system

Abstract

We provide the system. [Solution] A method for analyzing medical interview data using natural language processing and proposing possible medical conditions, A means of automatically generating electronic medical records based on the analysis results, A means of providing the generated medical records in an editable format and storing them in a medical information database, Security management measures to securely manage patient information and provide it based on necessary access rights, A means of acquiring and analyzing voice data to assess health status within the home, A means of presenting health management information based on evaluation results, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the medical field, there is a demand to reduce the long working hours, overwork, and mental stress of doctors. However, conventional methods require a lot of time and labor for interviews, medical record creation, and data management, which has become a burden on doctors. Due to such problems, it has become difficult to improve the efficiency of medical treatment and provide high-quality medical care. There is a need for a system that automates and supports these processes in an efficient and reliable manner.

Means for Solving the Problems

[0005] This invention provides a system that analyzes patient interview data using natural language processing and proposes estimated medical conditions. Furthermore, it automatically generates electronic medical records based on these analysis results and provides an editable interface for medical professionals as needed. In addition, these medical records are stored under secure management and provided to those with appropriate access rights. This enables efficient diagnostic support and data management in medical settings, reducing the burden on physicians and improving the quality of medical care.

[0006] "Natural language processing" is a technology that enables computers to understand and analyze human language, and is used for analyzing text data and extracting information.

[0007] "Medical interview data" refers to digital information provided by patients to medical institutions regarding their symptoms and health status.

[0008] A "suggested medical condition" is an estimated result that shows healthcare professionals possible illnesses and symptoms based on the analysis of interview data.

[0009] An "electronic medical record" is a medical document that electronically records a patient's medical information and health status, and is used to manage diagnostic results and treatment history.

[0010] "Security management" is a general term for methods and technologies used to protect the confidentiality, integrity, and availability of data, and is a management system designed to prevent unauthorized access and information leaks.

[0011] A "learning model" is an algorithm or mathematical structure built to extract patterns and knowledge from data and perform predictions and classifications. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to a system for medical interviews, symptom suggestion, automatic medical record generation, and data management in a medical setting, and has the following configuration and operation.

[0034] Medical history and analysis

[0035] Users answer questions about their symptoms and health status through a medical questionnaire terminal. This response data is sent from the terminal to a server. The server analyzes this questionnaire data using a natural language processing engine to understand and classify the patient's complaints. For example, if a patient answers, "I have a persistent cough and headache," the server analyzes this information and extracts possible medical conditions.

[0036] Suggestions for the medical condition

[0037] The server uses natural language processing results to reference statistical models and medical knowledge databases to list possible medical conditions. This list, along with estimated probabilities, is sent to the terminal and presented to the user (a physician). The physician can then use this suggestion to consider directions for an initial diagnosis.

[0038] Automatic generation of medical records

[0039] The server automatically generates an electronic medical record based on the patient's medical history data and the proposed list of symptoms. The medical record consists of the patient's basic information, symptoms, and proposed diagnosis. The generated medical record can be viewed in real time by the doctor via a terminal, and any necessary information can be added or modified.

[0040] Data storage and management

[0041] The edited medical record information is stored in a highly secure database. The server provides secure access control to the stored data, ensuring that healthcare professionals and patients can access the information based on appropriate access rights. This system allows for the unified management of patient information across different healthcare facilities, enabling consistent treatment.

[0042] As a specific example

[0043] If a patient complains of symptoms such as "chest pain and shortness of breath," the server analyzes this and suggests possible diagnoses such as "myocardial infarction" or "angina." The doctor then reviews this and performs the necessary tests. Based on the test results, the information is added directly to the medical record and saved. This entire process is performed digitally and efficiently, reducing the burden on doctors and ensuring the provision of high-quality medical services.

[0044] As described above, the present invention provides specific means for improving the efficiency and quality of medical operations.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The user (patient) uses a terminal for medical questionnaires to input answers to questions about their health status and symptoms. Once input is complete, the terminal sends this questionnaire data to the server in digital format.

[0048] Step 2:

[0049] The server passes the received medical questionnaire data to a natural language processing engine for analysis. During this analysis phase, symptoms and health information are identified and converted into necessary medical terminology.

[0050] Step 3:

[0051] The server uses the analysis results to reference a medical knowledge base and statistical models to create a list of predicted medical conditions. This list also includes the estimated probability of each condition.

[0052] Step 4:

[0053] The terminal displays a list of medical conditions received from the server to the user, who is a physician. This allows the physician to review the estimated medical conditions and use them as a reference for initial diagnosis.

[0054] Step 5:

[0055] The server automatically generates an electronic medical record based on the patient interview data and the proposed list of symptoms. The medical record includes the patient's basic information, discovered symptoms, and proposed diagnosis.

[0056] Step 6:

[0057] The terminal displays the generated electronic medical record to the physician and provides editing functions that allow the physician to add or modify information in the medical record as needed.

[0058] Step 7:

[0059] The server stores the final edited medical record information in a secure database. This data is managed with a high level of security and is accessible only to authorized users as needed.

[0060] Step 8:

[0061] Users (healthcare professionals and patients) can access past medical data and manage their own health status based on their permitted access rights.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] Modern healthcare demands rapid and accurate diagnosis and efficient information management. However, many healthcare institutions rely heavily on manual record creation and information management, which places a burden on healthcare professionals. Therefore, there is a need for systems that streamline the entire process, from patient interviews and diagnosis to record creation and information management, thereby improving the quality of medical care.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes an algorithm that uses natural language processing to analyze medical information entered by the user and proposes a suspected disease; an automatic generation means that includes a method for automatically generating an electronic medical record file based on the analysis results and user information; an digitization means that provides the generated medical record file to medical professionals in a real-time editable format and stores it in a storage database; and an information protection means that securely manages patient information and related data and provides it based on determined access rights. This makes it possible to streamline the entire process from medical interview to diagnosis and information management, reduce the burden on medical professionals, and improve the quality of medical care.

[0067] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is used to accurately interpret user medical information.

[0068] "Medical history information" refers to data about the patient's health status and symptoms, and is a fundamental source of information for making a diagnosis.

[0069] An "algorithmic method" is a series of steps or calculation methods for solving a specific problem, and this method uses natural language processing to analyze medical interview information and derive a suspected disease.

[0070] An "electronic medical record file" is a digital document that records a patient's medical information and is used to accurately track the process of diagnosis and treatment.

[0071] "Automated generation means" refers to a technology that uses algorithms to automatically create medical records, and is a procedure for efficiently organizing and creating medical information.

[0072] "Digitization means" refers to methods for representing, storing, and managing information in digital format, and is a process for securely storing generated medical records and providing them in an editable format.

[0073] "Information protection measures" are technologies or processes designed to ensure the confidentiality and integrity of data, and are methods for securely managing patient information and restricting access based on authorization.

[0074] This invention is a system that enables efficient patient interviews, diagnostic support, medical record generation, and data management in medical settings. This system consists of users, terminals, and a server, and operates as follows:

[0075] The user first uses a medical questionnaire terminal to answer questions about their physical symptoms and health status. The data entered is easily processed by following the on-screen instructions on the terminal. This information is then transmitted to the server using the terminal's communication capabilities. The communication uses an encrypted protocol to protect the data.

[0076] The server uses natural language processing (NLP) techniques to analyze the received medical questionnaire data. Software used for this includes, for example, Python libraries and natural language processing APIs. This analysis allows for the appropriate interpretation of the patient's symptoms and their conversion into medical terminology and relevant information.

[0077] Based on the analysis results, the server utilizes a generative AI model to estimate possible medical conditions. The estimation process involves referencing medical databases to create a more accurate list of conditions. This list, along with estimated probabilities, is then sent to the terminal.

[0078] The terminal displays a list of generated medical conditions, allowing healthcare professionals to determine their initial diagnostic strategy based on this information. The server automatically generates an electronic medical record based on the analysis results and estimated medical conditions. This record includes patient information, current symptoms, and proposed diagnoses, and is configured to allow physicians to review and edit it in real time as needed.

[0079] For example, if a patient reports "fever and sore throat" and enters their medical history, the server can analyze this information and estimate the patient's condition, such as "viral pharyngitis" or "influenza." This information is automatically included in the medical record and serves as a reference for the doctor.

[0080] An example of a prompt message would be: "This patient's symptoms are 'fever and sore throat.' Please use the AI ​​model to calculate possible conditions and their estimated probabilities." The system would then produce appropriate output based on this input. In this way, the invention enables accurate and efficient information processing in medical settings.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The user answers questions about their health status and symptoms using a medical questionnaire terminal. The user's input is recorded on the terminal in text format. The terminal encrypts the entered questionnaire data and sends it to the server via a secure communication protocol. The input data is raw symptom information and is ready to be transferred to the server as output.

[0084] Step 2:

[0085] The server initiates natural language processing using the patient interview data received from the terminal. The input is encrypted interview data. The server decrypts it and parses the text using the Python NLTK library. Specifically, the server divides the data into tokens and extracts important keywords. This outputs the patient's complaints as structured data, allowing the server to proceed to the next diagnostic estimation step.

[0086] Step 3:

[0087] The server uses a generative AI model to estimate possible medical conditions based on extracted keywords. The input is keyword data structured using natural language processing. The server refers to statistical models and medical databases to generate a list of medical conditions with estimated probabilities. The output is a list of proposed medical conditions, which is then sent to the next serving step.

[0088] Step 4:

[0089] The server sends a list of estimated medical conditions to the terminal, allowing the user, a healthcare professional, to make a diagnosis based on this information. The input is a list of estimated medical conditions, which the server converts into a format that can be displayed on the terminal in real time and provides as output. This information supports rapid decision-making in the medical field.

[0090] Step 5:

[0091] The server automatically generates electronic medical records based on patient interview data and a list of medical conditions. Input consists of structured patient information and medical condition data. The server integrates this information and creates the electronic medical record based on a template. The output is an editable medical record file, which users can view, edit, and save in real time on their terminals.

[0092] Step 6:

[0093] The server stores the generated medical records in secure data storage. The input is the generated medical record file. The server properly encrypts the patient data and stores it in the database. The output is securely stored medical record information, ready for later access. This information can be securely used by the appropriate users based on access permissions.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] Reducing the workload in healthcare settings and providing efficient medical care are crucial challenges. In particular, systems for home health management and daily health checks contribute not only to reducing the burden on medical facilities but also to maintaining the health of the general public. However, conventional systems have been difficult to use in homes, posing challenges in real-time health assessment and appropriate management of medical information.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] This invention includes a server that analyzes medical interview data using natural language processing and proposes possible medical conditions, a server that automatically generates an electronic medical record based on the analysis results, a server that provides the generated medical record in an editable format and stores it in a medical information database, a server that acquires and analyzes voice data to evaluate the patient's health status at home, and a server that presents health management information based on the evaluation results. This enables efficient and consistent health management both in medical settings and at home.

[0099] "Natural language processing" refers to the ability of computers to understand and analyze human language, and is a technology that extracts and generates information based on text and audio data.

[0100] "Medical interview data" refers to information that patients provide when answering questions about their health status and symptoms, and serves as the basis for analyzing and diagnosing their medical condition.

[0101] The "means of suggesting medical conditions" refers to a function that lists and presents possible health conditions and diseases based on data analyzed using natural language processing.

[0102] "Automatic electronic medical record generation" is a system that creates a patient's medical record in digital format based on analyzed medical history data and suggested medical condition information.

[0103] "Security management measures" refer to systems that securely protect patients' medical information and data, and restrict access to and use of that information based on appropriate access rights.

[0104] "Means for acquiring audio data" refers to technologies that collect user speech using microphones or speech recognition devices.

[0105] A "means for evaluating health status" refers to a system that determines and evaluates a user's health status based on acquired voice data and analysis results.

[0106] "Means of providing health management information" refers to a function that provides users with improvement measures and precautions based on their analyzed health status.

[0107] To realize this invention, a system operating in a smart home is required. To support in-home health management, a combination of a server, an internet-connected terminal, and a voice recognition device for user interaction will be used.

[0108] The server converts user speech into text data using speech recognition technologies such as Google® Cloud Speech-to-Text API and Amazon Transcribe. This text data is analyzed using OpenAI®'s GPT-3® and BERT natural language processing engines to suggest possible medical conditions. Based on the analyzed data, an electronic medical record is generated and stored in a medical information database for security management.

[0109] The terminal installed in the home provides users with feedback on analysis results and health management suggestions via voice and display screens. This information is presented as measures to improve health and precautions, playing a role in supporting daily health management. For example, if a user voice-inputs "I have a headache today," the system operates in the background, the server analyzes the information, and presents possible causes and minor remedies visually or audibly.

