system

Abstract

Provide a system. 【Solution means】means for providing a user interface for a patient to input symptoms by voice or text, means for converting the input voice into text, means for sending the text data to a server, means for the server to analyze the received text data and convert it into medical jargon, means for sending and displaying the analysis result to the terminal of a medical expert, means for providing a user interface for a medical expert to input a diagnosis result, means for sending the input diagnosis result to a server, means for the server to convert the received diagnosis result into a form that is easy for the patient to understand, means for sending and displaying the conversion result to the patient's terminal, A system including

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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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, communication between patients and doctors is often insufficient. This is because patients may not be able to express their symptoms appropriately, or doctors may use specialized language for explanations, making it difficult for patients to understand. Such communication failures can lead to misdiagnosis and inappropriate treatment, potentially affecting the health of patients. The purpose of the present invention is to solve the communication problems in the medical field by enabling the transmission of information corresponding to the state and characteristics of patients.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to a server, means for the server to analyze the received text data and convert it into medical terminology, means for transmitting and displaying the analysis results on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to a server, means for the server to convert the received diagnostic results into a form that is easy for the patient to understand, and means for transmitting and displaying the conversion results on the patient's terminal. This system improves communication in medical settings by enabling patients to properly communicate their symptoms and understand doctors' diagnoses and instructions more easily.

[0006] A "patient" is an individual who receives medical examination or treatment in a healthcare setting.

[0007] "Medical professionals" refer to doctors who perform examinations, diagnoses, and treatments, as well as healthcare workers who assist them.

[0008] A "user interface" refers to the screens, input devices, output devices, and other elements that allow a user to interact with a system.

[0009] A "speech recognition API" is a programmatic interface for converting input speech into text format.

[0010] "Text data" refers to a format of data that is stored or processed as character information.

[0011] A "server" is a computer system that receives, processes, and transmits data over a network.

[0012] A "natural language processing engine" is a part of software that analyzes, understands, and generates language that people use on a daily basis.

[0013] "Medical terminology" refers to specific, specialized words and expressions used in the medical field.

[0014] "Analysis results" refer to the processing results of the input information, generated by the server using natural language processing or similar methods. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (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.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage 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.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it is a system that appropriately conveys information entered by the patient to the healthcare professional and provides the results entered by the healthcare professional to the patient in an easy-to-understand manner. This system consists of the following programs and processes.

[0037] System Overview

[0038] 1. Patient's terminal

[0039] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. This text data is sent to the server.

[0040] 2. Server-side processing

[0041] The server receives text data sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms and converts them into a format that is easy for medical professionals to understand. The analysis results are generated in a format using medical terminology and sent to the medical professionals' terminals.

[0042] 3. Terminals on the medical professional's side

[0043] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0044] 4. Server-side re-analysis

[0045] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[0046] 5. Patient-side display

[0047] The patient's device displays the conversion results sent from the server. These results are displayed not only in text format but can also be played back using speech synthesis. This allows patients to accurately understand the instructions from medical professionals.

[0048] Specific example

[0049] Specifically, the following operations are performed:

[0050] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the data and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then check this information on their device and take appropriate action.

[0051] The above describes the "mode for carrying out the invention" of this invention. This mode dramatically improves communication between patients and medical professionals, enabling accurate diagnosis and appropriate treatment.

[0052] The following describes the processing flow.

[0053] Step 1:

[0054] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[0055] Step 2:

[0056] The device uses a speech recognition API to convert the input speech into text data: "My right knee has been hurting lately."

[0057] Step 3:

[0058] The terminal sends the converted text data to the server.

[0059] Step 4:

[0060] The server analyzes the received text data, "My right knee has been hurting recently," and uses a natural language processing engine to extract keywords related to the patient's symptoms (e.g., "right knee," "painful," "recently").

[0061] Step 5:

[0062] Based on the extracted information, the server generates a message in a format that is easy for medical professionals to understand (e.g., "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain").

[0063] Step 6:

[0064] The server sends the generated message to the medical professional's terminal.

[0065] Step 7:

[0066] The device displays the received message to a medical professional, who then reviews it.

[0067] Step 8:

[0068] The user (medical professional) enters the diagnosis into the terminal. Example: "Inflammation is suspected in the right knee. I prescribe ice packs and pain medication."

[0069] Step 9:

[0070] The terminal sends the entered diagnostic results to the server.

[0071] Step 10:

[0072] The server analyzes the received diagnostic results and uses a natural language processing engine to convert them into a format that is easy for the patient to understand. Example: "You may have inflammation in your right knee. Apply ice and take medication."

[0073] Step 11:

[0074] The server sends the converted message to the patient's terminal.

[0075] Step 12:

[0076] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis.

[0077] The above outlines the specific processing steps involved in each stage.

[0078] (Example 1)

[0079] 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."

[0080] Traditionally, communication between patients and healthcare professionals has been fraught with problems. Patients often struggled to accurately describe their symptoms, and the specialized terminology used by healthcare professionals was often difficult to understand, leading to misunderstandings of diagnoses and treatment plans. This increased the risk of delays in proper diagnosis and treatment, potentially leading to a deterioration of the patient's health.

[0081] 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.

[0082] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for analyzing the received text data using a natural language processing engine, extracting keywords and important information related to the symptoms, and converting them into medical terminology, means for transmitting and displaying the analysis results on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for converting the received diagnostic results into a form that is easy for the patient to understand and replacing complex medical terminology with everyday language, and means for transmitting and displaying and playing the conversion results on the patient's terminal. This enables smooth information exchange between the patient and the medical professional, and allows for prompt and appropriate diagnosis and treatment.

[0083] A "user interface" is a mechanism that provides screens and input methods for users to interact with a system.

[0084] A "speech recognition API" is an application programming interface for converting speech data into text data.

[0085] A "server" is a computer system used to receive and process data over a network.

[0086] A "natural language processing engine" is a software program that analyzes text data and extracts its meaning.

[0087] A "keyword" is a word or phrase that indicates important information in data analysis.

[0088] "Medical terminology" refers to specialized words and expressions used in the medical field.

[0089] A "medical professional" is someone who possesses specialized knowledge in the medical field, such as a doctor or nurse.

[0090] A "diagnosis" is a judgment or conclusion made by a medical professional based on a patient's symptoms and test results.

[0091] "Conversion result" refers to information that shows how the analyzed data was ultimately represented.

[0092] "Speech synthesis" is a technology that converts text data into speech data.

[0093] This invention is a system for improving communication between patients and healthcare professionals, aiming to enable patients to describe their symptoms in detail and for healthcare professionals to communicate diagnostic results accurately and clearly to patients. This system consists of the following components and associated processes.

[0094] 1. Entering patient information

[0095] For user (patient) information input, the terminal provides a user interface that allows symptom input via voice or text. In the case of voice input, the terminal uses a speech recognition API to convert speech to text. For example, Google® Speech-to-Text API is used. The converted text data is sent from the terminal to the server.

