the user's emotional state.

[1058] Step 6:

[1059] The server analyzes the text data and emotion data and adjusts the extracted medical information and the content to be recorded in the electronic medical record. The input is text data and emotion data, and the output is adjusted medical information. Specifically, the system changes the way information is displayed and the recommended content based on the emotion data.

[1060] Step 7:

[1061] The server automatically enters the extracted medical information into an electronic medical record template. The input is the adjusted medical information, and the output is the data recorded in the electronic medical record. The specific operation is to embed the data into the template and complete the medical record.

[1062] Step 8:

[1063] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. The input is medical information recorded in the electronic medical record, and the output is the recommended tests and medications. Specifically, the diagnostic algorithm suggests the optimal tests and treatments.

[1064] Step 9:

[1065] The server automatically executes the order for the recommended tests and medications. The input is the recommended tests and medications, and the output is the executed test and treatment order. Specific operations include sending the necessary information to the ordering system.

[1066] Step 10:

[1067] The server automatically generates a medical certificate. The input is the data recorded in the electronic medical record and examination and treatment information, and the output is the completed medical certificate. Specifically, the data is embedded in a medical certificate template and an official medical certificate is generated.

[1068] Step 11:

[1069] The terminal scans the patient's insurance card and sends the information to the server. The input is the scanned data of the insurance card, and the output is the insurance information sent to the server. Specifically, the scanned image is converted into digital data and sent to the server.

[1070] Step 12:

[1071] The server automatically calculates the billing amount based on the insurance information and medical treatment details, and reflects this in the accounting system. The input is the medical treatment details and insurance information, and the output is the calculated billing amount. Specifically, the amount is calculated using the medical treatment details and insurance information, and registered in the accounting system.

[1072] Step 13:

[1073] The server analyzes past medical record information and automatically creates medical summaries for returning patients. The input is past medical record data, and the output is a medical summary for the returning patient. Specifically, the server analyzes the medical record data, extracts important medical information, and compiles it into a summary.

[1074] Step 14:

[1075] The user reviews the generated summary and corrects it if necessary. The input is the automatically generated medical summary, and the output is the reviewed and corrected summary. Specific operations involve the user viewing the summary and manually correcting any inaccuracies.

[1076] (Application example 2)

[1077] 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."

[1078] With conventional customer service systems, it is difficult for store staff to accurately understand customer feedback in real time and respond appropriately in an instant. Furthermore, while flexible responses based on customer emotions are required, there is a lack of means to achieve this. As a result, customer satisfaction declines and purchasing motivation decreases.

[1079] 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 means for recording the user's voice, means for converting voice data into text data, means for extracting information from the text data, means for automatically recording the extracted information in an electronic record, means for making necessary suggestions and recommendations, means for automatically implementing the recommended content, means for automatically creating a report, means for inputting transaction information and automatically calculating the billing amount based on the usage details, means for analyzing past information and automatically creating a summary of repeat users, and means for recognizing emotions from the user's voice and adjusting the response. This enables store clerks to accurately understand customer voices and respond appropriately and flexibly in real time according to their emotions.

[1080] "User" refers to the entity that uses the system, including store clerks and customers.

[1081] "Voice data" refers to digital audio signals recorded from users or customers.

[1082] "Text data" is voice data converted into character information.

[1083] "Information" refers to important content and elements extracted from the statements of users and customers.

[1084] An "electronic record" is a digital file or database that stores information extracted from audio data.

[1085] "Suggestions and recommendations" refer to appropriate products, services, and methods of response that the system presents based on the needs of the user or customer.

[1086] "Execution" refers to specific actions or operations that are carried out based on the proposed content.

[1087] A "report" is a document automatically created by the system that details the proposal and the results of its implementation.

[1088] "Transaction information" is detailed data relating to transactions with customers, including purchased items, quantities, amounts, etc.

[1089] "Amount Due" means the amount due calculated based on a Transaction.

[1090] "Historical information" refers to historical data stored in the system, such as previous transactions and records.

[1091] "Re-users" are customers or users who have used the system in the past and will use it again.

[1092] The "Summary" is a report document that briefly summarizes the past usage and transaction history of the repeat user.

[1093] "Emotion" refers to the emotional state or mood of a user or customer as recognized from their voice data.

[1094] "Adjustment" is the process of changing and optimizing suggestions and responses based on emotions.

[1095] This invention relates to a "smart customer service system" that improves the efficiency and quality of customer service in brick-and-mortar stores. The system analyzes conversations between users (store clerks) and customers in real time, and provides appropriate product suggestions and services based on the customer's emotions. This is realized by using "smart glasses."

[1096] Hardware and software used

[1097] Hardware:

[1098] Smart glasses (e.g. Google Glass)

[1099] server

[1100] software:

[1101] Speech recognition engine (e.g. Google Cloud Speech-to-Text)

[1102] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[1103] NLP engine (e.g. OpenAI GPT-3)

[1104] Database (e.g. MySQL)

[1105] Data processing and calculation flow

[1106] 1. Speech recognition and text conversion:

[1107] The smart glasses record conversations between store clerks and customers in real time, and the recorded data is sent from the smart glasses to a server where it is converted into text using a voice recognition engine.

[1108] 2. Emotion recognition and information regulation:

[1109] The server passes the text data to an emotion recognition engine to analyze the customer's emotions (e.g., desire, anxiety, interest). This emotion data is used to tailor suggestions and recommendations.

[1110] 3. Appropriate product recommendations:

[1111] As part of its task, the server uses an NLP engine to extract customer intent and requests from the text data, and based on this, it searches for the most suitable product and service information from a database and displays the selected product information on the smart glasses in real time.

[1112] 4. Real-time feedback:

[1113] By combining customer sentiment data with product suggestions, the smart glasses display the most appropriate suggestions and explanations to the salesperson. For example, if a customer shows interest, the smart glasses will provide detailed information about the latest popular products.

[1114] Specific examples

[1115] Consider a scenario in which a store clerk wearing smart glasses is having a conversation with a customer. For example, if the customer says, "I want to know about the latest popular products," the following sequence of events will take place.

[1116] 1. The voice recognition engine converts the customer's speech into text data.

[1117] 2. The emotion recognition engine analyzes the customer's emotions and determines that they are highly interested.