[0110] For example, the prompt could be written as follows: "Please tell me what to do if the user complains of a headache. Please list possible causes and remedies that can be done at home." This would enable a self-sustaining system to function within the home to support the user's health.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The user communicates their health status and symptoms to a voice input device. This voice input becomes the system's initial data source. The acquired voice data is converted into text data using speech recognition technology on the device. This conversion process yields text data that can be subsequently analyzed.

[0114] Step 2:

[0115] The terminal sends text data to the server. The server receives this text and analyzes the data using a natural language processing engine. Specifically, the input text is passed through OpenAI's GPT-3 or BERT to systematically analyze its meaning and extract possible medical conditions and related information. This analysis generates hypotheses about the health status.

[0116] Step 3:

[0117] The server suggests medical conditions based on the extracted information and generates an electronic medical record. This record includes the user's basic information, chief complaint, and suggested medical conditions. The generated record is then provided to the terminal in a format that can be reviewed and modified by the user and medical professionals. This record generation process enables unified management of health information.

[0118] Step 4:

[0119] The server securely stores the generated electronic medical records and analysis results in a medical information database. This stored information can be used as a record of the user's past health history to aid in future diagnoses and health management.

[0120] Step 5:

[0121] The device provides users with health management suggestions and advice based on analysis results and medical record information. These suggestions are fed back to the user via voice or display, supporting daily health management. For example, it might offer advice such as, "We recommend you drink more water."

[0122] Through these steps, users can easily monitor their health status at home and decide whether to seek medical attention if necessary.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention is a medical support system for the medical field, which includes analysis of medical interview data, suggestion of medical conditions, automatic generation of electronic medical records, and an emotion engine that recognizes the user's emotions. This emotion engine analyzes the patient's emotional state and uses it to supplement data in the diagnostic process and adjust the suggested content.

[0125] Medical history and emotional recognition

[0126] The user (patient) uses a device to answer questions about their health status by typing or speaking. During this process, the emotion engine analyzes facial expressions and tone of voice through the camera and microphone to recognize the patient's emotional state (e.g., anxiety, stress, relief). The recognized emotional information is sent to the server as part of the medical questionnaire data.

[0127] Data analysis and disease state recommendations

[0128] The server analyzes the patient's interview data and recognized emotional information using a natural language processing engine. The analysis results support more accurate predictions of the patient's condition, taking into account the patient's emotional state. For example, if a patient exhibits severe anxiety, this information will influence the stress-related condition suggestions.

[0129] Electronic medical record generation

[0130] Based on the analysis results, the server automatically generates an electronic medical record. The generated record includes the patient's basic health information, detected symptoms, recommended diagnosis, and emotional information. The terminal provides this record to healthcare professionals in an editable format, allowing for adjustments as needed.

[0131] Data storage and security management

[0132] Edited medical record information is stored in a highly secure database on the server. Emotional information is also handled as part of data management. This allows users (healthcare professionals) to provide more consistent treatment based on information including the patient's emotional state.

[0133] Specific example

[0134] For example, if a patient presents with symptoms of stomach pain while also showing clear signs of anxiety, the server will analyze this emotional state and suggest conditions such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses and provide care that take the patient's psychological state into account.

[0135] This system, incorporating an emotional engine, will provide multifaceted support for physicians' diagnostic work and enable the provision of medical care that takes into account the patient's psychological state.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user (patient) uses a medical questionnaire terminal to answer questions about their health status and symptoms via text input or voice input. During this process, the terminal records the patient's facial expressions and tone of voice using a camera and microphone, collecting emotional data.

[0139] Step 2:

[0140] The device transmits the collected medical interview data and emotional data to the server. An encryption protocol is used during transmission to ensure data security.

[0141] Step 3:

[0142] The server uses a natural language processing engine to analyze the medical interview data. Through this analysis, it organizes the extracted information about symptoms and health, and simultaneously evaluates emotional data using an emotion engine to identify the patient's emotional state.

[0143] Step 4:

[0144] The server references a medical knowledge base based on analysis results and emotional information to list possible medical conditions. This list includes the severity and probability of the predicted conditions, as well as consideration of the patient's emotional state.

[0145] Step 5:

[0146] The created list of medical conditions is sent to the terminal and displayed to the user (doctor). The doctor uses this information to help determine the subsequent diagnostic course.

[0147] Step 6:

[0148] The server automatically generates an electronic medical record based on the patient's interview data, emotional data, and a list of suggested conditions. This record includes the patient's symptoms, suggested diagnoses, and perceived emotional states.

[0149] Step 7:

[0150] The terminal provides the generated electronic medical record to the physician in an editable format. The physician can then add feedback and additional information to this record.

[0151] Step 8:

[0152] The edited medical record data is stored in a secure database on the server. The stored data is protected by appropriate access controls, allowing healthcare professionals to access it as needed.

[0153] This entire process allows for patient-centered care and enables the provision of more personalized medical services.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0156] Conventional medical support systems often perform data analysis without considering emotional states, making it difficult to make diagnoses that adequately reflect the patient's psychological state. Furthermore, the lack of mechanisms to utilize post-treatment evaluations within the system limited the ability to continuously improve the accuracy of medical care.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for analyzing medical interview information using natural language processing and proposing a health status, means for automatically generating electronic records, and means for analyzing the user's emotional state using an emotion recognition engine and integrating it with the medical interview information. This makes it possible to generate diagnoses and records that take into account the patient's emotional state.

[0159] "Natural language processing" is the technology that enables computers to understand, generate, and analyze human language.

[0160] "Medical interview information" refers to data about a patient's health status and symptoms that they provide to a medical institution.

[0161] "Health status" refers to an indicator of a patient's physical and psychological health.

[0162] "Electronic records" are digital documents generated for the purpose of electronically storing and managing medical information about patients.

[0163] An "emotion recognition engine" is a system that analyzes a user's facial expressions and voice to identify their emotional state.

[0164] A "user" is defined as the entity that operates the system and inputs or verifies information.

[0165] "Analysis accuracy" is an indicator used to evaluate the accuracy and reliability of data analysis.

[0166] "Learning techniques" refer to algorithms and methods that enable a system to gain experience and improve its performance.

[0167] This invention is a medical support system that provides a process in which a user (patient) inputs health-related information, and a server analyzes the health status based on that information and generates an electronic record. By using an emotion recognition engine, this system makes it possible to incorporate the patient's psychological state into the diagnosis.

[0168] Users input health information using a terminal. The terminal has an interface that accepts keyboard input or voice responses. The terminal also captures facial expressions and tone of voice using its built-in camera and microphone, and an emotion recognition engine analyzes this data. The analyzed emotion information is integrated into the medical questionnaire information sent to the server.

[0169] The server uses natural language processing technology to analyze the received medical history and emotional information. A generative AI model is used for this analysis, resulting in the generation of suggestions regarding the patient's health status. Emotional information is used to further refine the suggestions.

[0170] Once the analysis is complete, the server automatically generates an electronic record. This electronic record includes the patient's basic information, analyzed symptoms, suggested diagnosis, and emotional information. The terminal can display this record in a format that healthcare professionals can edit as needed.

[0171] For example, if a patient complains of stomach pain and expresses anxiety during a consultation, the server will examine this information and suggest possibilities such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses that take the patient's psychological state into account.

[0172] An example of a prompt message would be, "Please list possible health conditions when a user complains of stomach pain and expresses anxiety." This allows the system to comprehensively analyze the user's condition and make appropriate suggestions.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The user answers questions about their health status by typing or speaking using the device. The device receives the input data (text or voice data) and converts it into a digital format. During this process, the camera and microphone simultaneously capture facial expressions and voice tone, generating emotion data.

[0176] Step 2:

[0177] The terminal sends the entered questionnaire data and recognized emotion data to the server. Specifically, the questionnaire data is in text format, and the emotion data is encoded as analyzed psychological indicators, and these are sent together. This transmitted data becomes the input for the next analysis step.

[0178] Step 3:

[0179] The server analyzes the received questionnaire data and emotional data using a natural language processing engine. The analysis employs a generative AI model to integrate text and emotional information and calculate probabilities related to the user's health condition. Based on these results, a list of hypothesized health conditions is output.

[0180] Step 4:

[0181] The server automatically generates an electronic record based on the analysis results and suggested health status. This electronic record includes the patient's basic information, detected symptoms, suggested health status name, and emotional information. The generated record is output in digital format and provided to healthcare professionals.

[0182] Step 5:

[0183] The terminal displays the generated electronic records to healthcare professionals. Healthcare professionals can edit these records as needed, adjusting them to finalize the clinical information. The edited records are then returned to the server for storage.

[0184] (Application Example 2)

[0185] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0186] In modern elderly care settings, a challenge is to appropriately understand the emotional state of the elderly and provide care based on that understanding. Care providers are required to understand the psychological and emotional needs of the elderly and respond accordingly, but this is sometimes difficult to achieve due to staffing shortages and technological limitations. Therefore, the development of support tools utilizing emotion recognition technology is necessary.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0188] In this invention, the server includes means for analyzing medical interview data using natural language processing and suggesting possible medical conditions, means for automatically generating an electronic medical record based on the analysis results, and means for recognizing the user's emotional state from acoustic or visual data and adjusting the suggested content based on emotions. This makes it possible to suggest dialogue content and care actions that correspond to the emotional state.

[0189] "Natural language processing" is a technology that allows computers to understand and analyze human language and extract meaningful information.

[0190] "Medical interview data" refers to information about the health status collected from patients or users.

[0191] An "electronic medical record" is a record-keeping system for storing and managing patients' health information and medical history in a digital format.

[0192] "Security management" refers to the measures and systems in place to protect patient information and medical data from unauthorized access and leakage.

[0193] "Emotion recognition" is a technology that analyzes acoustic or visual data to identify the emotional state of a subject.

[0194] "Care providers" refer to people who are responsible for providing care and support to users or patients in nursing homes and medical institutions.

[0195] "Emotion-based proposals" are a method of adjusting and proposing the content of dialogue and actions according to the perceived emotional state.

[0196] This invention realizes a system that provides care providers in nursing care settings with dialogue and behavioral suggestions based on the emotional state of elderly individuals. The server analyzes the user's medical history data using natural language processing technology to predict possible medical conditions. The main software used in this process includes a natural language processing engine and an emotion recognition library. Specifically, the IBM Watson® natural language processing engine is used, and the Microsoft® Azure® Emotion API is used as the emotion recognition library.

[0197] The server utilizes acoustic and visual data to recognize the user's emotional state in real time. This enables the automatic generation of electronic medical records based on analysis results combined with interview data. The generated electronic medical records are then used as an interface to provide care providers with appropriate suggestions tailored to the user's emotional state.

[0198] The terminal, via devices such as smart glasses, presents specific suggestions regarding conversation content and actions in the care setting. For example, if an elderly person shows anxiety, the server generates a prompt such as, "How about talking about a happy memory from the past?" and provides this suggestion to the care staff.

[0199] For example, if a caregiver is talking to an elderly person and the user says, "I don't really want to do anything today," the generative AI model, based on past experience, will generate a prompt such as, "Let's talk about a hobby you used to enjoy," and present it to the care staff. In this way, it is possible to support appropriate care tailored to the user's emotional state.

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The user inputs speech and facial expressions through smart glasses. The device captures audio and video data using its camera and microphone and sends it to a server. The input data is analyzed acoustically and visually using an emotion recognition library and output as an emotional state (e.g., joy, anxiety, calmness).

[0203] Step 2:

[0204] The server receives emotional states derived from the user's acoustic and visual data as input. A natural language processing engine is used to analyze the questionnaire data and emotional states. Based on the results, an electronic medical record reflecting the user's health status is automatically generated and stored in a database. This electronic medical record includes recommendations based on the detected medical conditions and emotional states.

[0205] Step 3:

[0206] The terminal displays suggestions based on the electronic medical record and emotional state provided by the server. Specifically, an AI model generates prompts tailored to the user's emotional state, instructing caregivers on recommended conversations and actions. For example, a prompt such as "Try talking about a fun activity from the past" might be presented.

[0207] Step 4:

[0208] Care providers use prompts displayed on the terminal to communicate with clients and conduct care activities. If responses or new information are obtained from the client, they return to step 1 to acquire new emotional state and interview data and continue the process. This allows for flexible, real-time responses.

[0209] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0210] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0211] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0215] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0216] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0217] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0219] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0220] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0221] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0222] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0223] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0224] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0225] This invention relates to a system for medical interviews, symptom suggestion, automatic medical record generation, and data management in a medical setting, and has the following configuration and operation.