[0096] 2. Initial analysis on the server

[0097] The server receives text data sent from the patient and stores it. Next, a natural language processing engine is used to analyze this text data and extract important keywords and information. Python's natural language processing library, such as spaCy, is used. The extracted information is converted into medical terminology in a format easily understood by healthcare professionals.

[0098] 3. Notification and input to medical professionals

[0099] Medical professionals review the analysis results sent from the server on a terminal. The terminal provides a user interface for medical professionals to input diagnostic results and treatment plans. The entered information is transmitted to the server via the electronic medical record system (EMR system).

[0100] 4. Re-analysis and conversion on the server

[0101] The server receives diagnostic results sent from medical professionals and performs a re-analysis. This re-analysis involves replacing medical terminology with everyday language. For example, the Gensim library is used to simplify the text. The converted information is then sent to the patient's terminal.

[0102] 5. Display and confirmation by the patient.

[0103] The patient's device receives the conversion results sent from the server and displays them in text format. Furthermore, it can also play the instructions audibly using speech synthesis functionality (e.g., Amazon Polly or Google Text-to-Speech API).

[0104] Specific example

[0105] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the message, and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then view this on their device and also hear the instructions by voice.

[0106] Example of a prompt

[0107] Below are examples of prompts for a generative AI model:

[0108] "Please describe in detail the processing steps of a system that improves communication between patients and healthcare professionals. Describe the entire process, from patient information input to the re-analysis of the healthcare professional's diagnosis and its subsequent communication to the patient."

[0109] The above describes the "mode for carrying out the invention" of the present invention. This mode enables smooth communication between patients and medical professionals, and allows for prompt and appropriate diagnosis and treatment.

[0110] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0111] Step 1:

[0112] The user (patient) inputs their symptoms using the terminal's user interface. In the case of voice input, the patient might say, "My right knee has been hurting lately." This voice data is input to the terminal's speech recognition API and converted into text data. This text data then becomes the input data for subsequent processing.

[0113] Step 2:

[0114] The terminal sends the converted text data to the server via an HTTP request. The server receives this request and temporarily stores the text data.

[0115] Step 3:

[0116] The server analyzes the received text data using a natural language processing engine (for example, Python's spaCy library). Specifically, it extracts keywords such as "right knee" and "painful" from the text data and converts them into a structured data format. This analyzed data becomes the input data for subsequent processing.

[0117] Step 4:

[0118] The server converts the analyzed data into medical terminology. For example, it converts "pain" to "pain" and generates sentences like "I have pain in my right knee." This makes the data easier for medical professionals to understand. This converted data is then sent to the medical professionals' terminals.

[0119] Step 5:

[0120] Medical professionals use the terminal's user interface to review the analysis data sent from the server. Next, they input the diagnosis and treatment plan. For example, they might enter, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication." This input data is then sent back to the server.

[0121] Step 6:

[0122] The server re-analyzes the received diagnostic results and converts them into everyday language that patients can easily understand. Specifically, it converts "inflammation of the right knee is suspected" to "there may be inflammation in your right knee," and further converts "we will prescribe painkillers" to "please take the medicine." The converted data becomes the input data for subsequent processing.

[0123] Step 7:

[0124] The server sends the re-analyzed and converted data to the patient's device. The device displays this data in text format and also plays it back as audio using a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech API). This allows the patient to confirm medical instructions both visually and aurally.

[0125] The above outlines the specific processing steps of this system's program.

[0126] (Application Example 1)

[0127] 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."

[0128] In traditional healthcare systems, communication between patients and healthcare professionals was often inefficient, particularly in verbalizing symptoms and conveying treatment plans. Furthermore, physical distance and time constraints made rapid diagnosis and treatment difficult, resulting in delays in patients receiving appropriate care. Additionally, obtaining necessary products and services for treatment after diagnosis was cumbersome.

[0129] 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.

[0130] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for the server to analyze the received text data and convert it into medical terminology, means for transmitting and displaying the analysis results on the terminal of a medical professional, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for the server to convert the received diagnostic results into a format that is easy for the patient to understand, means for transmitting and displaying the conversion results on the patient's terminal, and means for the patient to check and purchase necessary products and services for treatment within a virtual healthcare store. This enables smooth communication between the patient and the medical professional, facilitating rapid diagnosis and communication of treatment plans, and allowing for consistent acquisition of necessary products and services for treatment.

[0131] "Text data" refers to data that represents speech or text input in a digital format.

[0132] "Analysis results" refer to information obtained after it has been processed by the server using natural language processing.

[0133] "Medical terminology" refers to specialized vocabulary and phrases commonly used in the medical field.

[0134] A "user interface" refers to the interactive screens or forms that allow users (patients or healthcare professionals) to interact directly with the system.

[0135] A "server" is a computer system that receives input data, processes it, and sends the analysis results to each terminal.

[0136] A "terminal" is a device used by a patient or medical professional to display analysis results or diagnostic results.

[0137] "Diagnosis results" refer to information about a diagnosis entered by a medical professional.

[0138] A "virtual healthcare store" is a virtual marketplace that provides medical-related products and services online.

[0139] "Input means" refers to the methods or devices by which a user inputs information into a system, either by voice or text.

[0140] "Display means" refers to methods or devices for visually displaying analysis results or diagnostic results on a terminal.

[0141] "Products and services necessary for treatment" refer to medications and medical services that a patient needs based on a diagnosis made by a medical professional.

[0142] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it appropriately conveys information entered by patients to healthcare professionals and provides patients with easily understandable results entered by healthcare professionals. The following shows a specific form for realizing this system.

[0143] System Overview

[0144] 1. Patient's terminal

[0145] Patients can use a user interface to input their symptoms. They can use either voice or text input; the voice input is converted to text using the device's speech recognition API. The converted text data is then sent to the server.

[0146] 2. Server-side processing

[0147] The server receives text data sent from patients and analyzes it using a generative AI model. Using natural language processing, it extracts keywords and important information related to symptoms and generates analysis results in a format using medical terminology. These analysis results are then sent to the terminals of medical professionals.

[0148] 3. Terminals on the medical professional's side

[0149] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0150] 4. Server-side re-analysis

[0151] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[0152] 5. Patient-side display

[0153] The patient's device displays the conversion results sent from the server. This allows the patient to accurately understand the instructions from the medical professional and take appropriate action. Furthermore, they can view and purchase necessary products and services within the virtual healthcare store.

[0154] Specific example

[0155] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server analyzes the received data and notifies a healthcare professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the healthcare professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then re-analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take medication." The patient can then review this on their device and take appropriate action. During this process, they can also purchase necessary medications and medical equipment from a virtual healthcare store.

[0156] Example of a prompt

[0157] Please analyze the symptoms of the following patient:

[0158] My right knee has been hurting lately.

[0159] Analysis results:

[0160] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0161] Step 1:

[0162] The patient enters their symptoms via voice or text.

[0163] Input: Audio or text describing the patient's symptoms.

[0164] Specific action: The patient uses the terminal's user interface to input voice commands such as, "My right knee has been hurting lately."

[0165] Output: Input audio or text data.

[0166] Step 2:

[0167] Converts the input audio into text.

[0168] Input: Audio data.