[1118] 3. The NLP engine extracts the latest popular product information from the database.

[1119] 4. The extracted information is displayed on the smart glasses, allowing the store clerk to introduce the latest products.

[1120] Prompt Sentence Examples

[1121] An example of a prompt is shown below.

[1122] The customer seems interested in the latest popular products. His words and facial expressions suggest curiosity and interest. Introduce the latest popular products and explain their features and recommended points. Adjust your speaking style and tempo according to the customer's emotions.

[1123] This system allows for flexible responses tailored to customer emotions, which is expected to improve customer satisfaction and promote sales.

[1124] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1125] Step 1: Record the user's voice

[1126] The smart glasses record conversations between store clerks and customers in real time. The recorded data (audio data) is stored in the smart glasses. The user's conversation data is input and output as audio data.

[1127] Step 2: Send the audio data to the server

[1128] The audio data recorded on the device is sent from the smart glasses to the server in real time. The input is the audio data, and the output is the audio data sent to the server.

[1129] Step 3: Convert audio data to text data

[1130] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). At this time, voice data is taken as input and output as text data.

[1131] Step 4: Send the text data to the emotion recognition engine

[1132] The server then sends the converted text data to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the customer's emotions. The input is text data, and the output is emotion data.

[1133] Step 5: Integrate emotion data and text data

[1134] The server integrates the emotional data and text data to generate data corresponding to the customer's emotional state. As a result, the input is text data and emotional data, and the output is the integrated data.

[1135] Step 6: Extract information with an NLP engine

[1136] The server sends the integrated data to an NLP engine (e.g., OpenAI GPT-3) to extract the necessary information from what the customer said. This process takes the integrated data as input and produces the extracted information as output.

[1137] Step 7: Product recommendations based on extracted information

[1138] The server accesses a database (e.g. MySQL) and searches for the appropriate product data based on the extracted information. The input is the extracted information and the output is the product data.

[1139] Step 8: Submit your product data

[1140] The server sends the searched product data to the smart glasses, and the salesperson makes a suggestion to the customer. The input is the product data, and the output is the display data on the smart glasses.

[1141] Step 9: Real-time feedback

[1142] The smart glasses display the proposed product information to the salesperson in real time, helping them to respond to the customer. The salesperson then looks at the displayed data and provides a detailed explanation of the product to the customer. The input is product data, and the output is display data.

[1143] 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.

[1144] 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.

[1145] 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.

[1146] [Fourth embodiment]

[1147] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1148] 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.

[1149] 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).

[1150] 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.

[1151] 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.

[1152] 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).

[1153] 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. 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.

[1154] 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.

[1155] 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.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] 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."

[1160] This invention is a system for automating administrative tasks in an electronic medical record system to reduce the burden on medical professionals. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[1161] 1. Speech Recognition and Text Conversion

[1162] The device records the conversation between the doctor and the patient during the consultation. This recorded voice data is sent in real time to a server. The server receives this voice data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[1163] 2. Extraction of medical information and entry into electronic medical records

[1164] The server analyzes the text data and extracts medical information from it. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter information into the medical record.

[1165] 3. Automatic ordering of necessary tests and medications

[1166] The server identifies suspected diseases based on the extracted medical information and uses an AI model to recommend necessary tests and medications. For example, if a patient complains of a cough and fever, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication. The user can review this, make any necessary corrections, and finally confirm the order. The server then automatically executes the confirmed order and updates the relevant systems.

[1167] 4. Automatic generation of medical certificates

[1168] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, etc. The user can check the certificate and make corrections as necessary, significantly reducing the effort required to create the certificate.

[1169] 5. Automated accounting

[1170] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[1171] 6. Automatic generation of summaries for returning patients

[1172] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[1173] Specific examples

[1174] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test, and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user reviews and completes. Through this series of processes, the user can complete many administrative tasks without any hassle.

[1175] As described above, the present invention enables efficient operation of an electronic medical record system and provides specific means for reducing the administrative work of medical personnel as much as possible.

[1176] The processing flow will be explained below.

[1177] Step 1:

[1178] The device records the conversation between the doctor and the patient during the consultation, and is designed to record high-quality audio data.

[1179] Step 2:

[1180] The device sends the recorded audio data to the server in real time, and the communication is encrypted to ensure security.

[1181] Step 3:

[1182] The server inputs the received voice data into a speech recognition model that is specifically trained to accurately recognize medical terminology and converts it into text.

[1183] Step 4:

[1184] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[1185] Step 5:

[1186] The server automatically records the extracted medical information in the electronic medical record, entering the information according to pre-defined templates.

[1187] Step 6:

[1188] The server identifies suspected illnesses based on the analysis results and recommends necessary tests and medications. For example, in the case of a cough and fever, it would recommend a chest X-ray, blood tests, and antipyretic and analgesic medications.

[1189] Step 7:

[1190] The user checks the recommendations and makes any necessary corrections. The server automatically orders the confirmed tests and medications, and the results are reflected in the electronic medical records and testing system.

[1191] Step 8:

[1192] The server automatically generates a medical report that includes the patient's symptoms, diagnosis, and recommended treatment.

[1193] Step 9:

[1194] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[1195] Step 10:

[1196] The terminal scans the patient's insurance card and reads the insurance information.

[1197] Step 11:

[1198] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[1199] Step 12:

[1200] The server analyzes past medical records and automatically creates a medical summary for returning patients. When a patient returns to the hospital, treatment is based on this summary.

[1201] Step 13:

[1202] The user reviews and corrects the automatically generated medical summary and completes the final summary.

[1203] Example 1

[1204] 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."

[1205] Medical institutions face a problem of a heavy administrative burden related to medical treatment and diagnosis, preventing medical professionals from concentrating on their primary medical activities. In particular, tasks such as filling out medical records, creating medical certificates, and processing insurance claims are time-consuming and labor-intensive, requiring efficient operations. It is also difficult to quickly grasp past medical information for returning patients and determine the necessary tests and medications. To solve these issues, a system that highly automates administrative tasks and reduces the burden on medical professionals is needed.

[1206] 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.