[0226] Medical history and analysis

[0227] Users answer questions about their symptoms and health status through a medical questionnaire terminal. This response data is sent from the terminal to a server. The server analyzes this questionnaire data using a natural language processing engine to understand and classify the patient's complaints. For example, if a patient answers, "I have a persistent cough and headache," the server analyzes this information and extracts possible medical conditions.

[0228] Suggestions for the medical condition

[0229] The server uses natural language processing results to reference statistical models and medical knowledge databases to list possible medical conditions. This list, along with estimated probabilities, is sent to the terminal and presented to the user (a physician). The physician can then use this suggestion to consider directions for an initial diagnosis.

[0230] Automatic generation of medical records

[0231] The server automatically generates an electronic medical record based on the patient's medical history data and the proposed list of symptoms. The medical record consists of the patient's basic information, symptoms, and proposed diagnosis. The generated medical record can be viewed in real time by the doctor via a terminal, and any necessary information can be added or modified.

[0232] Data storage and management

[0233] The edited medical record information is stored in a highly secure database. The server provides secure access control to the stored data, ensuring that healthcare professionals and patients can access the information based on appropriate access rights. This system allows for the unified management of patient information across different healthcare facilities, enabling consistent treatment.

[0234] As a specific example

[0235] If a patient complains of symptoms such as "chest pain and shortness of breath," the server analyzes this and suggests possible diagnoses such as "myocardial infarction" or "angina." The doctor then reviews this and performs the necessary tests. Based on the test results, the information is added directly to the medical record and saved. This entire process is performed digitally and efficiently, reducing the burden on doctors and ensuring the provision of high-quality medical services.

[0236] As described above, the present invention provides specific means for improving the efficiency and quality of medical operations.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] The user (patient) uses a terminal for medical questionnaires to input answers to questions about their health status and symptoms. Once input is complete, the terminal sends this questionnaire data to the server in digital format.

[0240] Step 2:

[0241] The server passes the received medical questionnaire data to a natural language processing engine for analysis. During this analysis phase, symptoms and health information are identified and converted into necessary medical terminology.

[0242] Step 3:

[0243] The server uses the analysis results to reference a medical knowledge base and statistical models to create a list of predicted medical conditions. This list also includes the estimated probability of each condition.

[0244] Step 4:

[0245] The terminal displays a list of medical conditions received from the server to the user, who is a physician. This allows the physician to review the estimated medical conditions and use them as a reference for initial diagnosis.

[0246] Step 5:

[0247] The server automatically generates an electronic medical record based on the patient interview data and the proposed list of symptoms. The medical record includes the patient's basic information, discovered symptoms, and proposed diagnosis.

[0248] Step 6:

[0249] The terminal displays the generated electronic medical record to the physician and provides editing functions that allow the physician to add or modify information in the medical record as needed.

[0250] Step 7:

[0251] The server stores the final edited medical record information in a secure database. This data is managed with a high level of security and is accessible only to authorized users as needed.

[0252] Step 8:

[0253] Users (healthcare professionals and patients) can access past medical data and manage their own health status based on their permitted access rights.

[0254] (Example 1)

[0255] Next, we will describe Example 1. 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".

[0256] Modern healthcare demands rapid and accurate diagnosis and efficient information management. However, many healthcare institutions rely heavily on manual record creation and information management, which places a burden on healthcare professionals. Therefore, there is a need for systems that streamline the entire process, from patient interviews and diagnosis to record creation and information management, thereby improving the quality of medical care.

[0257] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0258] In this invention, the server includes an algorithm that uses natural language processing to analyze medical information entered by the user and proposes a suspected disease; an automatic generation means that includes a method for automatically generating an electronic medical record file based on the analysis results and user information; an digitization means that provides the generated medical record file to medical professionals in a real-time editable format and stores it in a storage database; and an information protection means that securely manages patient information and related data and provides it based on determined access rights. This makes it possible to streamline the entire process from medical interview to diagnosis and information management, reduce the burden on medical professionals, and improve the quality of medical care.

[0259] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is used to accurately interpret user medical information.

[0260] "Medical history information" refers to data about the patient's health status and symptoms, and is a fundamental source of information for making a diagnosis.

[0261] An "algorithmic method" is a series of steps or calculation methods for solving a specific problem, and this method uses natural language processing to analyze medical interview information and derive a suspected disease.

[0262] An "electronic medical record file" is a digital document that records a patient's medical information and is used to accurately track the process of diagnosis and treatment.

[0263] "Automated generation means" refers to a technology that uses algorithms to automatically create medical records, and is a procedure for efficiently organizing and creating medical information.

[0264] "Digitization means" refers to methods for representing, storing, and managing information in digital format, and is a process for securely storing generated medical records and providing them in an editable format.

[0265] "Information protection measures" are technologies or processes designed to ensure the confidentiality and integrity of data, and are methods for securely managing patient information and restricting access based on authorization.

[0266] This invention is a system that enables efficient patient interviews, diagnostic support, medical record generation, and data management in medical settings. This system consists of users, terminals, and a server, and operates as follows:

[0267] The user first uses a medical questionnaire terminal to answer questions about their physical symptoms and health status. The data entered is easily processed by following the on-screen instructions on the terminal. This information is then transmitted to the server using the terminal's communication capabilities. The communication uses an encrypted protocol to protect the data.

[0268] The server uses natural language processing (NLP) techniques to analyze the received medical questionnaire data. Software used for this includes, for example, Python libraries and natural language processing APIs. This analysis allows for the appropriate interpretation of the patient's symptoms and their conversion into medical terminology and relevant information.

[0269] Based on the analysis results, the server utilizes a generative AI model to estimate possible medical conditions. The estimation process involves referencing medical databases to create a more accurate list of conditions. This list, along with estimated probabilities, is then sent to the terminal.

[0270] The terminal displays a list of generated medical conditions, allowing healthcare professionals to determine their initial diagnostic strategy based on this information. The server automatically generates an electronic medical record based on the analysis results and estimated medical conditions. This record includes patient information, current symptoms, and proposed diagnoses, and is configured to allow physicians to review and edit it in real time as needed.

[0271] For example, if a patient reports "fever and sore throat" and enters their medical history, the server can analyze this information and estimate the patient's condition, such as "viral pharyngitis" or "influenza." This information is automatically included in the medical record and serves as a reference for the doctor.

[0272] An example of a prompt message would be: "This patient's symptoms are 'fever and sore throat.' Please use the AI ​​model to calculate possible conditions and their estimated probabilities." The system would then produce appropriate output based on this input. In this way, the invention enables accurate and efficient information processing in medical settings.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] The user answers questions about their health status and symptoms using a medical questionnaire terminal. The user's input is recorded on the terminal in text format. The terminal encrypts the entered questionnaire data and sends it to the server via a secure communication protocol. The input data is raw symptom information and is ready to be transferred to the server as output.

[0276] Step 2:

[0277] The server initiates natural language processing using the patient interview data received from the terminal. The input is encrypted interview data. The server decrypts it and parses the text using the Python NLTK library. Specifically, the server divides the data into tokens and extracts important keywords. This outputs the patient's complaints as structured data, allowing the server to proceed to the next diagnostic estimation step.

[0278] Step 3:

[0279] Based on the extracted keywords, the server uses a generative AI model to estimate possible medical conditions. The input is keyword data structured by natural language processing. The server refers to statistical models and medical databases to generate a list of medical conditions with estimated probabilities. As output, a list of proposed medical conditions is generated and sent to the next provision step.

[0280] Step 4:

[0281] The server sends the list of estimated medical conditions to the terminal, enabling the medical expert, who is the user, to make a diagnosis based on this information. The input is the list of estimated medical conditions, and the server converts it into a format that can be displayed on the terminal in real time and provides it as output. This information supports rapid decision-making in the medical field.

[0282] Step 5:

[0283] The server automatically generates an electronic medical record based on the interview data and the list of medical conditions. The input is structured patient information and medical condition data. The server integrates this information and creates an electronic medical record based on a template. The output is an editable medical record file that the user can view, edit, and save in real time on the terminal.

[0284] Step 6:

[0285] The server saves the generated medical record in a secure data storage. The input is the generated medical record file. The server appropriately encrypts the patient data and stores it in the database. As output, securely stored medical record information is generated for future access. This information can be safely utilized by appropriate users based on access rights.

[0286] (Application Example 1)

[0287] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0288] Reducing the workload in healthcare settings and providing efficient medical care are crucial challenges. In particular, systems for home health management and daily health checks contribute not only to reducing the burden on medical facilities but also to maintaining the health of the general public. However, conventional systems have been difficult to use in homes, posing challenges in real-time health assessment and appropriate management of medical information.

[0289] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0290] This invention includes a server that analyzes medical interview data using natural language processing and proposes possible medical conditions, a server that automatically generates an electronic medical record based on the analysis results, a server that provides the generated medical record in an editable format and stores it in a medical information database, a server that acquires and analyzes voice data to evaluate the patient's health status at home, and a server that presents health management information based on the evaluation results. This enables efficient and consistent health management both in medical settings and at home.

[0291] "Natural language processing" refers to the ability of computers to understand and analyze human language, and is a technology that extracts and generates information based on text and audio data.

[0292] "Medical interview data" refers to information that patients provide when answering questions about their health status and symptoms, and serves as the basis for analyzing and diagnosing their medical condition.

[0293] The "means of suggesting medical conditions" refers to a function that lists and presents possible health conditions and diseases based on data analyzed using natural language processing.

[0294] "Automatic electronic medical record generation" is a system that creates a patient's medical record in digital format based on analyzed medical history data and suggested medical condition information.

[0295] "Security management measures" refer to systems that securely protect patients' medical information and data, and restrict access to and use of that information based on appropriate access rights.

[0296] "Means for acquiring audio data" refers to technologies that collect user speech using microphones or speech recognition devices.

[0297] A "means for evaluating health status" refers to a system that determines and evaluates a user's health status based on acquired voice data and analysis results.

[0298] "Means of providing health management information" refers to a function that provides users with improvement measures and precautions based on their analyzed health status.

[0299] To realize this invention, a system operating in a smart home is required. To support in-home health management, a combination of a server, an internet-connected terminal, and a voice recognition device for user interaction will be used.

[0300] The server converts user speech into text data using speech recognition technologies such as Google Cloud Speech-to-Text API or Amazon Transcribe. This text data is analyzed using OpenAI's GPT-3 and BERT natural language processing engines to suggest possible medical conditions. Based on the analyzed data, an electronic medical record is generated and stored in a medical information database for security management.

[0301] The terminal installed in the home provides users with feedback on analysis results and health management suggestions via voice and display screens. This information is presented as measures to improve health and precautions, playing a role in supporting daily health management. For example, if a user voice-inputs "I have a headache today," the system operates in the background, the server analyzes the information, and presents possible causes and minor remedies visually or audibly.

[0302] As a specific example, the prompt text can be described as follows. "Please teach me how to deal with the situation when a user complains of a headache. Please list the possible causes and the coping methods that can be done at home." As a result, an autonomous system that supports the user's health maintenance functions within the home.

[0303] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0304] Step 1:

[0305] The user conveys their health status and symptoms to the voice input device. This voice input becomes the first data source for the system. The acquired voice data is converted into text data using voice recognition technology on the terminal. Through this conversion process, data in text format that can be subsequently analyzed is obtained.

[0306] Step 2:

[0307] The terminal sends the text data to the server. The server receives this text and analyzes the data using a natural language processing engine. Specifically, the input text is passed through OpenAI's GPT-3 or BERT to systematically analyze the meaning and extract possible medical conditions and related information. Through this analysis, a hypothesis about the health status is generated.

[0308] Step 3:

[0309] The server makes a proposal for the medical condition based on the extracted information and generates an electronic medical record. The electronic medical record contains the user's basic information, chief complaint, proposed medical condition candidates, etc. The generated medical record is provided to the terminal in a form that can be further confirmed and corrected by the user or medical professionals. Through this medical record generation, unified management of health information becomes possible.

[0310] Step 4:

[0311] The server securely stores the generated electronic medical records and analysis results in a medical information database. This stored information can be used as a record of the user's past health history to aid in future diagnoses and health management.

[0312] Step 5:

[0313] The device provides users with health management suggestions and advice based on analysis results and medical record information. These suggestions are fed back to the user via voice or display, supporting daily health management. For example, it might offer advice such as, "We recommend you drink more water."

[0314] Through these steps, users can easily monitor their health status at home and decide whether to seek medical attention if necessary.

[0315] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0316] This invention is a medical support system for the medical field, which includes analysis of medical interview data, suggestion of medical conditions, automatic generation of electronic medical records, and an emotion engine that recognizes the user's emotions. This emotion engine analyzes the patient's emotional state and uses it to supplement data in the diagnostic process and adjust the suggested content.