[0169] Specific action: The device uses a speech recognition API to convert the speech into text, "My right knee has been hurting lately."

[0170] Output: Text data.

[0171] Step 3:

[0172] Send text data to the server.

[0173] Input: Text data.

[0174] Specific action: The terminal sends the text data "My right knee has been hurting lately" to the server.

[0175] Output: Text data received by the server.

[0176] Step 4:

[0177] The server analyzes the received text data and converts it into medical terminology.

[0178] Input: Received text data.

[0179] Specific operation: The server uses a generated AI model to analyze text data and convert it into medical terminology such as, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain."

[0180] Output: Analysis results converted into medical terminology.

[0181] Step 5:

[0182] The analysis results are sent to the terminals of medical professionals for display.

[0183] Input: Analysis results converted into medical terminology.

[0184] Specific operation: The server sends a message to the medical professional's terminal stating, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain," and this message is displayed on the terminal.

[0185] Output: Analysis results displayed on the medical professional's terminal.

[0186] Step 6:

[0187] It uses a user interface where medical professionals input diagnostic results.

[0188] Input: Diagnosis from a medical professional.

[0189] Specific operation: A medical professional uses the terminal's user interface to input a diagnosis such as, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[0190] Output: The entered diagnostic result.

[0191] Step 7:

[0192] The entered diagnostic results are sent to the server.

[0193] Input: Diagnostic result.

[0194] Specific action: A medical professional's terminal sends a diagnosis to the server stating, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[0195] Output: Diagnostic results received by the server.

[0196] Step 8:

[0197] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[0198] Input: Diagnostic result.

[0199] Specific operation: The server uses a natural language processing engine to convert the diagnostic results into a format that is easy for the patient to understand, such as "You may have inflammation in your right knee. Apply ice and take medication."

[0200] Output: Diagnostic results converted into a format that is easy for the patient to understand.

[0201] Step 9:

[0202] The conversion results are sent to the patient's device and displayed.

[0203] Input: Diagnostic results converted into a format that is easy for the patient to understand.

[0204] Specific operation: The server sends a message to the patient's device saying, "You may have inflammation in your right knee. Apply ice and take medication," and this message is displayed on the device.

[0205] Output: Diagnostic results displayed on the patient's device.

[0206] Step 10:

[0207] Patients can view and purchase necessary products and services for their treatment within a virtual healthcare store.

[0208] Input: Information about a virtual healthcare store.

[0209] Specific operation: Patients use the terminal's virtual healthcare store function to check and purchase necessary medications and medical devices.

[0210] Output: Information about the purchased goods or services.

[0211] 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.

[0212] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate information transmission. This system consists of the following programs and processes.

[0213] System Overview

[0214] 1. Patient's terminal

[0215] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. The device also has a built-in emotion engine that recognizes the patient's emotions from the voice. This text data and emotion information are sent to the server.

[0216] 2. Server-side processing

[0217] The server receives text data and emotional information sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized emotional information. The analysis results are converted into a format that is easy for medical professionals to understand.

[0218] 3. Terminals on the medical professional's side

[0219] Medical professionals can view analysis results and emotional information transmitted from the server on their terminals. This allows them to understand not only the symptoms but also the patient's emotions, leading to more appropriate diagnoses and communication. A user interface is also provided for inputting diagnostic results and treatment plans, and the entered information is transmitted to the server.

[0220] 4. Server-side re-analysis

[0221] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent back to the patient's device.

[0222] 5. Patient-side display

[0223] The patient's device displays the conversion results and emotional information sent from the server. This information is displayed not only in text format but can also be played back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[0224] Specific example

[0225] For example, if a patient voice-inputs "My right knee has been hurting recently," the system recognizes the emotion of "anxiety" from the voice input. The terminal converts this to text and sends the text "My right knee has been hurting recently" along with the emotion information of "anxiety" to the server. The server receives and analyzes the input and notifies the medical professional, "The patient is complaining of right knee pain and is feeling anxious. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "Inflammation of the right knee is suspected. I will prescribe ice and painkillers," which is analyzed by the server and notified to the patient, "There may be inflammation in your right knee. Apply ice and take the medication." The patient can then check this on the terminal and take appropriate action.

[0226] The above describes the "modes for carrying out the invention" of this invention. This mode enables communication that takes into account not only the patient's physical symptoms but also their emotional state, dramatically improving communication in medical settings.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[0230] Step 2:

[0231] The device converts the input voice data into text using a speech recognition API. The text generated is "My right knee has been hurting lately."

[0232] Step 3:

[0233] The device analyzes voice data using an emotion engine to recognize the emotions the patient is feeling. For example, it can recognize the emotion of "anxiety."

[0234] Step 4:

[0235] The device sends the converted text data and recognized emotion information to the server.

[0236] Step 5:

[0237] The server analyzes the received text data and sentiment information. Using a natural language processing engine, it extracts keywords and important information related to symptoms. For example, it extracts keywords such as "right knee," "painful," and "recently."

[0238] Step 6:

[0239] The server generates messages in a format easily understood by medical professionals, based on extracted information and emotional data. For example, it might generate a message such as, "The patient is complaining of pain in their right knee and is feeling anxious. Please note when the pain started and what movements cause it."

[0240] Step 7:

[0241] The server sends the generated message to the medical professional's terminal.

[0242] Step 8:

[0243] The device displays the received message to a medical professional, who then reviews it.

[0244] Step 9:

[0245] The user (medical professional) enters the diagnosis and treatment plan into the terminal. For example, they might enter, "Inflammation is suspected in the right knee. I will prescribe ice packs and pain medication."

[0246] Step 10:

[0247] The terminal sends the entered diagnostic results to the server.

[0248] Step 11:

[0249] The server analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Using a natural language processing engine, it replaces complex medical jargon with everyday language. For example, it might generate a message like, "You may have inflammation in your right knee. Apply ice and take medication."

[0250] Step 12:

[0251] The server sends the converted message to the patient's terminal.

[0252] Step 13:

[0253] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[0254] The above outlines the specific processing steps involved in each stage.

[0255] (Example 2)

[0256] 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 as the "terminal".

[0257] Conventional medical communication systems need to not only accurately understand a patient's symptoms but also consider their emotional information to enable more accurate and effective diagnosis and treatment. However, current systems lack the technology to appropriately recognize and analyze a patient's emotional information, resulting in a decline in the quality of communication and often placing a burden on diagnosis and treatment. This invention aims to solve these problems and significantly improve communication between patients and medical professionals.

[0258] 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.

[0259] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for recognizing emotions from the input voice data, means for transmitting text data and emotional information to the server, means for analyzing the received text data and emotional information and extracting keywords and important information related to the symptoms, means for transmitting and displaying the analysis results and emotional information on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnosis results and treatment plans, means for transmitting the input diagnosis results and treatment plans to the server, means for converting the received diagnosis results into a format that is easy for the patient to understand and transmitting the conversion results to the patient's terminal, and means for displaying or playing the conversion results and emotional information on the patient's terminal. This makes it possible to diagnose and treat patients while considering not only their physical symptoms but also their emotional state, and significantly improves the quality of communication in medical settings.