[1207] In this invention, the server includes means for recording a user's voice, means for converting voice data into text data, means for extracting medical information from the text data, means for automatically recording the extracted medical information in a record, means for recommending suspected diseases and necessary tests and medications, means for automatically executing instructions for the recommended tests and medications, means for automatically generating reports, means for inputting insurance information and automatically calculating billing amounts based on the medical treatment details, means for analyzing past medical information and automatically creating medical summaries for returning patients, means for transmitting voice data to the server in real time, means for analyzing text data using natural language processing technology, means for generating recommendations using an AI model, and means for extracting text data from image data using OCR technology. This automates administrative tasks such as filling out medical charts, creating medical certificates, and processing insurance claims, enabling medical professionals to focus on their medical activities.

[1208] "User" refers to the medical professional or doctor in charge of medical treatment.

[1209] "Audio data" refers to data in which audio is recorded in digital format.

[1210] "Text data" refers to data that includes character information converted from audio data.

[1211] "Medical information" refers to information about a patient's chief complaint, symptoms, medical history, and diagnosis.

[1212] "Record" refers to documents containing patient medical information, such as electronic medical records and medical notes.

[1213] "Suspected disease" refers to a potential disease that is suspected based on medical information.

[1214] "Test" means a medical procedure to confirm or diagnose a suspected illness.

[1215] "Medication" means a medicine prescribed for medical treatment.

[1216] "Recommendation" refers to proposing optimal testing and treatment options derived from AI models, etc.

[1217] "Instructions" refer to medical procedures that are ultimately approved by the user.

[1218] A "report" refers to a document that summarizes diagnostic results, treatment plans, etc.

[1219] "Insurance Information" refers to information regarding a patient's health insurance.

[1220] "Billed amount" refers to the amount of medical expenses calculated based on the medical treatment.

[1221] "Medical summary" refers to a summary document that compiles past medical information for returning patients.

[1222] A "server" refers to a computer system that analyzes voice data and manages medical information.

[1223] "Natural language processing technology" is a technology for analyzing text data and is used to extract useful information from text data.

[1224] "AI model" refers to a predictive model built using machine learning algorithms.

[1225] "OCR technology" is a technology that optically reads character information and converts it into digital data.

[1226] This invention relates to an electronic medical record system that automates administrative tasks in medical institutions to reduce the burden on medical staff. This system is composed of users, terminals, and a server, and its specific operation and program processing are described below.

[1227] Speech recognition and text conversion

[1228] The device records the conversation between the doctor and the patient during the consultation. The recorded audio data is sent to a server in real time. The server then converts the audio data into text using a speech recognition model such as Google Cloud Speech-to-Text or IBM Watson Speech to Text. The converted text data includes information such as the patient's chief complaint, symptoms, and medical history.

[1229] Extraction of medical information and entry into electronic medical records

[1230] The server uses natural language processing (NLP) technology to analyze the text data and extract medical information from it. Software such as SpaCy and Stanford NLP are used. The extracted medical information is automatically entered into an electronic medical record template and stored in an SQL database.

[1231] Automatic ordering of necessary tests and medications

[1232] The server uses the extracted medical information to make inferences to identify suspected illnesses. AI models built with TensorFlow and PyTorch are used for inference. For example, if a patient complains of a cough and fever, the server recommends a chest X-ray, blood tests, and prescriptions for antipyretics and analgesics. The user can review these recommendations and make corrections as necessary. Once the final order is confirmed, the server updates the relevant systems and automatically executes it.

[1233] Automatic generation of medical certificates

[1234] The server automatically generates a medical certificate using a medical certificate template based on the details of the examination and the patient's medical record. The medical certificate includes the patient's symptoms, diagnosis, and recommended treatment. The user can review the medical certificate and make any necessary corrections.

[1235] Automating accounting processes

[1236] The terminal scans the patient's insurance card and sends the information to the server. The server extracts the insurance information using OCR technology (e.g., Tesseract OCR). The server then automatically calculates the billing amount based on the insurance information and the medical treatment details, and automatically updates the accounting system. Finally, a bill is issued to the patient.

[1237] Automatic summary generation for returning patients

[1238] The server analyzes the past medical records of returning patients and automatically generates a medical summary that will be useful for the next visit. The user can then check the summary and make any necessary corrections.

[1239] Specific examples

[1240] Consider the case of a 40-year-old male patient who complains of a persistent cough for the past few days and a high fever of 38 degrees since yesterday. In this case, the device records the conversation, and the server converts the audio into text using Google Cloud Speech-to-Text. The converted text is analyzed using SpaCy to extract the patient's symptom information. Based on the extracted information, the server recommends a chest X-ray and blood tests, and suggests a prescription for antipyretic and analgesic medication. Once the user confirms the order, the server automatically generates a medical certificate, which is ultimately saved and distributed in PDF format.

[1241] Prompt Sentence Examples

[1242] The following prompt sentence can be input into the generative AI model to automatically generate medical documents:

[1243] A 40-year-old male patient comes to the clinic complaining, "I've had a cough that hasn't stopped for the past few days. I've had a high fever of 38 degrees since yesterday." Based on the consultation, please write about the patient's symptoms, the recommended tests, and the prescribed medications.

[1244] These procedures allow users to efficiently complete many administrative tasks without any hassle.

[1245] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] The device records the conversation between the doctor and the patient during the consultation. The device's microphone is used to collect the conversation audio in WAV file format and save it as a file. The input is the conversation audio during the consultation, and the output is the recorded WAV file.

[1248] Step 2:

[1249] The device transmits the recorded audio data to the server in real time. The saved WAV file is uploaded to the server using the HTTP protocol. The input is the WAV file, and the output is the audio data transferred to the server.

[1250] Step 3:

[1251] The server calls the Google Cloud Speech-to-Text API to convert the received voice data into text data. It sends an API request and performs speech analysis. The input is the voice data, and the output is the converted text data.

[1252] Step 4:

[1253] The server analyzes the text data using natural language processing (NLP) technology. The software used is SpaCy or Stanford NLP. Important keywords (e.g., fever, cough, etc.) are extracted from the text data. The input is the text data, and the output is JSON data containing the extracted medical information.

[1254] Step 5:

[1255] The server stores the extracted medical information in an SQL database and automatically records it in an electronic medical record template. The input is medical information in JSON format, and the output is the information automatically recorded in the electronic medical record.