[0317] Medical history and emotional recognition

[0318] The user (patient) uses a device to answer questions about their health status by typing or speaking. During this process, the emotion engine analyzes facial expressions and tone of voice through the camera and microphone to recognize the patient's emotional state (e.g., anxiety, stress, relief). The recognized emotional information is sent to the server as part of the medical questionnaire data.

[0319] Data analysis and disease state recommendations

[0320] The server analyzes the patient's interview data and recognized emotional information using a natural language processing engine. The analysis results support more accurate predictions of the patient's condition, taking into account the patient's emotional state. For example, if a patient exhibits severe anxiety, this information will influence the stress-related condition suggestions.

[0321] Electronic medical record generation

[0322] Based on the analysis results, the server automatically generates an electronic medical record. The generated record includes the patient's basic health information, detected symptoms, recommended diagnosis, and emotional information. The terminal provides this record to healthcare professionals in an editable format, allowing for adjustments as needed.

[0323] Data storage and security management

[0324] Edited medical record information is stored in a highly secure database on the server. Emotional information is also handled as part of data management. This allows users (healthcare professionals) to provide more consistent treatment based on information including the patient's emotional state.

[0325] Specific example

[0326] For example, if a patient presents with symptoms of stomach pain while also showing clear signs of anxiety, the server will analyze this emotional state and suggest conditions such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses and provide care that take the patient's psychological state into account.

[0327] This system, incorporating an emotional engine, will provide multifaceted support for physicians' diagnostic work and enable the provision of medical care that takes into account the patient's psychological state.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The user (patient) uses a medical questionnaire terminal to answer questions about their health status and symptoms via text input or voice input. During this process, the terminal records the patient's facial expressions and tone of voice using a camera and microphone, collecting emotional data.

[0331] Step 2:

[0332] The device transmits the collected medical interview data and emotional data to the server. An encryption protocol is used during transmission to ensure data security.

[0333] Step 3:

[0334] The server uses a natural language processing engine to analyze the medical interview data. Through this analysis, it organizes the extracted information about symptoms and health, and simultaneously evaluates emotional data using an emotion engine to identify the patient's emotional state.

[0335] Step 4:

[0336] The server references a medical knowledge base based on analysis results and emotional information to list possible medical conditions. This list includes the severity and probability of the predicted conditions, as well as consideration of the patient's emotional state.

[0337] Step 5:

[0338] The created list of medical conditions is sent to the terminal and displayed to the user (doctor). The doctor uses this information to help determine the subsequent diagnostic course.

[0339] Step 6:

[0340] The server automatically generates an electronic medical record based on the patient's interview data, emotional data, and a list of suggested conditions. This record includes the patient's symptoms, suggested diagnoses, and perceived emotional states.

[0341] Step 7:

[0342] The terminal provides the generated electronic medical record to the physician in an editable format. The physician can then add feedback and additional information to this record.

[0343] Step 8:

[0344] The edited medical record data is stored in a secure database on the server. The stored data is protected by appropriate access controls, allowing healthcare professionals to access it as needed.

[0345] This entire process allows for patient-centered care and enables the provision of more personalized medical services.

[0346] (Example 2)

[0347] Next, we will describe Example 2. 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".

[0348] Conventional medical support systems often perform data analysis without considering emotional states, making it difficult to make diagnoses that adequately reflect the patient's psychological state. Furthermore, the lack of mechanisms to utilize post-treatment evaluations within the system limited the ability to continuously improve the accuracy of medical care.

[0349] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0350] In this invention, the server includes means for analyzing medical interview information using natural language processing and proposing a health status, means for automatically generating electronic records, and means for analyzing the user's emotional state using an emotion recognition engine and integrating it with the medical interview information. This makes it possible to generate diagnoses and records that take into account the patient's emotional state.

[0351] "Natural language processing" is the technology that enables computers to understand, generate, and analyze human language.

[0352] "Medical interview information" refers to data about a patient's health status and symptoms that they provide to a medical institution.

[0353] "Health status" refers to an indicator of a patient's physical and psychological health.

[0354] "Electronic records" are digital documents generated for the purpose of electronically storing and managing medical information about patients.

[0355] An "emotion recognition engine" is a system that analyzes a user's facial expressions and voice to identify their emotional state.

[0356] A "user" is defined as the entity that operates the system and inputs or verifies information.

[0357] "Analysis accuracy" is an indicator used to evaluate the accuracy and reliability of data analysis.

[0358] "Learning techniques" refer to algorithms and methods that enable a system to gain experience and improve its performance.

[0359] This invention is a medical support system that provides a process in which a user (patient) inputs health-related information, and a server analyzes the health status based on that information and generates an electronic record. By using an emotion recognition engine, this system makes it possible to incorporate the patient's psychological state into the diagnosis.

[0360] Users input health information using a terminal. The terminal has an interface that accepts keyboard input or voice responses. The terminal also captures facial expressions and tone of voice using its built-in camera and microphone, and an emotion recognition engine analyzes this data. The analyzed emotion information is integrated into the medical questionnaire information sent to the server.

[0361] The server uses natural language processing technology to analyze the received medical history and emotional information. A generative AI model is used for this analysis, resulting in the generation of suggestions regarding the patient's health status. Emotional information is used to further refine the suggestions.

[0362] Once the analysis is complete, the server automatically generates an electronic record. This electronic record includes the patient's basic information, analyzed symptoms, suggested diagnosis, and emotional information. The terminal can display this record in a format that healthcare professionals can edit as needed.

[0363] For example, if a patient complains of stomach pain and expresses anxiety during a consultation, the server will examine this information and suggest possibilities such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses that take the patient's psychological state into account.

[0364] An example of a prompt message would be, "Please list possible health conditions when a user complains of stomach pain and expresses anxiety." This allows the system to comprehensively analyze the user's condition and make appropriate suggestions.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The user answers questions about their health status by typing or speaking using the device. The device receives the input data (text or voice data) and converts it into a digital format. During this process, the camera and microphone simultaneously capture facial expressions and voice tone, generating emotion data.

[0368] Step 2:

[0369] The terminal sends the entered questionnaire data and recognized emotion data to the server. Specifically, the questionnaire data is in text format, and the emotion data is encoded as analyzed psychological indicators, and these are sent together. This transmitted data becomes the input for the next analysis step.

[0370] Step 3:

[0371] The server analyzes the received questionnaire data and emotional data using a natural language processing engine. The analysis employs a generative AI model to integrate text and emotional information and calculate probabilities related to the user's health condition. Based on these results, a list of hypothesized health conditions is output.

[0372] Step 4:

[0373] The server automatically generates an electronic record based on the analysis results and suggested health status. This electronic record includes the patient's basic information, detected symptoms, suggested health status name, and emotional information. The generated record is output in digital format and provided to healthcare professionals.

[0374] Step 5:

[0375] The terminal displays the generated electronic records to healthcare professionals. Healthcare professionals can edit these records as needed, adjusting them to finalize the clinical information. The edited records are then returned to the server for storage.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0378] In modern elderly care settings, a challenge is to appropriately understand the emotional state of the elderly and provide care based on that understanding. Care providers are required to understand the psychological and emotional needs of the elderly and respond accordingly, but this is sometimes difficult to achieve due to staffing shortages and technological limitations. Therefore, the development of support tools utilizing emotion recognition technology is necessary.

[0379] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0380] In this invention, the server includes means for analyzing medical interview data using natural language processing and suggesting possible medical conditions, means for automatically generating an electronic medical record based on the analysis results, and means for recognizing the user's emotional state from acoustic or visual data and adjusting the suggested content based on emotions. This makes it possible to suggest dialogue content and care actions that correspond to the emotional state.

[0381] "Natural language processing" is a technology that allows computers to understand and analyze human language and extract meaningful information.

[0382] "Medical interview data" refers to information about the health status collected from patients or users.

[0383] An "electronic medical record" is a record-keeping system for storing and managing patients' health information and medical history in a digital format.

[0384] "Security management" refers to the measures and systems in place to protect patient information and medical data from unauthorized access and leakage.

[0385] "Emotion recognition" is a technology that analyzes acoustic or visual data to identify the emotional state of a subject.

[0386] "Care providers" refer to people who are responsible for providing care and support to users or patients in nursing homes and medical institutions.

[0387] "Emotion-based proposals" are a method of adjusting and proposing the content of dialogue and actions according to the perceived emotional state.

[0388] This invention realizes a system that provides care providers in nursing care settings with dialogue and behavioral suggestions based on the emotional state of elderly individuals. The server uses natural language processing technology to analyze user interview data and predict possible medical conditions. The main software used in this process includes a natural language processing engine and an emotion recognition library. Specifically, the IBM Watson, a common natural language processing engine, is used, and the Microsoft Azure Emotion API is used as the emotion recognition library.

[0389] The server utilizes acoustic and visual data to recognize the user's emotional state in real time. This enables the automatic generation of electronic medical records based on analysis results combined with interview data. The generated electronic medical records are then used as an interface to provide care providers with appropriate suggestions tailored to the user's emotional state.

[0390] The terminal, via devices such as smart glasses, presents specific suggestions regarding conversation content and actions in the care setting. For example, if an elderly person shows anxiety, the server generates a prompt such as, "How about talking about a happy memory from the past?" and provides this suggestion to the care staff.

[0391] For example, if a caregiver is talking to an elderly person and the user says, "I don't really want to do anything today," the generative AI model, based on past experience, will generate a prompt such as, "Let's talk about a hobby you used to enjoy," and present it to the care staff. In this way, it is possible to support appropriate care tailored to the user's emotional state.

[0392] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0393] Step 1:

[0394] The user inputs speech and facial expressions through smart glasses. The device captures audio and video data using its camera and microphone and sends it to a server. The input data is analyzed acoustically and visually using an emotion recognition library and output as an emotional state (e.g., joy, anxiety, calmness).

[0395] Step 2:

[0396] The server receives emotional states derived from the user's acoustic and visual data as input. A natural language processing engine is used to analyze the questionnaire data and emotional states. Based on the results, an electronic medical record reflecting the user's health status is automatically generated and stored in a database. This electronic medical record includes recommendations based on the detected medical conditions and emotional states.

[0397] Step 3:

[0398] The terminal displays suggestions based on the electronic medical record and emotional state provided by the server. Specifically, an AI model generates prompts tailored to the user's emotional state, instructing caregivers on recommended conversations and actions. For example, a prompt such as "Try talking about a fun activity from the past" might be presented.

[0399] Step 4:

[0400] Care providers use prompts displayed on the terminal to communicate with clients and conduct care activities. If responses or new information are obtained from the client, they return to step 1 to acquire new emotional state and interview data and continue the process. This allows for flexible, real-time responses.

[0401] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0402] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0403] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0404] [Third Embodiment]

[0405] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0406] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0407] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0408] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0409] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0410] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0411] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0412] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0413] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0414] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0415] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0416] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0417] This invention relates to a system for medical interviews, symptom suggestion, automatic medical record generation, and data management in a medical setting, and has the following configuration and operation.

[0418] Medical history and analysis

[0419] Users answer questions about their symptoms and health status through a medical questionnaire terminal. This response data is sent from the terminal to a server. The server analyzes this questionnaire data using a natural language processing engine to understand and classify the patient's complaints. For example, if a patient answers, "I have a persistent cough and headache," the server analyzes this information and extracts possible medical conditions.

[0420] Suggestions for the medical condition

[0421] The server uses natural language processing results to reference statistical models and medical knowledge databases to list possible medical conditions. This list, along with estimated probabilities, is sent to the terminal and presented to the user (a physician). The physician can then use this suggestion to consider directions for an initial diagnosis.

[0422] Automatic generation of medical records

[0423] The server automatically generates an electronic medical record based on the patient's medical history data and the proposed list of symptoms. The medical record consists of the patient's basic information, symptoms, and proposed diagnosis. The generated medical record can be viewed in real time by the doctor via a terminal, and any necessary information can be added or modified.

[0424] Data storage and management

[0425] The edited medical record information is stored in a highly secure database. The server provides secure access control to the stored data, ensuring that healthcare professionals and patients can access the information based on appropriate access rights. This system allows for the unified management of patient information across different healthcare facilities, enabling consistent treatment.

[0426] As a specific example

[0427] If a patient complains of symptoms such as "chest pain and shortness of breath," the server analyzes this and suggests possible diagnoses such as "myocardial infarction" or "angina." The doctor then reviews this and performs the necessary tests. Based on the test results, the information is added directly to the medical record and saved. This entire process is performed digitally and efficiently, reducing the burden on doctors and ensuring the provision of high-quality medical services.