[0260] A "user interface for patient symptom input via voice or text" refers to an interface that allows patients to input their symptoms via voice or text, and is an input device for interaction between the system and the patient.

[0261] "Means for converting input speech to text" refers to a processing function that uses speech recognition technology to convert voice input data into text data.

[0262] "Means of recognizing emotions from input audio data" refers to a processing function that uses audio analysis technology to extract emotional information from audio data and determine the emotion being expressed.

[0263] "Means for sending text data and sentiment information to a server" refers to communication means for sending input text data and sentiment information to a server via a network.

[0264] "Means for the server to analyze received text data and sentiment information and extract keywords and important information related to symptoms" refers to a processing function in which the server uses natural language processing technology to analyze text data and sentiment information and identify important keywords and information.

[0265] "Means for transmitting and displaying analysis results and emotional information on a medical professional's terminal" refers to a function that transmits the analysis results and emotional information from the server to a medical professional's terminal via the network and displays them.

[0266] "Means of providing a user interface for medical professionals to input diagnostic results and treatment plans" refers to an interface for medical professionals to input diagnostic results and treatment plans, and an input device for interaction between the system and medical professionals.

[0267] "Means for transmitting entered diagnostic results and treatment plans to a server" refers to communication means for transmitting diagnostic results and treatment plans entered by medical professionals to a server via a network.

[0268] "A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand and sends the converted results to the patient's terminal" refers to a function that analyzes the received diagnostic results, converts them into simple language that the patient can understand, and sends the converted results to the patient's terminal.

[0269] "Means for displaying or playing back the conversion results and emotional information on the patient's terminal" refers to a function that allows the patient's terminal to display the conversion results and emotional information sent from the server on a screen, or to play them back as audio using speech synthesis technology.

[0270] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate and effective information transmission. This system is built on a network basis, including patient terminals, a server, and healthcare professional terminals.

[0271] Patient's terminal

[0272] The patient's terminal provides a user interface for the patient to input their symptoms. The patient can input via voice or text. The input voice is converted to text using a speech recognition API (e.g., a speech recognition API). Furthermore, an emotion engine (e.g., emotion recognition technology) built into the terminal is used to recognize the patient's emotions from the voice data. This text data and emotion information are transmitted to a server via the network.

[0273] Server-side processing

[0274] The server receives text data and sentiment information sent from the patient and analyzes it using a natural language processing engine (e.g., a natural language processing engine). Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized sentiment information. The analysis results and sentiment information are converted into a format that is easy for medical professionals to understand and sent to the medical professionals' terminals.

[0275] Terminal on the medical professional's side

[0276] The medical professional's terminal displays analysis results and sentiment information sent from the server. The medical professional can use the user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0277] Server-side re-analysis

[0278] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent to the patient's device.

[0279] Patient-side display

[0280] The patient's terminal displays the conversion result and emotion information sent from the server. As a result, the patient can accurately understand the instructions of medical experts. Not only can it be displayed in text format, but it can also be played back in voice using voice synthesis technology (for example, voice synthesis technology).

[0281] Specific example

[0282] For example, when a patient inputs "Recently, my right knee hurts" by voice, the terminal converts the voice into text data "Recently, my right knee hurts" and recognizes the emotion of "uneasiness" by emotion recognition technology. When this text data and emotion information are sent to the server, the server analyzes the data using a natural language processing engine and extracts information such as "pain in the right knee" and "uneasiness". The analysis result is notified to the medical expert in the form of "The patient complains of pain in the right knee and feels uneasy. Please confirm the time when the pain started and what actions cause the pain." After the medical expert's examination, they input "Inflammation of the right knee is suspected. Prescribe icing and painkillers", and the server re-analyzes it and conveys it to the patient as "There may be inflammation in the right knee. Apply cold and take medicine."

[0283] Examples of prompt sentences

[0284] "The patient complains of pain in the right knee but feels uneasy. How should I convey this to the medical expert?"

[0285] "Please convert the diagnosis result into words that are easy for the patient to understand. Diagnosis content: Inflammation of the right knee, Prescription: Icing and painkillers."

[0286] The above is the embodiment of the present invention. With this form, effective communication considering not only the physical symptoms of the patient but also the emotional state becomes possible, and diagnosis and treatment in the medical field are dramatically improved.

[0287] The flow of specific processing in Example 2 will be described using FIG. 13.

[0288] Step 1:

[0289] The user (patient) enters their symptoms using the terminal's user interface.

[0290] Specific action: The patient inputs by voice, "My right knee has been hurting lately."

[0291] Input: Audio data.

[0292] Output: Audio data.

[0293] Step 2:

[0294] The device sends the input voice data to a speech recognition API, which then converts it to text.

[0295] Specific operation: The speech recognition API converts the voice data "My right knee has been hurting recently" into the text "My right knee has been hurting recently".

[0296] Input: Audio data.

[0297] Output: Text data.

[0298] Step 3:

[0299] The device recognizes emotions from the input voice data.

[0300] Specific operation: The emotion engine recognizes the emotion "anxiety" from the audio data.

[0301] Input: Audio data.

[0302] Output: Emotional information.

[0303] Step 4:

[0304] The device sends text data and sentiment information to the server.

[0305] Specific operation: The terminal sends text data "I have been having pain in my right knee recently" and emotion information "uneasy" to the server.

[0306] Input: Text data and emotion information.

[0307] Output: Text data and emotion information sent to the server.

[0308] Step 5:

[0309] The server analyzes the text data and emotion information it received.

[0310] Specific operation: The natural language processing engine extracts keywords such as "pain in the right knee" and "uneasy".

[0311] Input: Text data and emotion information.

[0312] Output: Analysis results and emotion information.

[0313] Step 6:

[0314] The server sends the analysis results and emotion information to the terminal of the medical expert for display.

[0315] Specific operation: As analysis results, information such as "The patient complains of pain in the right knee and feels uneasy. Please confirm the time when the pain started and how it hurts when performing certain movements" is sent to the terminal of the medical expert.

[0316] Input: Analysis results and emotion information.

[0317] Output: Analysis results and emotion information displayed on the terminal of the medical expert.

[0318] Step 7:

[0319] The medical expert inputs the diagnosis result and treatment plan.

[0320] Specific action: A medical professional enters into the terminal, "Inflammation is suspected in the right knee. I will prescribe ice and pain medication."

[0321] Input: Diagnosis and treatment plan.

[0322] Output: Input diagnostic results and treatment plan.

[0323] Step 8:

[0324] The terminal sends the entered diagnostic results and treatment plan to the server.

[0325] Specific action: The medical professional enters "Inflammation is suspected in the right knee. I will prescribe ice and pain medication" and sends it to the server.

[0326] Input: Diagnosis and treatment plan.

[0327] Output: Diagnostic results and treatment plan sent to the server.

[0328] Step 9:

[0329] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[0330] Specific action: The server converts the diagnosis "Inflammation of the right knee is suspected. We prescribe ice and pain medication" to "There may be inflammation in your right knee. Apply ice and take medication."