[1256] Step 6:

[1257] The server uses an AI model (using TensorFlow or PyTorch) to identify suspected diseases based on the extracted information and recommend necessary tests and treatments. Input data is provided to the AI ​​model, and an inference result is obtained. The input is medical information, and the output is a list of recommended tests and treatments.

[1258] Step 7:

[1259] The user reviews the recommended tests and medications on the web interface, makes any necessary modifications, and clicks a button on the UI to confirm the final order. The input is the recommendations and any modifications made by the user, and the output is the confirmed order.

[1260] Step 8:

[1261] The server sends the confirmed order in HL7 message format to the related systems (test order system, medication management system) and executes it automatically. The input is the confirmed order data, and the output is the order message sent to the related systems.

[1262] Step 9:

[1263] The server automatically generates a medical certificate using a LaTeX template based on the information in the medical record. The generated medical certificate is saved in PDF format and a download link is provided to the user. The input is the medical record information, and the output is a medical certificate in PDF format.

[1264] Step 10:

[1265] The terminal uses a scanner to scan the patient's insurance card and generate an image file. The input is the actual insurance card, and the output is the scanned image file.

[1266] Step 11:

[1267] The device sends the image file to the server and converts it into text data using OCR technology (using Tesseract OCR). The input is the scanned image file, and the output is text data containing insurance information.

[1268] Step 12:

[1269] The server automatically calculates the billing amount based on the insurance information and medical information using a rule engine (such as Drools). The input is the insurance information and medical information, and the output is the calculated billing amount.

[1270] Step 13:

[1271] The server updates the calculated billing amount to an accounting system such as SAP, generates a PDF invoice, and emails it to the patient. The input is the calculated billing amount, and the output is the PDF invoice sent.

[1272] Step 14:

[1273] The server analyzes the past medical records of returning patients and processes the data on a Hadoop cluster to extract key medical information. The input is the past medical records, and the output is the extracted medical information.

[1274] Step 15:

[1275] The server automatically generates a medical summary of the returning patient in Markdown format based on the extracted information. The input is the extracted medical information, and the output is the generated medical summary.

[1276] Step 16:

[1277] The user can check the generated medical summary through the web interface, and modify and save it as necessary. The input is the generated medical summary, and the output is the finalized medical summary.

[1278] (Application example 1)

[1279] 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."

[1280] In today's medical field, the administrative work involved in managing electronic medical records and creating medical records is increasing, placing a heavy burden on medical professionals. Providing appropriate diagnoses and treatments requires fast and accurate information entry and analysis, but doing this manually is inefficient and carries the risk of errors. Furthermore, with the spread of online medical consultations, a similarly efficient management system is required for consultations from remote locations. A system is needed to solve these issues and improve efficiency in the medical field.

[1281] 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.

[1282] In this invention, the server includes a means for converting voice data into text data, a means for extracting information from the text data, and a means for automatically recording the extracted information in a recording system. This allows voice data recorded during medical treatment to be converted into text data in real time, and necessary medical information can be quickly extracted. The extracted information is automatically recorded in an electronic medical record, and appropriate diagnoses and treatment recommendations are provided, significantly reducing administrative work in medical settings. Furthermore, past records are analyzed and information is automatically generated during follow-up visits, improving the efficiency of medical treatment. Furthermore, information analysis is possible via an external API, and the results are reflected in medical certificates and other record documents, enabling more accurate medical treatment.

[1283] "Audio data" refers to data in which an audio signal is recorded in digital format.

[1284] "Text data" refers to data in which character information is recorded in digital format.

[1285] "Information extraction" is the process of selecting necessary information from data based on a specific purpose.

[1286] A "system of record" is a computer system for storing and managing data.

[1287] A "disease" is a state of deviation from the normal physiological function of an organism, or a pathological process leading to that state.

[1288] A "test" is a method or procedure for making a medically necessary diagnosis or evaluation.

[1289] A "therapeutic procedure" is a method for treating, improving, or alleviating a specific disease or disorder.

[1290] A "recommendation" is a suggestion or recommendation based on specific conditions.

[1291] An "external API" is a mechanism that allows programs to exchange data and functions using interfaces provided by external applications and services.

[1292] "Analysis" is the process of examining data in detail to understand and evaluate its structure and content.

[1293] A "medical certificate" is an official document that lists the diagnosis and treatment plan.

[1294] "Insurance Information" means data and records relating to health insurance.

[1295] "Amount Due" means the amount due for services or goods.

[1296] A "revisit" is a consultation for additional treatment or evaluation after the initial visit.

[1297] The present invention provides a system for supporting the work of medical professionals in a virtual medical environment. This system converts voice data into text data, extracts medical information from the text data, and automatically creates various recommendations and records. Specific embodiments of the system are described below.

[1298] Speech recognition and text conversion

[1299] The conversation between the patient and doctor during the consultation is recorded using a device such as a smartphone or head-mounted display. The recorded voice data is sent to a server in real time. The server then uses voice recognition software (e.g., Google Speech Recognition API) to convert this voice data into text data. Through this process, the patient's chief complaint, symptoms, medical history, etc. are recorded in text format.

[1300] Extraction of medical information and entry into electronic medical records

[1301] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from the converted text data. This extraction includes information provided by the patient and treatment details provided by the doctor. The extracted medical information is automatically entered into an electronic medical record template, eliminating the need for users to manually enter medical records.

[1302] Automated Recommendations and Ordering

[1303] The server estimates the diagnosis based on the extracted medical information and recommends the necessary tests and treatments. The recommended tests and treatments are then automatically ordered after the user confirms and modifies them as necessary. For example, if a patient complains of a persistent cough and high fever for the past few days, the server will recommend a chest X-ray, blood tests, and a prescription for antipyretic and analgesic medication.

[1304] Automated medical certificate and accounting procedures

[1305] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The user can review the certificate and make corrections as necessary, reducing the effort required to create the certificate. The server also automatically calculates the billing amount based on the patient's insurance information and details of the treatment, and updates the accounting system. The calculated billing amount is then issued to the patient.

[1306] Automatic summary generation for returning patients

[1307] The server analyzes past medical records and automatically generates medical summaries for returning patients. By providing medical treatment based on these summaries, users can improve their work efficiency. For example, if a patient who was previously diagnosed with pneumonia returns for a follow-up visit, a summary of their past treatment history, medication prescription history, and other information is automatically generated, allowing users to easily check it.