[0428] As described above, the present invention provides specific means for improving the efficiency and quality of medical operations.

[0429] The following describes the processing flow.

[0430] Step 1:

[0431] The user (patient) uses a terminal for medical questionnaires to input answers to questions about their health status and symptoms. Once input is complete, the terminal sends this questionnaire data to the server in digital format.

[0432] Step 2:

[0433] The server passes the received medical questionnaire data to a natural language processing engine for analysis. During this analysis phase, symptoms and health information are identified and converted into necessary medical terminology.

[0434] Step 3:

[0435] The server uses the analysis results to reference a medical knowledge base and statistical models to create a list of predicted medical conditions. This list also includes the estimated probability of each condition.

[0436] Step 4:

[0437] The terminal displays a list of medical conditions received from the server to the user, who is a physician. This allows the physician to review the estimated medical conditions and use them as a reference for initial diagnosis.

[0438] Step 5:

[0439] The server automatically generates an electronic medical record based on the patient interview data and the proposed list of symptoms. The medical record includes the patient's basic information, discovered symptoms, and proposed diagnosis.

[0440] Step 6:

[0441] The terminal displays the generated electronic medical record to the physician and provides editing functions that allow the physician to add or modify information in the medical record as needed.

[0442] Step 7:

[0443] The server stores the final edited medical record information in a secure database. This data is managed with a high level of security and is accessible only to authorized users as needed.

[0444] Step 8:

[0445] Users (healthcare professionals and patients) can access past medical data and manage their own health status based on their permitted access rights.

[0446] (Example 1)

[0447] Next, we will describe Example 1. 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."

[0448] Modern healthcare demands rapid and accurate diagnosis and efficient information management. However, many healthcare institutions rely heavily on manual record creation and information management, which places a burden on healthcare professionals. Therefore, there is a need for systems that streamline the entire process, from patient interviews and diagnosis to record creation and information management, thereby improving the quality of medical care.

[0449] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0450] In this invention, the server includes an algorithm that uses natural language processing to analyze medical information entered by the user and proposes a suspected disease; an automatic generation means that includes a method for automatically generating an electronic medical record file based on the analysis results and user information; an digitization means that provides the generated medical record file to medical professionals in a real-time editable format and stores it in a storage database; and an information protection means that securely manages patient information and related data and provides it based on determined access rights. This makes it possible to streamline the entire process from medical interview to diagnosis and information management, reduce the burden on medical professionals, and improve the quality of medical care.

[0451] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is used to accurately interpret user medical information.

[0452] "Medical history information" refers to data about the patient's health status and symptoms, and is a fundamental source of information for making a diagnosis.

[0453] An "algorithmic method" is a series of steps or calculation methods for solving a specific problem, and this method uses natural language processing to analyze medical interview information and derive a suspected disease.

[0454] An "electronic medical record file" is a digital document that records a patient's medical information and is used to accurately track the process of diagnosis and treatment.

[0455] "Automated generation means" refers to a technology that uses algorithms to automatically create medical records, and is a procedure for efficiently organizing and creating medical information.

[0456] "Digitization means" refers to methods for representing, storing, and managing information in digital format, and is a process for securely storing generated medical records and providing them in an editable format.

[0457] "Information protection measures" are technologies or processes designed to ensure the confidentiality and integrity of data, and are methods for securely managing patient information and restricting access based on authorization.

[0458] This invention is a system that enables efficient patient interviews, diagnostic support, medical record generation, and data management in medical settings. This system consists of users, terminals, and a server, and operates as follows:

[0459] The user first uses a medical questionnaire terminal to answer questions about their physical symptoms and health status. The data entered is easily processed by following the on-screen instructions on the terminal. This information is then transmitted to the server using the terminal's communication capabilities. The communication uses an encrypted protocol to protect the data.

[0460] The server uses natural language processing (NLP) techniques to analyze the received medical questionnaire data. Software used for this includes, for example, Python libraries and natural language processing APIs. This analysis allows for the appropriate interpretation of the patient's symptoms and their conversion into medical terminology and relevant information.

[0461] Based on the analysis results, the server utilizes a generative AI model to estimate possible medical conditions. The estimation process involves referencing medical databases to create a more accurate list of conditions. This list, along with estimated probabilities, is then sent to the terminal.

[0462] The terminal displays a list of generated medical conditions, allowing healthcare professionals to determine their initial diagnostic strategy based on this information. The server automatically generates an electronic medical record based on the analysis results and estimated medical conditions. This record includes patient information, current symptoms, and proposed diagnoses, and is configured to allow physicians to review and edit it in real time as needed.

[0463] For example, if a patient reports "fever and sore throat" and enters their medical history, the server can analyze this information and estimate the patient's condition, such as "viral pharyngitis" or "influenza." This information is automatically included in the medical record and serves as a reference for the doctor.

[0464] An example of a prompt message would be: "This patient's symptoms are 'fever and sore throat.' Please use the AI ​​model to calculate possible conditions and their estimated probabilities." The system would then produce appropriate output based on this input. In this way, the invention enables accurate and efficient information processing in medical settings.

[0465] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0466] Step 1:

[0467] The user answers questions about their health status and symptoms using a medical questionnaire terminal. The user's input is recorded on the terminal in text format. The terminal encrypts the entered questionnaire data and sends it to the server via a secure communication protocol. The input data is raw symptom information and is ready to be transferred to the server as output.

[0468] Step 2:

[0469] The server initiates natural language processing using the patient interview data received from the terminal. The input is encrypted interview data. The server decrypts it and parses the text using the Python NLTK library. Specifically, the server divides the data into tokens and extracts important keywords. This outputs the patient's complaints as structured data, allowing the server to proceed to the next diagnostic estimation step.

[0470] Step 3:

[0471] The server uses a generative AI model to estimate possible medical conditions based on extracted keywords. The input is keyword data structured using natural language processing. The server refers to statistical models and medical databases to generate a list of medical conditions with estimated probabilities. The output is a list of proposed medical conditions, which is then sent to the next serving step.

[0472] Step 4:

[0473] The server sends a list of estimated medical conditions to the terminal, allowing the user, a healthcare professional, to make a diagnosis based on this information. The input is a list of estimated medical conditions, which the server converts into a format that can be displayed on the terminal in real time and provides as output. This information supports rapid decision-making in the medical field.

[0474] Step 5:

[0475] The server automatically generates electronic medical records based on patient interview data and a list of medical conditions. Input consists of structured patient information and medical condition data. The server integrates this information and creates the electronic medical record based on a template. The output is an editable medical record file, which users can view, edit, and save in real time on their terminals.

[0476] Step 6:

[0477] The server stores the generated medical records in secure data storage. The input is the generated medical record file. The server properly encrypts the patient data and stores it in the database. The output is securely stored medical record information, ready for later access. This information can be securely used by the appropriate users based on access permissions.

[0478] (Application Example 1)

[0479] Next, we will explain Application Example 1. In the following explanation, 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."

[0480] Reducing the workload in healthcare settings and providing efficient medical care are crucial challenges. In particular, systems for home health management and daily health checks contribute not only to reducing the burden on medical facilities but also to maintaining the health of the general public. However, conventional systems have been difficult to use in homes, posing challenges in real-time health assessment and appropriate management of medical information.

[0481] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0482] This invention includes a server that analyzes medical interview data using natural language processing and proposes possible medical conditions, a server that automatically generates an electronic medical record based on the analysis results, a server that provides the generated medical record in an editable format and stores it in a medical information database, a server that acquires and analyzes voice data to evaluate the patient's health status at home, and a server that presents health management information based on the evaluation results. This enables efficient and consistent health management both in medical settings and at home.

[0483] "Natural language processing" refers to the ability of computers to understand and analyze human language, and is a technology that extracts and generates information based on text and audio data.

[0484] "Medical interview data" refers to information that patients provide when answering questions about their health status and symptoms, and serves as the basis for analyzing and diagnosing their medical condition.

[0485] The "means of suggesting medical conditions" refers to a function that lists and presents possible health conditions and diseases based on data analyzed using natural language processing.

[0486] "Automatic electronic medical record generation" is a system that creates a patient's medical record in digital format based on analyzed medical history data and suggested medical condition information.

[0487] "Security management measures" refer to systems that securely protect patients' medical information and data, and restrict access to and use of that information based on appropriate access rights.

[0488] "Means for acquiring audio data" refers to technologies that collect user speech using microphones or speech recognition devices.

[0489] A "means for evaluating health status" refers to a system that determines and evaluates a user's health status based on acquired voice data and analysis results.

[0490] "Means of providing health management information" refers to a function that provides users with improvement measures and precautions based on their analyzed health status.

[0491] To realize this invention, a system operating in a smart home is required. To support in-home health management, a combination of a server, an internet-connected terminal, and a voice recognition device for user interaction will be used.

[0492] The server converts user speech into text data using speech recognition technologies such as Google Cloud Speech-to-Text API or Amazon Transcribe. This text data is analyzed using OpenAI's GPT-3 and BERT natural language processing engines to suggest possible medical conditions. Based on the analyzed data, an electronic medical record is generated and stored in a medical information database for security management.

[0493] The terminal installed in the home provides users with feedback on analysis results and health management suggestions via voice and display screens. This information is presented as measures to improve health and precautions, playing a role in supporting daily health management. For example, if a user voice-inputs "I have a headache today," the system operates in the background, the server analyzes the information, and presents possible causes and minor remedies visually or audibly.

[0494] For example, the prompt could be written as follows: "Please tell me what to do if the user complains of a headache. Please list possible causes and remedies that can be done at home." This would enable a self-sustaining system to function within the home to support the user's health.

[0495] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0496] Step 1:

[0497] The user communicates their health status and symptoms to a voice input device. This voice input becomes the system's initial data source. The acquired voice data is converted into text data using speech recognition technology on the device. This conversion process yields text data that can be subsequently analyzed.

[0498] Step 2:

[0499] The terminal sends text data to the server. The server receives this text and analyzes the data using a natural language processing engine. Specifically, the input text is passed through OpenAI's GPT-3 or BERT to systematically analyze its meaning and extract possible medical conditions and related information. This analysis generates hypotheses about the health status.

[0500] Step 3:

[0501] The server suggests medical conditions based on the extracted information and generates an electronic medical record. This record includes the user's basic information, chief complaint, and suggested medical conditions. The generated record is then provided to the terminal in a format that can be reviewed and modified by the user and medical professionals. This record generation process enables unified management of health information.

[0502] Step 4:

[0503] The server securely stores the generated electronic medical records and analysis results in a medical information database. This stored information can be used as a record of the user's past health history to aid in future diagnoses and health management.

[0504] Step 5:

[0505] The device provides users with health management suggestions and advice based on analysis results and medical record information. These suggestions are fed back to the user via voice or display, supporting daily health management. For example, it might offer advice such as, "We recommend you drink more water."

[0506] Through these steps, users can easily monitor their health status at home and decide whether to seek medical attention if necessary.

[0507] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0508] This invention is a medical support system for the medical field, which includes analysis of medical interview data, suggestion of medical conditions, automatic generation of electronic medical records, and an emotion engine that recognizes the user's emotions. This emotion engine analyzes the patient's emotional state and uses it to supplement data in the diagnostic process and adjust the suggested content.

[0509] Medical history and emotional recognition

[0510] The user (patient) uses a device to answer questions about their health status by typing or speaking. During this process, the emotion engine analyzes facial expressions and tone of voice through the camera and microphone to recognize the patient's emotional state (e.g., anxiety, stress, relief). The recognized emotional information is sent to the server as part of the medical questionnaire data.

[0511] Data analysis and disease state recommendations

[0512] The server analyzes the patient's interview data and recognized emotional information using a natural language processing engine. The analysis results support more accurate predictions of the patient's condition, taking into account the patient's emotional state. For example, if a patient exhibits severe anxiety, this information will influence the stress-related condition suggestions.

[0513] Electronic medical record generation

[0514] Based on the analysis results, the server automatically generates an electronic medical record. The generated record includes the patient's basic health information, detected symptoms, recommended diagnosis, and emotional information. The terminal provides this record to healthcare professionals in an editable format, allowing for adjustments as needed.

[0515] Data storage and security management

[0516] Edited medical record information is stored in a highly secure database on the server. Emotional information is also handled as part of data management. This allows users (healthcare professionals) to provide more consistent treatment based on information including the patient's emotional state.

[0517] Specific example

[0518] For example, if a patient presents with symptoms of stomach pain while also showing clear signs of anxiety, the server will analyze this emotional state and suggest conditions such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses and provide care that take the patient's psychological state into account.