[0331] Input: Diagnosis and treatment plan.

[0332] Output: Converted diagnostic results.

[0333] Step 10:

[0334] The server sends the conversion results to the patient's terminal.

[0335] Specific operation: The server sends the converted diagnostic results to the patient's terminal.

[0336] Input: Converted diagnostic results.

[0337] Output: The conversion result sent to the patient's terminal.

[0338] Step 11:

[0339] The patient's device displays or plays back the conversion results and emotional information via audio.

[0340] Specific actions: The patient's device displays the translated message, "You may have inflammation in your right knee. Apply ice and take medicine," or plays it aloud using speech synthesis technology.

[0341] Input: Conversion result and sentiment information.

[0342] Output: The displayed text or the played audio.

[0343] (Application Example 2)

[0344] 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".

[0345] Traditional security systems have struggled to monitor and analyze the psychological state of external visitors and employees in real time. Furthermore, early detection of potential threats is difficult, leading to delays in post-incident response. There has also been a lack of means to analyze emotional information such as employee stress and anxiety, enabling timely and appropriate responses.

[0346] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for recognizing and analyzing emotional information from voice data, means for transmitting and displaying the analysis results on the security guard's terminal, and means for detecting abnormal emotions and issuing warnings. This enables real-time analysis of emotional information of external visitors and employees, early detection of potential threats, and swift and appropriate responses.

[0347] A "user interface for patient symptom input via voice or text" is an input device designed to allow patients to easily input their symptoms as voice or text information.

[0348] "Means for converting input speech to text" refers to a device or software that has the function of converting speech information into corresponding text information using speech recognition technology.

[0349] "Means for sending text data to a server" refers to a communication device or program for sending acquired text information to a designated server via a network.

[0350] "A means of analyzing text data received by a server and converting it into medical terminology" refers to a process in which a program running on the server converts general text data received into specialized medical terminology.

[0351] "Means for transmitting and displaying analysis results on a medical professional's terminal" refers to a device or software that transmits the results of analysis performed on a server to a medical professional's terminal via a network and displays them on that terminal.

[0352] A "user interface for medical professionals to input diagnostic results" refers to a dedicated input device or screen for medical professionals to input diagnostic results and treatment plans.

[0353] "Means for transmitting entered diagnostic results to a server" refers to a device or program that has the function of transmitting diagnostic results entered by a medical professional to a server via a network.

[0354] "Means of converting diagnostic results received by the server into a format that is easy for patients to understand" refers to the process of converting specialized diagnostic results received by the server into everyday language that patients can easily understand.

[0355] "Means for sending and displaying conversion results on the patient's terminal" refers to a device or software that has the function of sending the converted results back to the patient's terminal and displaying them on that terminal.

[0356] "Means for recognizing and analyzing emotional information from collected audio data" refers to a technology or solution for recognizing and analyzing the emotional state of a speaker contained within audio data.

[0357] "Means for transmitting and displaying analysis results including emotional information on a medical professional's terminal" refers to a device or software that transmits and displays analysis results including emotional information on a medical professional's terminal via a network.

[0358] This invention relates to a system for improving communication between patients and healthcare professionals, and in particular to enabling more accurate information transmission by recognizing and analyzing the patient's emotional information. The embodiments for carrying out this invention are as follows.

[0359] System Configuration

[0360] 1. Patient's device:

[0361] It provides a user interface for patients to input their symptoms via voice or text.

[0362] It has the ability to convert speech to text using a speech recognition API (for example, Google Speech-to-Text API).

[0363] To recognize emotional information from speech, incorporate an emotion recognition library (e.g., EmotionRecognizer).

[0364] A communication function that sends input text data and sentiment information to the server.

[0365] 2. Server-side processing:

[0366] A natural language processing engine (e.g., NLPProcessor) is used to analyze the received text data and sentiment information.

[0367] It generates analysis results and converts them into a format that is easy for medical professionals to understand.

[0368] The analysis results, including emotional information, are sent to the terminals of medical professionals.

[0369] 3. Terminals used by medical professionals:

[0370] It has a display interface that allows medical professionals to review analysis results and emotional information.

[0371] It provides a user interface for inputting diagnostic results and treatment plans.

[0372] A communication function that sends the entered diagnostic results to the server.

[0373] 4. Server-side re-analysis:

[0374] The received diagnostic results are reanalyzed and converted into a format that is easy for the patient to understand.

[0375] The conversion results are sent back to the patient's device.

[0376] 5. Patient's display:

[0377] It has a display interface that allows patients to check the conversion results received from the server.

[0378] It has a function that allows instructions to be played back as audio using speech synthesis.

[0379] Examples of specific cases and prompt statements

[0380] For example, consider a scenario where this system is installed in a security guard's smart glasses. When the guard is spoken to by an outside visitor, the audio data is collected and analyzed in real time. If the system detects that the visitor is "slightly panicked," it issues a warning and prompts the guard to take immediate action.

[0381] Also, consider the following example prompts for a generative AI model:

[0382] The system collected audio data and generated the following sentiment and text information:

[0383] Voice: "I'm a little nervous, but I'm okay."

[0384] Emotion: “Tension, anxiety”

[0385] Please send this to the server in the following format:

[0386] {

[0387] "text_input": "I'm a little nervous, but I'm okay",

[0388] "emotion": "tension, anxiety",

[0389] "Analysis": "The visitor appears nervous, but there doesn't seem to be any major problem."

[0390] }

[0391] Thus, the present invention is a system that analyzes voice data and emotional information and provides it to the appropriate user, thereby achieving highly accurate medical support and security management.

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

[0393] Step 1:

[0394] The patient enters their symptoms via voice or text. Specifically, when the patient provides voice input, a speech recognition API (e.g., Google Speech-to-Text API) captures the audio and converts it to text. Here, the input is the patient's voice, and the output is the corresponding text information.

[0395] Step 2:

[0396] The terminal sends text data to the server. This process uses the terminal's communication capabilities to send the converted text data and emotional information recognized from the speech to the server. The input is the text and emotional information acquired by the terminal, and the output is this data sent to the server.

[0397] Step 3:

[0398] The server analyzes the text data and sentiment information it receives. The server uses a natural language processing engine (e.g., NLPProcessor) to extract symptoms and important information from the text data, and also analyzes the sentiment information. The input is the text data and sentiment information sent to the server, and the output is the analysis result.

[0399] Step 4:

[0400] The server sends and displays the analysis results on the medical professional's terminal. The analysis results include symptom information and emotion information in text data. Using the server's communication function, this data is sent to the medical professional's terminal, which then displays it. The input is the server's analysis results, and the output is the information displayed on the medical professional's terminal.

[0401] Step 5:

[0402] Medical professionals input the diagnostic results. They input the diagnostic results and treatment plan using a user interface on their terminal. This input is diagnostic information based on the analysis results provided by the medical professionals.

[0403] Step 6:

[0404] The medical professional's terminal sends the entered diagnostic results to the server. The terminal's communication function is used to send the diagnostic results to the server. The input is the diagnostic information entered on the medical professional's terminal, and the output is the data sent to the server.