[1308] Examples and prompts

[1309] A specific example would be a case where a 40-year-old male patient complains, "I haven't had a cough for several days and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text and automatically records it in the electronic medical record. The server then recommends a chest X-ray and blood test and generates an order to prescribe antipyretic and analgesic medication. Finally, the server automatically generates a medical certificate, which the user confirms and completes.

[1310] An example of a prompt to input to a generative AI model is as follows:

[1311] Extract medical information from the following text:

[1312] A 40-year-old male patient has had a persistent cough for the past few days and has had a high fever of 38 degrees since yesterday. A chest X-ray will be performed and we are considering prescribing antipyretics and analgesics.

[1313] In this way, the present invention is a system that reduces the burden on medical professionals in a virtual medical environment and enables efficient and accurate medical treatment.

[1314] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1315] Step 1:

[1316] Recording and transmitting audio data

[1317] The terminal records the conversation between the patient and the doctor during the consultation. This voice data is input and the recorded voice data is sent to the server in real time. The specific operation of the terminal is to capture the voice through the microphone and transfer it to the server via the network.

[1318] Step 2:

[1319] Converting audio data to text

[1320] The server converts the received voice data into text data using voice recognition software such as the Google Speech Recognition API. The input in this process is the voice data, and the output is the corresponding text data. Specifically, the server calls the voice recognition API, analyzes the voice signal, and outputs the corresponding string of characters.

[1321] Step 3:

[1322] Extracting medical information from text data

[1323] The server uses a generative AI model (e.g., OpenAI GPT-3) to extract medical information from text data. The input to this process is text data, and the output is the extracted medical information. Specifically, the server sends the prompt "Please extract medical information from the following text:" and the text data to the GPT-3 model, and receives the returned information as medical information.

[1324] Step 4:

[1325] Automatic recording of medical information in electronic medical records

[1326] The server automatically enters the extracted medical information into the electronic medical record template. In this step, the input is medical information and the output is an updated electronic medical record. Specifically, the server calls the API of the electronic medical record system and automatically enters the information into the corresponding fields in the medical record.

[1327] Step 5:

[1328] Automated recommendation and order fulfillment

[1329] The server predicts the diagnosis based on the medical information and recommends the necessary tests and treatments. After the user confirms and modifies the order, it automatically executes the order. The input is the extracted medical information and the order data modified by the user, and the output is the executed order. Specifically, the server uses the AI ​​model to predict the diagnosis, creates an appropriate order, and reflects it in the electronic medical record system and the testing institution's system.

[1330] Step 6:

[1331] Automatic generation of medical certificates

[1332] The server automatically generates a medical certificate based on the details of the medical treatment and the medical record information. The input to this process is the details of the medical treatment and the medical record information, and the output is the generated medical certificate. Specifically, the server embeds the details of the medical treatment into a medical certificate template and generates the medical certificate in PDF format or other format.

[1333] Step 7:

[1334] Automating accounting processes

[1335] The server automatically calculates the billing amount based on the insurance information and medical details, and reflects this in the accounting system. The input for this step is the insurance information and medical details, and the output is the calculated billing amount. Specifically, the server collates the medical details with the insurance information, generates a bill, and sends the information to the accounting system.

[1336] Step 8:

[1337] Automatic summary generation for returning patients

[1338] The server analyzes past medical record information for returning patients and automatically generates a medical summary. The input to this process is past medical record information, and the output is the generated medical summary. Specifically, the server searches the medical record database and creates a summary based on the past medical history.

[1339] 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.

[1340] This invention is a system that highly automates administrative tasks in an electronic medical record system and improves medical treatment efficiency by recognizing and adapting to the user's emotions. This system is composed of a user, a terminal, and a server, and its specific operation and program processing are described below.

[1341] 1. Speech Recognition and Text Conversion

[1342] The device records the conversation between the doctor and the patient during the consultation. The audio data is designed to be recorded at high quality. The recorded audio data is sent to the server in real time. The server receives this audio data and converts it into text data using a speech recognition model. The text data includes the patient's chief complaint, symptoms, medical history, etc.

[1343] 2. Emotion recognition and information regulation

[1344] The device sends recorded voice data to the emotion engine, which recognizes the emotions of the user (doctor or patient). The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[1345] 3. Extraction of medical information and entry into electronic medical records

[1346] The server analyzes the text data using natural language processing (NLP) technology. As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[1347] 4. Automatic ordering of necessary tests and medications

[1348] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[1349] 5. Automatic generation of medical certificates

[1350] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[1351] 6. Automating accounting processes

[1352] The device scans the patient's insurance card and sends the information to the server. The server automatically calculates the billing amount based on the insurance information and medical details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[1353] 7. Automatic generation of summaries for returning patients

[1354] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing treatment based on this summary during the return visit, the user's work efficiency improves. The user can then review the summary and make any necessary corrections.

[1355] Specific examples

[1356] For example, consider the case of a 40-year-old male patient who complains, "I haven't had a cough for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice into text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate support. For example, if the patient is feeling anxious, the system will display detailed explanations and help the doctor explain things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[1357] As described above, the present invention enables efficient operation of electronic medical record systems, minimizes administrative work for medical professionals, and provides a better medical environment by recognizing and adapting to user emotions.

[1358] The processing flow will be explained below.

[1359] Step 1:

[1360] The device records the conversation between the doctor and the patient during the consultation. The recording function is designed to capture high-quality audio data, which is then sent to the server in real time.

[1361] Step 2:

[1362] The device sends the recorded voice data to the emotion engine, which recognizes the emotions of the user and patient. The emotion engine analyzes the voice features and identifies emotions such as tension, anger, and joy.

[1363] Step 3:

[1364] The server inputs the received voice data into a speech recognition model and converts it into text data, which then contains the patient's complaint, symptoms, medical history, and other information contained in the conversation.

[1365] Step 4:

[1366] The server analyzes the text data using natural language processing (NLP) technology, and extracts medical information such as the patient's chief complaint, symptoms, medical history, and medication information.

[1367] Step 5:

[1368] The server automatically fills the extracted medical information into an electronic medical record template, adjusting the filling based on the emotional data identified from the emotion engine. For example, if the doctor is tired, a concise presentation of information is preferred.