[0519] This system, incorporating an emotional engine, will provide multifaceted support for physicians' diagnostic work and enable the provision of medical care that takes into account the patient's psychological state.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] The user (patient) uses a medical questionnaire terminal to answer questions about their health status and symptoms via text input or voice input. During this process, the terminal records the patient's facial expressions and tone of voice using a camera and microphone, collecting emotional data.

[0523] Step 2:

[0524] The device transmits the collected medical interview data and emotional data to the server. An encryption protocol is used during transmission to ensure data security.

[0525] Step 3:

[0526] The server uses a natural language processing engine to analyze the medical interview data. Through this analysis, it organizes the extracted information about symptoms and health, and simultaneously evaluates emotional data using an emotion engine to identify the patient's emotional state.

[0527] Step 4:

[0528] The server references a medical knowledge base based on analysis results and emotional information to list possible medical conditions. This list includes the severity and probability of the predicted conditions, as well as consideration of the patient's emotional state.

[0529] Step 5:

[0530] The created list of medical conditions is sent to the terminal and displayed to the user (doctor). The doctor uses this information to help determine the subsequent diagnostic course.

[0531] Step 6:

[0532] The server automatically generates an electronic medical record based on the patient's interview data, emotional data, and a list of suggested conditions. This record includes the patient's symptoms, suggested diagnoses, and perceived emotional states.

[0533] Step 7:

[0534] The terminal provides the generated electronic medical record to the physician in an editable format. The physician can then add feedback and additional information to this record.

[0535] Step 8:

[0536] The edited medical record data is stored in a secure database on the server. The stored data is protected by appropriate access controls, allowing healthcare professionals to access it as needed.

[0537] This entire process allows for patient-centered care and enables the provision of more personalized medical services.

[0538] (Example 2)

[0539] Next, we will describe Example 2. 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."

[0540] Conventional medical support systems often perform data analysis without considering emotional states, making it difficult to make diagnoses that adequately reflect the patient's psychological state. Furthermore, the lack of mechanisms to utilize post-treatment evaluations within the system limited the ability to continuously improve the accuracy of medical care.

[0541] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0542] In this invention, the server includes means for analyzing medical interview information using natural language processing and proposing a health status, means for automatically generating electronic records, and means for analyzing the user's emotional state using an emotion recognition engine and integrating it with the medical interview information. This makes it possible to generate diagnoses and records that take into account the patient's emotional state.

[0543] "Natural language processing" is the technology that enables computers to understand, generate, and analyze human language.

[0544] "Medical interview information" refers to data about a patient's health status and symptoms that they provide to a medical institution.

[0545] "Health status" refers to an indicator of a patient's physical and psychological health.

[0546] "Electronic records" are digital documents generated for the purpose of electronically storing and managing medical information about patients.

[0547] An "emotion recognition engine" is a system that analyzes a user's facial expressions and voice to identify their emotional state.

[0548] A "user" is defined as the entity that operates the system and inputs or verifies information.

[0549] "Analysis accuracy" is an indicator used to evaluate the accuracy and reliability of data analysis.

[0550] "Learning techniques" refer to algorithms and methods that enable a system to gain experience and improve its performance.

[0551] This invention is a medical support system that provides a process in which a user (patient) inputs health-related information, and a server analyzes the health status based on that information and generates an electronic record. By using an emotion recognition engine, this system makes it possible to incorporate the patient's psychological state into the diagnosis.

[0552] Users input health information using a terminal. The terminal has an interface that accepts keyboard input or voice responses. The terminal also captures facial expressions and tone of voice using its built-in camera and microphone, and an emotion recognition engine analyzes this data. The analyzed emotion information is integrated into the medical questionnaire information sent to the server.

[0553] The server uses natural language processing technology to analyze the received medical history and emotional information. A generative AI model is used for this analysis, resulting in the generation of suggestions regarding the patient's health status. Emotional information is used to further refine the suggestions.

[0554] Once the analysis is complete, the server automatically generates an electronic record. This electronic record includes the patient's basic information, analyzed symptoms, suggested diagnosis, and emotional information. The terminal can display this record in a format that healthcare professionals can edit as needed.

[0555] For example, if a patient complains of stomach pain and expresses anxiety during a consultation, the server will examine this information and suggest possibilities such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses that take the patient's psychological state into account.

[0556] An example of a prompt message would be, "Please list possible health conditions when a user complains of stomach pain and expresses anxiety." This allows the system to comprehensively analyze the user's condition and make appropriate suggestions.

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1:

[0559] The user answers questions about their health status by typing or speaking using the device. The device receives the input data (text or voice data) and converts it into a digital format. During this process, the camera and microphone simultaneously capture facial expressions and voice tone, generating emotion data.

[0560] Step 2:

[0561] The terminal sends the entered questionnaire data and recognized emotion data to the server. Specifically, the questionnaire data is in text format, and the emotion data is encoded as analyzed psychological indicators, and these are sent together. This transmitted data becomes the input for the next analysis step.

[0562] Step 3:

[0563] The server analyzes the received questionnaire data and emotional data using a natural language processing engine. The analysis employs a generative AI model to integrate text and emotional information and calculate probabilities related to the user's health condition. Based on these results, a list of hypothesized health conditions is output.

[0564] Step 4:

[0565] The server automatically generates an electronic record based on the analysis results and suggested health status. This electronic record includes the patient's basic information, detected symptoms, suggested health status name, and emotional information. The generated record is output in digital format and provided to healthcare professionals.

[0566] Step 5:

[0567] The terminal displays the generated electronic records to healthcare professionals. Healthcare professionals can edit these records as needed, adjusting them to finalize the clinical information. The edited records are then returned to the server for storage.

[0568] (Application Example 2)

[0569] Next, we will explain application example 2. In the following explanation, 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."

[0570] In modern elderly care settings, a challenge is to appropriately understand the emotional state of the elderly and provide care based on that understanding. Care providers are required to understand the psychological and emotional needs of the elderly and respond accordingly, but this is sometimes difficult to achieve due to staffing shortages and technological limitations. Therefore, the development of support tools utilizing emotion recognition technology is necessary.

[0571] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0572] In this invention, the server includes means for analyzing medical interview data using natural language processing and suggesting possible medical conditions, means for automatically generating an electronic medical record based on the analysis results, and means for recognizing the user's emotional state from acoustic or visual data and adjusting the suggested content based on emotions. This makes it possible to suggest dialogue content and care actions that correspond to the emotional state.

[0573] "Natural language processing" is a technology that allows computers to understand and analyze human language and extract meaningful information.

[0574] "Medical interview data" refers to information about the health status collected from patients or users.

[0575] An "electronic medical record" is a record-keeping system for storing and managing patients' health information and medical history in a digital format.

[0576] "Security management" refers to the measures and systems in place to protect patient information and medical data from unauthorized access and leakage.

[0577] "Emotion recognition" is a technology that analyzes acoustic or visual data to identify the emotional state of a subject.

[0578] "Care providers" refer to people who are responsible for providing care and support to users or patients in nursing homes and medical institutions.

[0579] "Emotion-based proposals" are a method of adjusting and proposing the content of dialogue and actions according to the perceived emotional state.

[0580] This invention realizes a system that provides care providers in nursing care settings with dialogue and behavioral suggestions based on the emotional state of elderly individuals. The server uses natural language processing technology to analyze user interview data and predict possible medical conditions. The main software used in this process includes a natural language processing engine and an emotion recognition library. Specifically, the IBM Watson, a common natural language processing engine, is used, and the Microsoft Azure Emotion API is used as the emotion recognition library.

[0581] The server utilizes acoustic and visual data to recognize the user's emotional state in real time. This enables the automatic generation of electronic medical records based on analysis results combined with interview data. The generated electronic medical records are then used as an interface to provide care providers with appropriate suggestions tailored to the user's emotional state.

[0582] The terminal, via devices such as smart glasses, presents specific suggestions regarding conversation content and actions in the care setting. For example, if an elderly person shows anxiety, the server generates a prompt such as, "How about talking about a happy memory from the past?" and provides this suggestion to the care staff.

[0583] For example, if a caregiver is talking to an elderly person and the user says, "I don't really want to do anything today," the generative AI model, based on past experience, will generate a prompt such as, "Let's talk about a hobby you used to enjoy," and present it to the care staff. In this way, it is possible to support appropriate care tailored to the user's emotional state.

[0584] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0585] Step 1:

[0586] The user inputs speech and facial expressions through smart glasses. The device captures audio and video data using its camera and microphone and sends it to a server. The input data is analyzed acoustically and visually using an emotion recognition library and output as an emotional state (e.g., joy, anxiety, calmness).

[0587] Step 2:

[0588] The server receives emotional states derived from the user's acoustic and visual data as input. A natural language processing engine is used to analyze the questionnaire data and emotional states. Based on the results, an electronic medical record reflecting the user's health status is automatically generated and stored in a database. This electronic medical record includes recommendations based on the detected medical conditions and emotional states.

[0589] Step 3:

[0590] The terminal displays suggestions based on the electronic medical record and emotional state provided by the server. Specifically, an AI model generates prompts tailored to the user's emotional state, instructing caregivers on recommended conversations and actions. For example, a prompt such as "Try talking about a fun activity from the past" might be presented.

[0591] Step 4:

[0592] Care providers use prompts displayed on the terminal to communicate with clients and conduct care activities. If responses or new information are obtained from the client, they return to step 1 to acquire new emotional state and interview data and continue the process. This allows for flexible, real-time responses.

[0593] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0594] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0595] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0596] [Fourth Embodiment]

[0597] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0598] As shown in Figure 7, the 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.

[0599] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0600] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0601] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0602] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0603] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0604] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0605] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0606] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0607] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0608] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0609] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0610] This invention relates to a system for medical interviews, symptom suggestion, automatic medical record generation, and data management in a medical setting, and has the following configuration and operation.

[0611] Medical history and analysis

[0612] Users answer questions about their symptoms and health status through a medical questionnaire terminal. This response data is sent from the terminal to a server. The server analyzes this questionnaire data using a natural language processing engine to understand and classify the patient's complaints. For example, if a patient answers, "I have a persistent cough and headache," the server analyzes this information and extracts possible medical conditions.

[0613] Suggestions for the medical condition

[0614] The server uses natural language processing results to reference statistical models and medical knowledge databases to list possible medical conditions. This list, along with estimated probabilities, is sent to the terminal and presented to the user (a physician). The physician can then use this suggestion to consider directions for an initial diagnosis.

[0615] Automatic generation of medical records

[0616] The server automatically generates an electronic medical record based on the patient's medical history data and the proposed list of symptoms. The medical record consists of the patient's basic information, symptoms, and proposed diagnosis. The generated medical record can be viewed in real time by the doctor via a terminal, and any necessary information can be added or modified.

[0617] Data storage and management

[0618] The edited medical record information is stored in a highly secure database. The server provides secure access control to the stored data, ensuring that healthcare professionals and patients can access the information based on appropriate access rights. This system allows for the unified management of patient information across different healthcare facilities, enabling consistent treatment.

[0619] As a specific example

[0620] If a patient complains of symptoms such as "chest pain and shortness of breath," the server analyzes this and suggests possible diagnoses such as "myocardial infarction" or "angina." The doctor then reviews this and performs the necessary tests. Based on the test results, the information is added directly to the medical record and saved. This entire process is performed digitally and efficiently, reducing the burden on doctors and ensuring the provision of high-quality medical services.

[0621] As described above, the present invention provides specific means for improving the efficiency and quality of medical operations.

[0622] The following describes the processing flow.

[0623] Step 1:

[0624] The user (patient) uses a terminal for medical questionnaires to input answers to questions about their health status and symptoms. Once input is complete, the terminal sends this questionnaire data to the server in digital format.

[0625] Step 2:

[0626] The server passes the received medical questionnaire data to a natural language processing engine for analysis. During this analysis phase, symptoms and health information are identified and converted into necessary medical terminology.

[0627] Step 3:

[0628] The server uses the analysis results to reference a medical knowledge base and statistical models to create a list of predicted medical conditions. This list also includes the estimated probability of each condition.

[0629] Step 4:

[0630] The terminal displays a list of medical conditions received from the server to the user, who is a physician. This allows the physician to review the estimated medical conditions and use them as a reference for initial diagnosis.

[0631] Step 5:

[0632] The server automatically generates an electronic medical record based on the patient interview data and the proposed list of symptoms. The medical record includes the patient's basic information, discovered symptoms, and proposed diagnosis.

[0633] Step 6:

[0634] The terminal displays the generated electronic medical record to the physician and provides editing functions that allow the physician to add or modify information in the medical record as needed.

[0635] Step 7:

[0636] The server stores the final edited medical record information in a secure database. This data is managed with a high level of security and is accessible only to authorized users as needed.