[0405] Step 7:

[0406] The server re-analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Within the server, complex medical terminology is translated into everyday language, and instructions are summarized concisely. The input is the diagnostic results sent by medical professionals, and the output is text converted into a format easily understood by patients.

[0407] Step 8:

[0408] The server sends and displays the conversion results on the patient's terminal. The conversion results are sent to the patient's terminal using the server's communication function, and the terminal displays them. Audio playback is also performed using speech synthesis technology. The input is the conversion result, and the output is the information displayed on the patient's terminal and the audio playback.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] [Second Embodiment]

[0413] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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".

[0425] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it is a system that appropriately conveys information entered by the patient to the healthcare professional and provides the results entered by the healthcare professional to the patient in an easy-to-understand manner. This system consists of the following programs and processes.

[0426] System Overview

[0427] 1. Patient's terminal

[0428] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. This text data is sent to the server.

[0429] 2. Server-side processing

[0430] The server receives text data sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms and converts them into a format that is easy for medical professionals to understand. The analysis results are generated in a format using medical terminology and sent to the medical professionals' terminals.

[0431] 3. Terminals on the medical professional's side

[0432] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0433] 4. Server-side re-analysis

[0434] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[0435] 5. Patient-side display

[0436] The patient's device displays the conversion results sent from the server. These results are displayed not only in text format but can also be played back using speech synthesis. This allows patients to accurately understand the instructions from medical professionals.

[0437] Specific example

[0438] Specifically, the following operations are performed:

[0439] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the data and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then check this information on their device and take appropriate action.

[0440] The above describes the "mode for carrying out the invention" of this invention. This mode dramatically improves communication between patients and medical professionals, enabling accurate diagnosis and appropriate treatment.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[0444] Step 2:

[0445] The device uses a speech recognition API to convert the input speech into text data: "My right knee has been hurting lately."

[0446] Step 3:

[0447] The terminal sends the converted text data to the server.

[0448] Step 4:

[0449] The server analyzes the received text data, "My right knee has been hurting recently," and uses a natural language processing engine to extract keywords related to the patient's symptoms (e.g., "right knee," "painful," "recently").

[0450] Step 5:

[0451] Based on the extracted information, the server generates a message in a format that is easy for medical professionals to understand (e.g., "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain").

[0452] Step 6:

[0453] The server sends the generated message to the medical professional's terminal.

[0454] Step 7:

[0455] The device displays the received message to a medical professional, who then reviews it.

[0456] Step 8:

[0457] The user (medical professional) enters the diagnosis into the terminal. Example: "Inflammation is suspected in the right knee. I prescribe ice packs and pain medication."

[0458] Step 9:

[0459] The terminal sends the entered diagnostic results to the server.

[0460] Step 10:

[0461] The server analyzes the received diagnostic results and uses a natural language processing engine to convert them into a format that is easy for the patient to understand. Example: "You may have inflammation in your right knee. Apply ice and take medication."

[0462] Step 11:

[0463] The server sends the converted message to the patient's terminal.

[0464] Step 12:

[0465] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis.

[0466] The above outlines the specific processing steps involved in each stage.

[0467] (Example 1)

[0468] 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."

[0469] Traditionally, communication between patients and healthcare professionals has been fraught with problems. Patients often struggled to accurately describe their symptoms, and the specialized terminology used by healthcare professionals was often difficult to understand, leading to misunderstandings of diagnoses and treatment plans. This increased the risk of delays in proper diagnosis and treatment, potentially leading to a deterioration of the patient's health.

[0470] 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.

[0471] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for analyzing the received text data using a natural language processing engine, extracting keywords and important information related to the symptoms, and converting them into medical terminology, means for transmitting and displaying the analysis results on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for converting the received diagnostic results into a form that is easy for the patient to understand and replacing complex medical terminology with everyday language, and means for transmitting and displaying and playing the conversion results on the patient's terminal. This enables smooth information exchange between the patient and the medical professional, and allows for prompt and appropriate diagnosis and treatment.

[0472] A "user interface" is a mechanism that provides screens and input methods for users to interact with a system.

[0473] A "speech recognition API" is an application programming interface for converting speech data into text data.

[0474] A "server" is a computer system used to receive and process data over a network.

[0475] A "natural language processing engine" is a software program that analyzes text data and extracts its meaning.

[0476] A "keyword" is a word or phrase that indicates important information in data analysis.

[0477] "Medical terminology" refers to specialized words and expressions used in the medical field.

[0478] A "medical professional" is someone who possesses specialized knowledge in the medical field, such as a doctor or nurse.

[0479] A "diagnosis" is a judgment or conclusion made by a medical professional based on a patient's symptoms and test results.

[0480] "Conversion result" refers to information that shows how the analyzed data was ultimately represented.

[0481] "Speech synthesis" is a technology that converts text data into speech data.

[0482] This invention is a system for improving communication between patients and healthcare professionals, aiming to enable patients to describe their symptoms in detail and for healthcare professionals to communicate diagnostic results accurately and clearly to patients. This system consists of the following components and associated processes.

[0483] 1. Entering patient information

[0484] For user (patient) information input, the terminal provides a user interface that allows symptom input via voice or text. In the case of voice input, the terminal uses a speech recognition API to convert speech to text. For example, the Google Speech-to-Text API is used. The converted text data is sent from the terminal to the server.

[0485] 2. Initial analysis on the server

[0486] The server receives text data sent from the patient and stores it. Next, a natural language processing engine is used to analyze this text data and extract important keywords and information. Python's natural language processing library, such as spaCy, is used. The extracted information is converted into medical terminology in a format easily understood by healthcare professionals.

[0487] 3. Notification and input to medical professionals

[0488] Medical professionals review the analysis results sent from the server on a terminal. The terminal provides a user interface for medical professionals to input diagnostic results and treatment plans. The entered information is transmitted to the server via the electronic medical record system (EMR system).

[0489] 4. Re-analysis and conversion on the server

[0490] The server receives diagnostic results sent from medical professionals and performs a re-analysis. This re-analysis involves replacing medical terminology with everyday language. For example, the Gensim library is used to simplify the text. The converted information is then sent to the patient's terminal.

[0491] 5. Display and confirmation by the patient.

[0492] The patient's device receives the conversion results sent from the server and displays them in text format. Furthermore, it can also play the instructions audibly using speech synthesis functionality (e.g., Amazon Polly or Google Text-to-Speech API).

[0493] Specific example

[0494] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the message, and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then view this on their device and also hear the instructions by voice.

[0495] Example of a prompt

[0496] Below are examples of prompts for a generative AI model:

[0497] "Please describe in detail the processing steps of a system that improves communication between patients and healthcare professionals. Describe the entire process, from patient information input to the re-analysis of the healthcare professional's diagnosis and its subsequent communication to the patient."

[0498] The above describes the "mode for carrying out the invention" of the present invention. This mode enables smooth communication between patients and medical professionals, and allows for prompt and appropriate diagnosis and treatment.