[1369] Step 6:

[1370] The server identifies suspected diseases based on the analysis results and emotional data, and recommends necessary tests and treatments. If the patient is in a high state of anxiety, detailed explanations of the tests and treatments will be automatically displayed.

[1371] Step 7:

[1372] The user checks the recommended tests and medications and makes any necessary changes. Once the final order is confirmed, the server automatically executes the order and updates the relevant systems.

[1373] Step 8:

[1374] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The content and format of the certificate are adjusted based on data from the emotion engine. For example, if the patient is feeling anxious, advice on how to relieve stress is added.

[1375] Step 9:

[1376] The user reviews the automatically generated medical report and makes any necessary corrections. The final medical report is then completed.

[1377] Step 10:

[1378] The device scans the patient's insurance card and sends the information to the server, where it is automatically updated in the system.

[1379] Step 11:

[1380] The server automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is reflected in the accounting system, and an invoice is issued to the patient.

[1381] Step 12:

[1382] The server analyzes past medical records and automatically creates a medical summary for returning patients. This summary can be used to provide treatment at the time of the return visit, making treatment more efficient.

[1383] Step 13:

[1384] The user reviews the automatically generated medical summary and corrects it if necessary, resulting in the final summary.

[1385] Example 2

[1386] 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."

[1387] In today's medical field, doctors and nurses are overwhelmed with a large amount of administrative work, which reduces the efficiency of medical treatment. It is also difficult to appropriately recognize and respond to patients' emotions, which affects patient satisfaction and the effectiveness of treatment. Furthermore, processing medical treatment details and insurance information is time-consuming, and past information cannot be efficiently utilized even during follow-up visits. This increases the burden on medical professionals and poses the issue of a decline in the quality of medical treatment.

[1388] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1389] In this invention, the server includes means for converting voice data into text data, means for using natural language processing technology to extract medical information from the text data, and means for recognizing the user's emotions and adjusting the way information is displayed and the content of recommendations. This significantly automates the administrative work of doctors and nurses during medical treatment, and by appropriately recognizing and responding to patients' emotions, it improves the efficiency and quality of medical treatment, reduces the burden on medical professionals, and improves patient satisfaction.

[1390] "Users" are medical professionals such as doctors and nurses who use the system.

[1391] "Audio data" is digital information that is a recording of the conversation between the user and the patient.

[1392] "Text data" refers to voice data converted into text information.

[1393] An "electronic medical record" is a system for electronically recording and managing a patient's medical information.

[1394] "Natural language processing technology" refers to the general technology that enables computers to understand, analyze, and generate human language.

[1395] An "emotion engine" is software or algorithms that analyze and recognize the emotions of users or patients.

[1396] "Recommendation of tests and treatments" is a function in which the system suggests appropriate tests and treatments based on the analysis results.

[1397] A "medical certificate" is an official document that lists medical examination results and treatment plans.

[1398] "Insurance Information" refers to data relating to a patient's health insurance.

[1399] "Billed amount" is the total amount calculated based on the medical treatment.

[1400] A "medical summary" is summary information created based on past medical information.

[1401] The present invention is an electronic medical record system that significantly improves the efficiency of medical treatment in medical settings. This system is composed of a user, a terminal, and a server, and utilizes speech recognition, emotion recognition, natural language processing (NLP), and data analysis technologies in an integrated manner. Specific embodiments are described below.

[1402] Speech recognition and text conversion

[1403] The device records the conversation between the doctor and the patient during the consultation. The recording device is equipped with a high-quality microphone and dedicated recording software. The recorded audio data is sent to a server in real time. The server receives this audio data and converts it into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). The text data includes the patient's chief complaint, symptoms, medical history, etc.

[1404] Emotion recognition and information regulation

[1405] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The server analyzes the emotion data along with the text data and adjusts the extracted medical information and the content recorded in the electronic medical record. For example, if the doctor is tired or the patient is feeling very anxious, the way the information is displayed and the recommended content will be changed accordingly.

[1406] Extraction of medical information and entry into electronic medical records

[1407] The server analyzes the text data using natural language processing (NLP) techniques (e.g., SpaCy or BERT). As a result of the analysis, medical information such as the patient's chief complaint, symptoms, medical history, and medication information is extracted. The extracted medical information is automatically entered into an electronic medical record template based on data from the emotion engine.

[1408] Automatic ordering of necessary tests and medications

[1409] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. These recommendations are adjusted according to the user's emotional state. For example, if the patient is in a high state of anxiety, detailed explanations of tests and treatments will be automatically displayed first. If the doctor is tired, simple orders will be displayed that emphasize medical efficiency.

[1410] Automatic generation of medical certificates

[1411] The server automatically generates a medical certificate based on the details of the examination and the patient's medical record. The certificate includes the patient's symptoms, diagnosis results, recommended treatment, and other information. The content and format of the certificate are adjusted based on information from the emotion engine. For example, if the patient is feeling stressed, advice on how to alleviate that stress is added.

[1412] Automating accounting processes

[1413] The device scans the patient's insurance card and sends the information to the server, which then automatically calculates the billing amount based on the insurance information and medical treatment details. The calculated billing amount is automatically updated in the accounting system, and an invoice is issued to the patient.

[1414] Automatic summary generation for returning patients

[1415] The server analyzes past medical records and automatically creates a medical summary for returning patients. By providing medical treatment based on this summary during the return visit, the user's work efficiency is improved. The user can then review the summary and make any necessary corrections.

[1416] Specific examples

[1417] For example, consider the case of a 40-year-old male patient who complains, "I've had a cough that hasn't stopped for the past few days, and I've had a high fever of 38 degrees since yesterday." The device records this conversation, and the server converts the voice to text, which is then automatically recorded in the electronic medical record. At the same time, the device uses an emotion engine to recognize the patient's impatience or anxiety and provides appropriate responses. For example, if the patient is feeling anxious, the system will display detailed explanations and support the patient in explaining things in an easy-to-understand manner. Also, if the doctor is tired, simplified information will be provided to make medical treatment more efficient.

[1418] Example of input prompt for generative AI model

[1419] Below is an example of an input prompt for the generative AI model based on the case of a 40-year-old male patient who complained of a persistent cough for the past few days and a high fever of 38 degrees Celsius since yesterday.