[0637] Step 8:

[0638] Users (healthcare professionals and patients) can access past medical data and manage their own health status based on their permitted access rights.

[0639] (Example 1)

[0640] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0641] Modern healthcare demands rapid and accurate diagnosis and efficient information management. However, many healthcare institutions rely heavily on manual record creation and information management, which places a burden on healthcare professionals. Therefore, there is a need for systems that streamline the entire process, from patient interviews and diagnosis to record creation and information management, thereby improving the quality of medical care.

[0642] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0643] In this invention, the server includes an algorithm that uses natural language processing to analyze medical information entered by the user and proposes a suspected disease; an automatic generation means that includes a method for automatically generating an electronic medical record file based on the analysis results and user information; an digitization means that provides the generated medical record file to medical professionals in a real-time editable format and stores it in a storage database; and an information protection means that securely manages patient information and related data and provides it based on determined access rights. This makes it possible to streamline the entire process from medical interview to diagnosis and information management, reduce the burden on medical professionals, and improve the quality of medical care.

[0644] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is used to accurately interpret user medical information.

[0645] "Medical history information" refers to data about the patient's health status and symptoms, and is a fundamental source of information for making a diagnosis.

[0646] An "algorithmic method" is a series of steps or calculation methods for solving a specific problem, and this method uses natural language processing to analyze medical interview information and derive a suspected disease.

[0647] An "electronic medical record file" is a digital document that records a patient's medical information and is used to accurately track the process of diagnosis and treatment.

[0648] "Automated generation means" refers to a technology that uses algorithms to automatically create medical records, and is a procedure for efficiently organizing and creating medical information.

[0649] "Digitization means" refers to methods for representing, storing, and managing information in digital format, and is a process for securely storing generated medical records and providing them in an editable format.

[0650] "Information protection measures" are technologies or processes designed to ensure the confidentiality and integrity of data, and are methods for securely managing patient information and restricting access based on authorization.

[0651] This invention is a system that enables efficient patient interviews, diagnostic support, medical record generation, and data management in medical settings. This system consists of users, terminals, and a server, and operates as follows:

[0652] The user first uses a medical questionnaire terminal to answer questions about their physical symptoms and health status. The data entered is easily processed by following the on-screen instructions on the terminal. This information is then transmitted to the server using the terminal's communication capabilities. The communication uses an encrypted protocol to protect the data.

[0653] The server uses natural language processing (NLP) techniques to analyze the received medical questionnaire data. Software used for this includes, for example, Python libraries and natural language processing APIs. This analysis allows for the appropriate interpretation of the patient's symptoms and their conversion into medical terminology and relevant information.

[0654] Based on the analysis results, the server utilizes a generative AI model to estimate possible medical conditions. The estimation process involves referencing medical databases to create a more accurate list of conditions. This list, along with estimated probabilities, is then sent to the terminal.

[0655] The terminal displays a list of generated medical conditions, allowing healthcare professionals to determine their initial diagnostic strategy based on this information. The server automatically generates an electronic medical record based on the analysis results and estimated medical conditions. This record includes patient information, current symptoms, and proposed diagnoses, and is configured to allow physicians to review and edit it in real time as needed.

[0656] For example, if a patient reports "fever and sore throat" and enters their medical history, the server can analyze this information and estimate the patient's condition, such as "viral pharyngitis" or "influenza." This information is automatically included in the medical record and serves as a reference for the doctor.

[0657] An example of a prompt message would be: "This patient's symptoms are 'fever and sore throat.' Please use the AI ​​model to calculate possible conditions and their estimated probabilities." The system would then produce appropriate output based on this input. In this way, the invention enables accurate and efficient information processing in medical settings.

[0658] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0659] Step 1:

[0660] The user answers questions about their health status and symptoms using a medical questionnaire terminal. The user's input is recorded on the terminal in text format. The terminal encrypts the entered questionnaire data and sends it to the server via a secure communication protocol. The input data is raw symptom information and is ready to be transferred to the server as output.

[0661] Step 2:

[0662] The server initiates natural language processing using the patient interview data received from the terminal. The input is encrypted interview data. The server decrypts it and parses the text using the Python NLTK library. Specifically, the server divides the data into tokens and extracts important keywords. This outputs the patient's complaints as structured data, allowing the server to proceed to the next diagnostic estimation step.

[0663] Step 3:

[0664] The server uses a generative AI model to estimate possible medical conditions based on extracted keywords. The input is keyword data structured using natural language processing. The server refers to statistical models and medical databases to generate a list of medical conditions with estimated probabilities. The output is a list of proposed medical conditions, which is then sent to the next serving step.

[0665] Step 4:

[0666] The server sends a list of estimated medical conditions to the terminal, allowing the user, a healthcare professional, to make a diagnosis based on this information. The input is a list of estimated medical conditions, which the server converts into a format that can be displayed on the terminal in real time and provides as output. This information supports rapid decision-making in the medical field.

[0667] Step 5:

[0668] The server automatically generates electronic medical records based on patient interview data and a list of medical conditions. Input consists of structured patient information and medical condition data. The server integrates this information and creates the electronic medical record based on a template. The output is an editable medical record file, which users can view, edit, and save in real time on their terminals.

[0669] Step 6:

[0670] The server stores the generated medical records in secure data storage. The input is the generated medical record file. The server properly encrypts the patient data and stores it in the database. The output is securely stored medical record information, ready for later access. This information can be securely used by the appropriate users based on access permissions.

[0671] (Application Example 1)

[0672] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0673] Reducing the workload in healthcare settings and providing efficient medical care are crucial challenges. In particular, systems for home health management and daily health checks contribute not only to reducing the burden on medical facilities but also to maintaining the health of the general public. However, conventional systems have been difficult to use in homes, posing challenges in real-time health assessment and appropriate management of medical information.

[0674] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0675] This invention includes a server that analyzes medical interview data using natural language processing and proposes possible medical conditions, a server that automatically generates an electronic medical record based on the analysis results, a server that provides the generated medical record in an editable format and stores it in a medical information database, a server that acquires and analyzes voice data to evaluate the patient's health status at home, and a server that presents health management information based on the evaluation results. This enables efficient and consistent health management both in medical settings and at home.

[0676] "Natural language processing" refers to the ability of computers to understand and analyze human language, and is a technology that extracts and generates information based on text and audio data.

[0677] "Medical interview data" refers to information that patients provide when answering questions about their health status and symptoms, and serves as the basis for analyzing and diagnosing their medical condition.

[0678] The "means of suggesting medical conditions" refers to a function that lists and presents possible health conditions and diseases based on data analyzed using natural language processing.

[0679] "Automatic electronic medical record generation" is a system that creates a patient's medical record in digital format based on analyzed medical history data and suggested medical condition information.

[0680] "Security management measures" refer to systems that securely protect patients' medical information and data, and restrict access to and use of that information based on appropriate access rights.

[0681] "Means for acquiring audio data" refers to technologies that collect user speech using microphones or speech recognition devices.

[0682] A "means for evaluating health status" refers to a system that determines and evaluates a user's health status based on acquired voice data and analysis results.

[0683] "Means of providing health management information" refers to a function that provides users with improvement measures and precautions based on their analyzed health status.

[0684] To realize this invention, a system operating in a smart home is required. To support in-home health management, a combination of a server, an internet-connected terminal, and a voice recognition device for user interaction will be used.

[0685] The server converts user speech into text data using speech recognition technologies such as Google Cloud Speech-to-Text API or Amazon Transcribe. This text data is analyzed using OpenAI's GPT-3 and BERT natural language processing engines to suggest possible medical conditions. Based on the analyzed data, an electronic medical record is generated and stored in a medical information database for security management.

[0686] The terminal installed in the home provides users with feedback on analysis results and health management suggestions via voice and display screens. This information is presented as measures to improve health and precautions, playing a role in supporting daily health management. For example, if a user voice-inputs "I have a headache today," the system operates in the background, the server analyzes the information, and presents possible causes and minor remedies visually or audibly.

[0687] For example, the prompt could be written as follows: "Please tell me what to do if the user complains of a headache. Please list possible causes and remedies that can be done at home." This would enable a self-sustaining system to function within the home to support the user's health.

[0688] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0689] Step 1:

[0690] The user communicates their health status and symptoms to a voice input device. This voice input becomes the system's initial data source. The acquired voice data is converted into text data using speech recognition technology on the device. This conversion process yields text data that can be subsequently analyzed.

[0691] Step 2:

[0692] The terminal sends text data to the server. The server receives this text and analyzes the data using a natural language processing engine. Specifically, the input text is passed through OpenAI's GPT-3 or BERT to systematically analyze its meaning and extract possible medical conditions and related information. This analysis generates hypotheses about the health status.

[0693] Step 3:

[0694] The server suggests medical conditions based on the extracted information and generates an electronic medical record. This record includes the user's basic information, chief complaint, and suggested medical conditions. The generated record is then provided to the terminal in a format that can be reviewed and modified by the user and medical professionals. This record generation process enables unified management of health information.

[0695] Step 4:

[0696] The server securely stores the generated electronic medical records and analysis results in a medical information database. This stored information can be used as a record of the user's past health history to aid in future diagnoses and health management.

[0697] Step 5:

[0698] The device provides users with health management suggestions and advice based on analysis results and medical record information. These suggestions are fed back to the user via voice or display, supporting daily health management. For example, it might offer advice such as, "We recommend you drink more water."

[0699] Through these steps, users can easily monitor their health status at home and decide whether to seek medical attention if necessary.

[0700] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0701] This invention is a medical support system for the medical field, which includes analysis of medical interview data, suggestion of medical conditions, automatic generation of electronic medical records, and an emotion engine that recognizes the user's emotions. This emotion engine analyzes the patient's emotional state and uses it to supplement data in the diagnostic process and adjust the suggested content.

[0702] Medical history and emotional recognition

[0703] The user (patient) uses a device to answer questions about their health status by typing or speaking. During this process, the emotion engine analyzes facial expressions and tone of voice through the camera and microphone to recognize the patient's emotional state (e.g., anxiety, stress, relief). The recognized emotional information is sent to the server as part of the medical questionnaire data.

[0704] Data analysis and disease state recommendations

[0705] The server analyzes the patient's interview data and recognized emotional information using a natural language processing engine. The analysis results support more accurate predictions of the patient's condition, taking into account the patient's emotional state. For example, if a patient exhibits severe anxiety, this information will influence the stress-related condition suggestions.

[0706] Electronic medical record generation

[0707] Based on the analysis results, the server automatically generates an electronic medical record. The generated record includes the patient's basic health information, detected symptoms, recommended diagnosis, and emotional information. The terminal provides this record to healthcare professionals in an editable format, allowing for adjustments as needed.

[0708] Data storage and security management

[0709] Edited medical record information is stored in a highly secure database on the server. Emotional information is also handled as part of data management. This allows users (healthcare professionals) to provide more consistent treatment based on information including the patient's emotional state.

[0710] Specific example

[0711] For example, if a patient presents with symptoms of stomach pain while also showing clear signs of anxiety, the server will analyze this emotional state and suggest conditions such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses and provide care that take the patient's psychological state into account.

[0712] This system, incorporating an emotional engine, will provide multifaceted support for physicians' diagnostic work and enable the provision of medical care that takes into account the patient's psychological state.

[0713] The following describes the processing flow.

[0714] Step 1:

[0715] The user (patient) uses a medical questionnaire terminal to answer questions about their health status and symptoms via text input or voice input. During this process, the terminal records the patient's facial expressions and tone of voice using a camera and microphone, collecting emotional data.

[0716] Step 2:

[0717] The device transmits the collected medical interview data and emotional data to the server. An encryption protocol is used during transmission to ensure data security.

[0718] Step 3:

[0719] The server uses a natural language processing engine to analyze the medical interview data. Through this analysis, it organizes the extracted information about symptoms and health, and simultaneously evaluates emotional data using an emotion engine to identify the patient's emotional state.

[0720] Step 4:

[0721] The server references a medical knowledge base based on analysis results and emotional information to list possible medical conditions. This list includes the severity and probability of the predicted conditions, as well as consideration of the patient's emotional state.

[0722] Step 5:

[0723] The created list of medical conditions is sent to the terminal and displayed to the user (doctor). The doctor uses this information to help determine the subsequent diagnostic course.

[0724] Step 6:

[0725] The server automatically generates an electronic medical record based on the patient's interview data, emotional data, and a list of suggested conditions. This record includes the patient's symptoms, suggested diagnoses, and perceived emotional states.

[0726] Step 7:

[0727] The terminal provides the generated electronic medical record to the physician in an editable format. The physician can then add feedback and additional information to this record.