[0499] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0500] Step 1:

[0501] The user (patient) inputs their symptoms using the terminal's user interface. In the case of voice input, the patient might say, "My right knee has been hurting lately." This voice data is input to the terminal's speech recognition API and converted into text data. This text data then becomes the input data for subsequent processing.

[0502] Step 2:

[0503] The terminal sends the converted text data to the server via an HTTP request. The server receives this request and temporarily stores the text data.

[0504] Step 3:

[0505] The server analyzes the received text data using a natural language processing engine (for example, Python's spaCy library). Specifically, it extracts keywords such as "right knee" and "painful" from the text data and converts them into a structured data format. This analyzed data becomes the input data for subsequent processing.

[0506] Step 4:

[0507] The server converts the analyzed data into medical terminology. For example, it converts "pain" to "pain" and generates sentences like "I have pain in my right knee." This makes the data easier for medical professionals to understand. This converted data is then sent to the medical professionals' terminals.

[0508] Step 5:

[0509] Medical professionals use the terminal's user interface to review the analysis data sent from the server. Next, they input the diagnosis and treatment plan. For example, they might enter, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication." This input data is then sent back to the server.

[0510] Step 6:

[0511] The server re-analyzes the received diagnostic results and converts them into everyday language that patients can easily understand. Specifically, it converts "inflammation of the right knee is suspected" to "there may be inflammation in your right knee," and further converts "we will prescribe painkillers" to "please take the medicine." The converted data becomes the input data for subsequent processing.

[0512] Step 7:

[0513] The server sends the re-analyzed and converted data to the patient's device. The device displays this data in text format and also plays it back as audio using a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech API). This allows the patient to confirm medical instructions both visually and aurally.

[0514] The above outlines the specific processing steps of this system's program.

[0515] (Application Example 1)

[0516] 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 glasses 214 will be referred to as the "terminal."

[0517] In traditional healthcare systems, communication between patients and healthcare professionals was often inefficient, particularly in verbalizing symptoms and conveying treatment plans. Furthermore, physical distance and time constraints made rapid diagnosis and treatment difficult, resulting in delays in patients receiving appropriate care. Additionally, obtaining necessary products and services for treatment after diagnosis was cumbersome.

[0518] 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.

[0519] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for the server to analyze the received text data and convert it into medical terminology, means for transmitting and displaying the analysis results on the terminal of a medical professional, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for the server to convert the received diagnostic results into a format that is easy for the patient to understand, means for transmitting and displaying the conversion results on the patient's terminal, and means for the patient to check and purchase necessary products and services for treatment within a virtual healthcare store. This enables smooth communication between the patient and the medical professional, facilitating rapid diagnosis and communication of treatment plans, and allowing for consistent acquisition of necessary products and services for treatment.

[0520] "Text data" refers to data that represents speech or text input in a digital format.

[0521] "Analysis results" refer to information obtained after it has been processed by the server using natural language processing.

[0522] "Medical terminology" refers to specialized vocabulary and phrases commonly used in the medical field.

[0523] A "user interface" refers to the interactive screens or forms that allow users (patients or healthcare professionals) to interact directly with the system.

[0524] A "server" is a computer system that receives input data, processes it, and sends the analysis results to each terminal.

[0525] A "terminal" is a device used by a patient or medical professional to display analysis results or diagnostic results.

[0526] "Diagnosis results" refer to information about a diagnosis entered by a medical professional.

[0527] A "virtual healthcare store" is a virtual marketplace that provides medical-related products and services online.

[0528] "Input means" refers to the methods or devices by which a user inputs information into a system, either by voice or text.

[0529] "Display means" refers to methods or devices for visually displaying analysis results or diagnostic results on a terminal.

[0530] "Products and services necessary for treatment" refer to medications and medical services that a patient needs based on a diagnosis made by a medical professional.

[0531] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it appropriately conveys information entered by patients to healthcare professionals and provides patients with easily understandable results entered by healthcare professionals. The following shows a specific form for realizing this system.

[0532] System Overview

[0533] 1. Patient's terminal

[0534] Patients can use a user interface to input their symptoms. They can use either voice or text input; the voice input is converted to text using the device's speech recognition API. The converted text data is then sent to the server.

[0535] 2. Server-side processing

[0536] The server receives text data sent from patients and analyzes it using a generative AI model. Using natural language processing, it extracts keywords and important information related to symptoms and generates analysis results in a format using medical terminology. These analysis results are then sent to the terminals of medical professionals.

[0537] 3. Terminals on the medical professional's side

[0538] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0539] 4. Server-side re-analysis

[0540] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[0541] 5. Patient-side display

[0542] The patient's device displays the conversion results sent from the server. This allows the patient to accurately understand the instructions from the medical professional and take appropriate action. Furthermore, they can view and purchase necessary products and services within the virtual healthcare store.

[0543] Specific example

[0544] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server analyzes the received data and notifies a healthcare professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the healthcare professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then re-analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take medication." The patient can then review this on their device and take appropriate action. During this process, they can also purchase necessary medications and medical equipment from a virtual healthcare store.

[0545] Example of a prompt

[0546] Please analyze the symptoms of the following patient:

[0547] My right knee has been hurting lately.

[0548] Analysis results:

[0549] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0550] Step 1:

[0551] The patient enters their symptoms via voice or text.

[0552] Input: Audio or text describing the patient's symptoms.

[0553] Specific action: The patient uses the terminal's user interface to input voice commands such as, "My right knee has been hurting lately."

[0554] Output: Input audio or text data.

[0555] Step 2:

[0556] Converts the input audio into text.

[0557] Input: Audio data.

[0558] Specific action: The device uses a speech recognition API to convert the speech into text, "My right knee has been hurting lately."

[0559] Output: Text data.

[0560] Step 3:

[0561] Send text data to the server.

[0562] Input: Text data.

[0563] Specific action: The terminal sends the text data "My right knee has been hurting lately" to the server.

[0564] Output: Text data received by the server.

[0565] Step 4:

[0566] The server analyzes the received text data and converts it into medical terminology.

[0567] Input: Received text data.

[0568] Specific operation: The server uses a generated AI model to analyze text data and convert it into medical terminology such as, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain."

[0569] Output: Analysis results converted into medical terminology.

[0570] Step 5:

[0571] The analysis results are sent to the terminals of medical professionals for display.

[0572] Input: Analysis results converted into medical terminology.

[0573] Specific operation: The server sends a message to the medical professional's terminal stating, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain," and this message is displayed on the terminal.

[0574] Output: Analysis results displayed on the medical professional's terminal.

[0575] Step 6:

[0576] It uses a user interface where medical professionals input diagnostic results.

[0577] Input: Diagnosis from a medical professional.

[0578] Specific operation: A medical professional uses the terminal's user interface to input a diagnosis such as, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[0579] Output: The entered diagnostic result.

[0580] Step 7:

[0581] The entered diagnostic results are sent to the server.

[0582] Input: Diagnostic result.

[0583] Specific action: A medical professional's terminal sends a diagnosis to the server stating, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[0584] Output: Diagnostic results received by the server.