[1420] "A 40-year-old male patient has had a persistent cough for the past few days, and has had a high fever of 38 degrees since yesterday. Based on this information, please perform speech recognition, sentiment analysis, and natural language processing, record it in the electronic medical record, and generate a processing code that will recommend appropriate tests and treatments."

[1421] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1422] Step 1:

[1423] The user begins a consultation. The device records the conversation between the doctor and the patient in high-quality format. Specifically, a microphone installed in the examination room captures the audio, and the audio data is stored in the device. The input is the audio of the conversation between the doctor and the patient, and the output is the recorded audio data.

[1424] Step 2:

[1425] The device transmits the recorded audio data to the server in real time using a secure protocol over an internet connection. The input is the recorded audio data, and the output is the audio data transmitted to the server.

[1426] Step 3:

[1427] The server converts the received voice data into text data using a speech recognition model (for example, Google Cloud Speech-to-Text API). Specifically, the speech recognition algorithm analyzes the voice signal and converts it into text information. The input is the voice data sent to the server, and the output is text data.

[1428] Step 4:

[1429] The server analyzes the text data and uses natural language processing (NLP) techniques (e.g., SpaCy or BERT) to extract medical information such as the patient's chief complaint, symptoms, and medical history. The input is text data generated by speech recognition, and the output is the extracted medical information. Specifically, the NLP engine analyzes the text and identifies important medical information.

[1430] Step 5:

[1431] The device sends the recorded voice data to an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's (doctor's or patient's) emotions. The input is the recorded voice data, and the output is the recognized emotion data. Specifically, the emotion engine analyzes the voice data and identifies the user's emotional state.

[1432] Step 6:

[1433] The server analyzes the text data and emotion data and adjusts the extracted medical information and the content to be recorded in the electronic medical record. The input is text data and emotion data, and the output is adjusted medical information. Specifically, the system changes the way information is displayed and the recommended content based on the emotion data.

[1434] Step 7:

[1435] The server automatically enters the extracted medical information into an electronic medical record template. The input is the adjusted medical information, and the output is the data recorded in the electronic medical record. The specific operation is to embed the data into the template and complete the medical record.

[1436] Step 8:

[1437] The server identifies suspected diseases based on the analysis results and recommends necessary tests and medications. The input is medical information recorded in the electronic medical record, and the output is the recommended tests and medications. Specifically, the diagnostic algorithm suggests the optimal tests and treatments.

[1438] Step 9:

[1439] The server automatically executes the order for the recommended tests and medications. The input is the recommended tests and medications, and the output is the executed test and treatment order. Specific operations include sending the necessary information to the ordering system.

[1440] Step 10:

[1441] The server automatically generates a medical certificate. The input is the data recorded in the electronic medical record and examination and treatment information, and the output is the completed medical certificate. Specifically, the data is embedded in a medical certificate template and an official medical certificate is generated.

[1442] Step 11:

[1443] The terminal scans the patient's insurance card and sends the information to the server. The input is the scanned data of the insurance card, and the output is the insurance information sent to the server. Specifically, the scanned image is converted into digital data and sent to the server.

[1444] Step 12:

[1445] The server automatically calculates the billing amount based on the insurance information and medical treatment details, and reflects this in the accounting system. The input is the medical treatment details and insurance information, and the output is the calculated billing amount. Specifically, the amount is calculated using the medical treatment details and insurance information, and registered in the accounting system.

[1446] Step 13:

[1447] The server analyzes past medical record information and automatically creates medical summaries for returning patients. The input is past medical record data, and the output is a medical summary for the returning patient. Specifically, the server analyzes the medical record data, extracts important medical information, and compiles it into a summary.

[1448] Step 14:

[1449] The user reviews the generated summary and corrects it if necessary. The input is the automatically generated medical summary, and the output is the reviewed and corrected summary. Specific operations involve the user viewing the summary and manually correcting any inaccuracies.

[1450] (Application example 2)

[1451] 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."

[1452] With conventional customer service systems, it is difficult for store staff to accurately understand customer feedback in real time and respond appropriately in an instant. Furthermore, while flexible responses based on customer emotions are required, there is a lack of means to achieve this. As a result, customer satisfaction declines and purchasing motivation decreases.

[1453] 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 means for recording the user's voice, means for converting voice data into text data, means for extracting information from the text data, means for automatically recording the extracted information in an electronic record, means for making necessary suggestions and recommendations, means for automatically implementing the recommended content, means for automatically creating a report, means for inputting transaction information and automatically calculating the billing amount based on the usage details, means for analyzing past information and automatically creating a summary of repeat users, and means for recognizing emotions from the user's voice and adjusting the response. This enables store clerks to accurately understand customer voices and respond appropriately and flexibly in real time according to their emotions.

[1454] "User" refers to the entity that uses the system, including store clerks and customers.

[1455] "Voice data" refers to digital audio signals recorded from users or customers.

[1456] "Text data" is voice data converted into character information.

[1457] "Information" refers to important content and elements extracted from the statements of users and customers.

[1458] An "electronic record" is a digital file or database that stores information extracted from audio data.

[1459] "Suggestions and recommendations" refer to appropriate products, services, and methods of response that the system presents based on the needs of the user or customer.

[1460] "Execution" refers to specific actions or operations that are carried out based on the proposed content.

[1461] A "report" is a document automatically created by the system that details the proposal and the results of its implementation.

[1462] "Transaction information" is detailed data relating to transactions with customers, including purchased items, quantities, amounts, etc.

[1463] "Amount Due" means the amount due calculated based on a Transaction.

[1464] "Historical information" refers to historical data stored in the system, such as previous transactions and records.

[1465] "Re-users" are customers or users who have used the system in the past and will use it again.

[1466] The "Summary" is a report document that briefly summarizes the past usage and transaction history of the repeat user.

[1467] "Emotion" refers to the emotional state or mood of a user or customer as recognized from their voice data.

[1468] "Adjustment" is the process of changing and optimizing suggestions and responses based on emotions.

[1469] This invention relates to a "smart customer service system" that improves the efficiency and quality of customer service in brick-and-mortar stores. The system analyzes conversations between users (store clerks) and customers in real time, and provides appropriate product suggestions and services based on the customer's emotions. This is realized by using "smart glasses."