[0728] Step 8:

[0729] The edited medical record data is stored in a secure database on the server. The stored data is protected by appropriate access controls, allowing healthcare professionals to access it as needed.

[0730] This entire process allows for patient-centered care and enables the provision of more personalized medical services.

[0731] (Example 2)

[0732] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0733] Conventional medical support systems often perform data analysis without considering emotional states, making it difficult to make diagnoses that adequately reflect the patient's psychological state. Furthermore, the lack of mechanisms to utilize post-treatment evaluations within the system limited the ability to continuously improve the accuracy of medical care.

[0734] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0735] In this invention, the server includes means for analyzing medical interview information using natural language processing and proposing a health status, means for automatically generating electronic records, and means for analyzing the user's emotional state using an emotion recognition engine and integrating it with the medical interview information. This makes it possible to generate diagnoses and records that take into account the patient's emotional state.

[0736] "Natural language processing" is the technology that enables computers to understand, generate, and analyze human language.

[0737] "Medical interview information" refers to data about a patient's health status and symptoms that they provide to a medical institution.

[0738] "Health status" refers to an indicator of a patient's physical and psychological health.

[0739] "Electronic records" are digital documents generated for the purpose of electronically storing and managing medical information about patients.

[0740] An "emotion recognition engine" is a system that analyzes a user's facial expressions and voice to identify their emotional state.

[0741] A "user" is defined as the entity that operates the system and inputs or verifies information.

[0742] "Analysis accuracy" is an indicator used to evaluate the accuracy and reliability of data analysis.

[0743] "Learning techniques" refer to algorithms and methods that enable a system to gain experience and improve its performance.

[0744] This invention is a medical support system that provides a process in which a user (patient) inputs health-related information, and a server analyzes the health status based on that information and generates an electronic record. By using an emotion recognition engine, this system makes it possible to incorporate the patient's psychological state into the diagnosis.

[0745] Users input health information using a terminal. The terminal has an interface that accepts keyboard input or voice responses. The terminal also captures facial expressions and tone of voice using its built-in camera and microphone, and an emotion recognition engine analyzes this data. The analyzed emotion information is integrated into the medical questionnaire information sent to the server.

[0746] The server uses natural language processing technology to analyze the received medical history and emotional information. A generative AI model is used for this analysis, resulting in the generation of suggestions regarding the patient's health status. Emotional information is used to further refine the suggestions.

[0747] Once the analysis is complete, the server automatically generates an electronic record. This electronic record includes the patient's basic information, analyzed symptoms, suggested diagnosis, and emotional information. The terminal can display this record in a format that healthcare professionals can edit as needed.

[0748] For example, if a patient complains of stomach pain and expresses anxiety during a consultation, the server will examine this information and suggest possibilities such as a stomach ulcer or stress-induced gastritis. This allows doctors to make more effective diagnoses that take the patient's psychological state into account.

[0749] An example of a prompt message would be, "Please list possible health conditions when a user complains of stomach pain and expresses anxiety." This allows the system to comprehensively analyze the user's condition and make appropriate suggestions.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1:

[0752] The user answers questions about their health status by typing or speaking using the device. The device receives the input data (text or voice data) and converts it into a digital format. During this process, the camera and microphone simultaneously capture facial expressions and voice tone, generating emotion data.

[0753] Step 2:

[0754] The terminal sends the entered questionnaire data and recognized emotion data to the server. Specifically, the questionnaire data is in text format, and the emotion data is encoded as analyzed psychological indicators, and these are sent together. This transmitted data becomes the input for the next analysis step.

[0755] Step 3:

[0756] The server analyzes the received questionnaire data and emotional data using a natural language processing engine. The analysis employs a generative AI model to integrate text and emotional information and calculate probabilities related to the user's health condition. Based on these results, a list of hypothesized health conditions is output.

[0757] Step 4:

[0758] The server automatically generates an electronic record based on the analysis results and suggested health status. This electronic record includes the patient's basic information, detected symptoms, suggested health status name, and emotional information. The generated record is output in digital format and provided to healthcare professionals.

[0759] Step 5:

[0760] The terminal displays the generated electronic records to healthcare professionals. Healthcare professionals can edit these records as needed, adjusting them to finalize the clinical information. The edited records are then returned to the server for storage.

[0761] (Application Example 2)

[0762] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0763] In modern elderly care settings, a challenge is to appropriately understand the emotional state of the elderly and provide care based on that understanding. Care providers are required to understand the psychological and emotional needs of the elderly and respond accordingly, but this is sometimes difficult to achieve due to staffing shortages and technological limitations. Therefore, the development of support tools utilizing emotion recognition technology is necessary.

[0764] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0765] In this invention, the server includes means for analyzing medical interview data using natural language processing and suggesting possible medical conditions, means for automatically generating an electronic medical record based on the analysis results, and means for recognizing the user's emotional state from acoustic or visual data and adjusting the suggested content based on emotions. This makes it possible to suggest dialogue content and care actions that correspond to the emotional state.

[0766] "Natural language processing" is a technology that allows computers to understand and analyze human language and extract meaningful information.

[0767] "Medical interview data" refers to information about the health status collected from patients or users.

[0768] An "electronic medical record" is a record-keeping system for storing and managing patients' health information and medical history in a digital format.

[0769] "Security management" refers to the measures and systems in place to protect patient information and medical data from unauthorized access and leakage.

[0770] "Emotion recognition" is a technology that analyzes acoustic or visual data to identify the emotional state of a subject.

[0771] "Care providers" refer to people who are responsible for providing care and support to users or patients in nursing homes and medical institutions.

[0772] "Emotion-based proposals" are a method of adjusting and proposing the content of dialogue and actions according to the perceived emotional state.

[0773] This invention realizes a system that provides care providers in nursing care settings with dialogue and behavioral suggestions based on the emotional state of elderly individuals. The server uses natural language processing technology to analyze user interview data and predict possible medical conditions. The main software used in this process includes a natural language processing engine and an emotion recognition library. Specifically, the IBM Watson, a common natural language processing engine, is used, and the Microsoft Azure Emotion API is used as the emotion recognition library.

[0774] The server utilizes acoustic and visual data to recognize the user's emotional state in real time. This enables the automatic generation of electronic medical records based on analysis results combined with interview data. The generated electronic medical records are then used as an interface to provide care providers with appropriate suggestions tailored to the user's emotional state.

[0775] The terminal, via devices such as smart glasses, presents specific suggestions regarding conversation content and actions in the care setting. For example, if an elderly person shows anxiety, the server generates a prompt such as, "How about talking about a happy memory from the past?" and provides this suggestion to the care staff.

[0776] For example, if a caregiver is talking to an elderly person and the user says, "I don't really want to do anything today," the generative AI model, based on past experience, will generate a prompt such as, "Let's talk about a hobby you used to enjoy," and present it to the care staff. In this way, it is possible to support appropriate care tailored to the user's emotional state.

[0777] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0778] Step 1:

[0779] The user inputs speech and facial expressions through smart glasses. The device captures audio and video data using its camera and microphone and sends it to a server. The input data is analyzed acoustically and visually using an emotion recognition library and output as an emotional state (e.g., joy, anxiety, calmness).

[0780] Step 2:

[0781] The server receives emotional states derived from the user's acoustic and visual data as input. A natural language processing engine is used to analyze the questionnaire data and emotional states. Based on the results, an electronic medical record reflecting the user's health status is automatically generated and stored in a database. This electronic medical record includes recommendations based on the detected medical conditions and emotional states.

[0782] Step 3:

[0783] The terminal displays suggestions based on the electronic medical record and emotional state provided by the server. Specifically, an AI model generates prompts tailored to the user's emotional state, instructing caregivers on recommended conversations and actions. For example, a prompt such as "Try talking about a fun activity from the past" might be presented.

[0784] Step 4:

[0785] Care providers use prompts displayed on the terminal to communicate with clients and conduct care activities. If responses or new information are obtained from the client, they return to step 1 to acquire new emotional state and interview data and continue the process. This allows for flexible, real-time responses.

[0786] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0787] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0788] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0789] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0790] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0791] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0792] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0793] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0794] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0795] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0796] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0797] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0798] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0799] 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.

[0800] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0801] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0802] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0803] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0804] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0805] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0806] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0807] The following is further disclosed regarding the embodiments described above.

[0808] (Claim 1)

[0809] A method for analyzing medical interview data using natural language processing and proposing possible medical conditions,

[0810] A means of automatically generating electronic medical records based on the analysis results,

[0811] A means of providing the generated medical records in an editable format and storing them in a medical information database,

[0812] Security management measures to securely manage patient information and provide it based on necessary access rights,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, which provides an interface for displaying disease condition suggestions generated based on medical interview data to a medical professional.

[0816] (Claim 3)

[0817] The system according to claim 1, comprising a learning model that receives feedback on medical procedures and continuously improves the accuracy of the analysis.

[0818] "Example 1"

[0819] (Claim 1)

[0820] An algorithm that uses natural language processing to analyze medical information entered by the user and proposes a suspected disease,

[0821] An automatic generation means that includes a method for automatically generating electronic medical record files based on analysis results and user information,

[0822] An electronic means of providing generated medical record files to medical professionals in a format that can be edited in real time and storing them in a record library,

[0823] Information protection measures for securely managing patient information and related data and providing it based on determined access rights,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, comprising a display device that visually presents disease suggestion results generated based on medical interview information to a medical professional.

[0827] (Claim 3)

[0828] The system according to claim 1, comprising a learning method that receives results and evaluations from medical procedures and uses AI technology to continuously improve the accuracy of the analysis.

[0829] "Application Example 1"

[0830] (Claim 1)

[0831] A method for analyzing medical interview data using natural language processing and proposing possible medical conditions,

[0832] A means of automatically generating electronic medical records based on the analysis results,

[0833] A means of providing the generated medical records in an editable format and storing them in a medical information database,

[0834] Security management measures to securely manage patient information and provide it based on necessary access rights,

[0835] A means of acquiring and analyzing voice data to assess health status within the home,

[0836] A means of presenting health management information based on evaluation results,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, which provides an interface for displaying disease condition suggestions generated based on medical interview data to a medical professional.

[0840] (Claim 3)

[0841] The system according to claim 1, which receives feedback on medical procedures and includes a learning model that continuously improves the accuracy of the analysis, thereby supporting routine health management.

[0842] "Example 2 of combining an emotion engine"

[0843] (Claim 1)

[0844] A method for analyzing medical interview information using natural language processing and proposing possible health conditions,

[0845] A means for automatically generating electronic records based on the analysis results,

[0846] A means of providing the generated records in an editable format and storing them in an information database,

[0847] A means of analyzing the user's emotional state using an emotion recognition engine and integrating it with medical interview information,

[0848] A means of adjusting health status suggestions based on emotional state and interview information,

[0849] A protective management system that securely manages user information and provides it based on the necessary permissions,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, which provides a device for displaying health status suggestions generated based on medical interview information to a specialist.

[0853] (Claim 3)

[0854] The system according to claim 1, comprising a learning technology that receives the results of a medical procedure and continuously improves the accuracy of the analysis.

[0855] "Application example 2 when combining with an emotional engine"

[0856] (Claim 1)

[0857] A method for analyzing medical interview data using natural language processing and proposing possible medical conditions,

[0858] A means of automatically generating electronic medical records based on the analysis results,

[0859] A means of providing the generated medical records in an editable format and storing them in a medical information database,

[0860] Security management measures to securely manage patient information and provide it based on necessary access rights,

[0861] A means for recognizing the user's emotional state from acoustic or visual data and adjusting the suggested content based on that emotion,

[0862] A means of suggesting dialogue content and actions to care providers that correspond to emotional states,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which provides an interface for displaying to a medical professional disease condition suggestions generated based on medical interview data and emotion recognition.

[0866] (Claim 3)

[0867] The system according to claim 1, comprising a learning model that receives feedback on medical procedures and the emotional state of the user, and continuously improves the accuracy of the analysis. [Explanation of Symbols]

[0868] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method for analyzing medical interview data using natural language processing and proposing possible medical conditions, A means of automatically generating electronic medical records based on the analysis results, A means of providing the generated medical records in an editable format and storing them in a medical information database, Security management measures to securely manage patient information and provide it based on necessary access rights, A means of acquiring and analyzing voice data to assess health status within the home, A means of presenting health management information based on evaluation results, A system that includes this.

2. The system according to claim 1, which provides an interface for displaying disease condition suggestions generated based on medical interview data to a medical professional.

3. The system according to claim 1, which receives feedback on medical procedures and includes a learning model that continuously improves the accuracy of the analysis, thereby supporting routine health management.

Images