[1470] Hardware and software used

[1471] Hardware:

[1472] Smart glasses (e.g. Google Glass)

[1473] server

[1474] software:

[1475] Speech recognition engine (e.g. Google Cloud Speech-to-Text)

[1476] Emotion recognition engine (e.g. IBM Watson Tone Analyzer)

[1477] NLP engine (e.g. OpenAI GPT-3)

[1478] Database (e.g. MySQL)

[1479] Data processing and calculation flow

[1480] 1. Speech recognition and text conversion:

[1481] The smart glasses record conversations between store clerks and customers in real time, and the recorded data is sent from the smart glasses to a server where it is converted into text using a voice recognition engine.

[1482] 2. Emotion recognition and information regulation:

[1483] The server passes the text data to an emotion recognition engine to analyze the customer's emotions (e.g., desire, anxiety, interest). This emotion data is used to tailor suggestions and recommendations.

[1484] 3. Appropriate product recommendations:

[1485] As part of its task, the server uses an NLP engine to extract customer intent and requests from the text data, and based on this, it searches for the most suitable product and service information from a database and displays the selected product information on the smart glasses in real time.

[1486] 4. Real-time feedback:

[1487] By combining customer sentiment data with product suggestions, the smart glasses display the most appropriate suggestions and explanations to the salesperson. For example, if a customer shows interest, the smart glasses will provide detailed information about the latest popular products.

[1488] Specific examples

[1489] Consider a scenario in which a store clerk wearing smart glasses is having a conversation with a customer. For example, if the customer says, "I want to know about the latest popular products," the following sequence of events will take place.

[1490] 1. The voice recognition engine converts the customer's speech into text data.

[1491] 2. The emotion recognition engine analyzes the customer's emotions and determines that they are highly interested.

[1492] 3. The NLP engine extracts the latest popular product information from the database.

[1493] 4. The extracted information is displayed on the smart glasses, allowing the store clerk to introduce the latest products.

[1494] Prompt Sentence Examples

[1495] An example of a prompt is shown below.

[1496] The customer seems interested in the latest popular products. His words and facial expressions suggest curiosity and interest. Introduce the latest popular products and explain their features and recommended points. Adjust your speaking style and tempo according to the customer's emotions.

[1497] This system allows for flexible responses tailored to customer emotions, which is expected to improve customer satisfaction and promote sales.

[1498] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1499] Step 1: Record the user's voice

[1500] The smart glasses record conversations between store clerks and customers in real time. The recorded data (audio data) is stored in the smart glasses. The user's conversation data is input and output as audio data.

[1501] Step 2: Send the audio data to the server

[1502] The audio data recorded on the device is sent from the smart glasses to the server in real time. The input is the audio data, and the output is the audio data sent to the server.

[1503] Step 3: Convert audio data to text data

[1504] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text). At this time, voice data is taken as input and output as text data.

[1505] Step 4: Send the text data to the emotion recognition engine

[1506] The server then sends the converted text data to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the customer's emotions. The input is text data, and the output is emotion data.

[1507] Step 5: Integrate emotion data and text data

[1508] The server integrates the emotional data and text data to generate data corresponding to the customer's emotional state. As a result, the input is text data and emotional data, and the output is the integrated data.

[1509] Step 6: Extract information with an NLP engine

[1510] The server sends the integrated data to an NLP engine (e.g., OpenAI GPT-3) to extract the necessary information from what the customer said. This process takes the integrated data as input and produces the extracted information as output.

[1511] Step 7: Product recommendations based on extracted information

[1512] The server accesses a database (e.g. MySQL) and searches for the appropriate product data based on the extracted information. The input is the extracted information and the output is the product data.

[1513] Step 8: Submit your product data

[1514] The server sends the searched product data to the smart glasses, and the salesperson makes a suggestion to the customer. The input is the product data, and the output is the display data on the smart glasses.

[1515] Step 9: Real-time feedback

[1516] The smart glasses display the proposed product information to the salesperson in real time, helping them to respond to the customer. The salesperson then looks at the displayed data and provides a detailed explanation of the product to the customer. The input is product data, and the output is display data.

[1517] 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.

[1518] 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.

[1519] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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).

[1524] 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.

[1525] 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."

[1526] 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.

[1527] 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).

[1528] 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.

[1529] 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.

[1530] 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.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] 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.

[1536] 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, in order to avoid confusion and to 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.

[1537] 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.

[1538] The following is further disclosed regarding the above embodiment.

[1539] (Claim 1)

[1540] a means for recording the user's voice;

[1541] means for converting voice data into text data;

[1542] means for extracting medical information from text data;

[1543] a means for automatically recording the extracted medical information in an electronic medical record;

[1544] A means of recommending suspected diseases, necessary tests, and treatments;

[1545] a means for automatically ordering the recommended tests and medications;

[1546] A means for automatically generating a medical certificate;

[1547] A means to input insurance information and automatically calculate the billing amount based on the medical treatment details;

[1548] A means for analyzing past medical record information and automatically creating medical summaries for returning patients;

[1549] A system including:

[1550] (Claim 2)

[1551] 2. The system according to claim 1, further comprising means for transferring a conversation between the user and the patient during medical treatment to the server in real time as voice data.

[1552] (Claim 3)

[1553] 10. The system of claim 1, further comprising means for a user to review and modify the automatically generated charts, diagnosis reports, and medical summaries.

[1554] "Example 1"

[1555] (Claim 1)

[1556] a means for recording the user's voice;

[1557] means for converting voice data into text data;

[1558] A means for extracting medical information from text data;

[1559] means for automatically recording the extracted medical info...

Claims

1. a means for recording the user's voice; means for converting voice data into text data; means for extracting medical information from text data; a means for automatically recording the extracted medical information in an electronic medical record; A means of recommending suspected diseases, necessary tests, and treatments; a means for automatically ordering the recommended tests and medications; A means for automatically generating a medical certificate; A means to input insurance information and automatically calculate the billing amount based on the medical treatment details; A means for analyzing past medical record information and automatically creating medical summaries for returning patients; A system including:

2. 2. The system according to claim 1, further comprising means for transferring a conversation between the user and the patient during medical treatment to the server in real time as voice data.

3. 10. The system of claim 1, further comprising means for a user to review and modify the automatically generated charts, diagnosis reports, and medical summaries.

Images