[0585] Step 8:

[0586] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[0587] Input: Diagnostic result.

[0588] Specific operation: The server uses a natural language processing engine to convert the diagnostic results into a format that is easy for the patient to understand, such as "You may have inflammation in your right knee. Apply ice and take medication."

[0589] Output: Diagnostic results converted into a format that is easy for the patient to understand.

[0590] Step 9:

[0591] The conversion results are sent to the patient's device and displayed.

[0592] Input: Diagnostic results converted into a format that is easy for the patient to understand.

[0593] Specific operation: The server sends a message to the patient's device saying, "You may have inflammation in your right knee. Apply ice and take medication," and this message is displayed on the device.

[0594] Output: Diagnostic results displayed on the patient's device.

[0595] Step 10:

[0596] Patients can view and purchase necessary products and services for their treatment within a virtual healthcare store.

[0597] Input: Information about a virtual healthcare store.

[0598] Specific operation: Patients use the terminal's virtual healthcare store function to check and purchase necessary medications and medical devices.

[0599] Output: Information about the purchased goods or services.

[0600] 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.

[0601] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate information transmission. This system consists of the following programs and processes.

[0602] System Overview

[0603] 1. Patient's terminal

[0604] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. The device also has a built-in emotion engine that recognizes the patient's emotions from the voice. This text data and emotion information are sent to the server.

[0605] 2. Server-side processing

[0606] The server receives text data and emotional information sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized emotional information. The analysis results are converted into a format that is easy for medical professionals to understand.

[0607] 3. Terminals on the medical professional's side

[0608] Medical professionals can view analysis results and emotional information transmitted from the server on their terminals. This allows them to understand not only the symptoms but also the patient's emotions, leading to more appropriate diagnoses and communication. A user interface is also provided for inputting diagnostic results and treatment plans, and the entered information is transmitted to the server.

[0609] 4. Server-side re-analysis

[0610] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent back to the patient's device.

[0611] 5. Patient-side display

[0612] The patient's device displays the conversion results and emotional information sent from the server. This information is displayed not only in text format but can also be played back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[0613] Specific example

[0614] For example, if a patient voice-inputs "My right knee has been hurting recently," the system recognizes the emotion of "anxiety" from the voice input. The terminal converts this to text and sends the text "My right knee has been hurting recently" along with the emotion information of "anxiety" to the server. The server receives and analyzes the input and notifies the medical professional, "The patient is complaining of right knee pain and is feeling anxious. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "Inflammation of the right knee is suspected. I will prescribe ice and painkillers," which is analyzed by the server and notified to the patient, "There may be inflammation in your right knee. Apply ice and take the medication." The patient can then check this on the terminal and take appropriate action.

[0615] The above describes the "modes for carrying out the invention" of this invention. This mode enables communication that takes into account not only the patient's physical symptoms but also their emotional state, dramatically improving communication in medical settings.

[0616] The following describes the processing flow.

[0617] Step 1:

[0618] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[0619] Step 2:

[0620] The device converts the input voice data into text using a speech recognition API. The text generated is "My right knee has been hurting lately."

[0621] Step 3:

[0622] The device analyzes voice data using an emotion engine to recognize the emotions the patient is feeling. For example, it can recognize the emotion of "anxiety."

[0623] Step 4:

[0624] The device sends the converted text data and recognized emotion information to the server.

[0625] Step 5:

[0626] The server analyzes the received text data and sentiment information. Using a natural language processing engine, it extracts keywords and important information related to symptoms. For example, it extracts keywords such as "right knee," "painful," and "recently."

[0627] Step 6:

[0628] The server generates messages in a format easily understood by medical professionals, based on extracted information and emotional data. For example, it might generate a message such as, "The patient is complaining of pain in their right knee and is feeling anxious. Please note when the pain started and what movements cause it."

[0629] Step 7:

[0630] The server sends the generated message to the medical professional's terminal.

[0631] Step 8:

[0632] The device displays the received message to a medical professional, who then reviews it.

[0633] Step 9:

[0634] The user (medical professional) enters the diagnosis and treatment plan into the terminal. For example, they might enter, "Inflammation is suspected in the right knee. I will prescribe ice packs and pain medication."

[0635] Step 10:

[0636] The terminal sends the entered diagnostic results to the server.

[0637] Step 11:

[0638] The server analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Using a natural language processing engine, it replaces complex medical jargon with everyday language. For example, it might generate a message like, "You may have inflammation in your right knee. Apply ice and take medication."

[0639] Step 12:

[0640] The server sends the converted message to the patient's terminal.

[0641] Step 13:

[0642] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[0643] The above outlines the specific processing steps involved in each stage.

[0644] (Example 2)

[0645] 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".

[0646] Conventional medical communication systems need to not only accurately understand a patient's symptoms but also consider their emotional information to enable more accurate and effective diagnosis and treatment. However, current systems lack the technology to appropriately recognize and analyze a patient's emotional information, resulting in a decline in the quality of communication and often placing a burden on diagnosis and treatment. This invention aims to solve these problems and significantly improve communication between patients and medical professionals.

[0647] 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.

[0648] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for recognizing emotions from the input voice data, means for transmitting text data and emotional information to the server, means for analyzing the received text data and emotional information and extracting keywords and important information related to the symptoms, means for transmitting and displaying the analysis results and emotional information on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnosis results and treatment plans, means for transmitting the input diagnosis results and treatment plans to the server, means for converting the received diagnosis results into a format that is easy for the patient to understand and transmitting the conversion results to the patient's terminal, and means for displaying or playing the conversion results and emotional information on the patient's terminal. This makes it possible to diagnose and treat patients while considering not only their physical symptoms but also their emotional state, and significantly improves the quality of communication in medical settings.

[0649] A "user interface for patient symptom input via voice or text" refers to an interface that allows patients to input their symptoms via voice or text, and is an input device for interaction between the system and the patient.

[0650] "Means for converting input speech to text" refers to a processing function that uses speech recognition technology to convert voice input data into text data.

[0651] "Means of recognizing emotions from input audio data" refers to a processing function that uses audio analysis technology to extract emotional information from audio data and determine the emotion being expressed.

[0652] "Means for sending text data and sentiment information to a server" refers to communication means for sending input text data and sentiment information to a server via a network.

[0653] "Means for the server to analyze received text data and sentiment information and extract keywords and important information related to symptoms" refers to a processing function in which the server uses natural language processing technology to analyze text data and sentiment information and identify important keywords and information.

[0654] "Means for transmitting and displaying analysis results and emotional information on a medical professional's terminal" refers to a function that transmits the analysis results and emotional information from the server to a medical professional's terminal via the network and displays them.

[0655] "Means of providing a user interface for medical professionals to input diagnostic results and treatment plans" refers to an interface for medical professionals to input diagnostic results and treatment plans, and an input device for interaction between the system and medical professionals.

[0656] "Means for transmitting entered diagnostic results and treatment plans to a server" refers to communication means for transmitting diagnostic results and treatment plans entered by medical professionals to a server via a network.

[0657] "A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand and sends the converted results to the patient's terminal" refers to a function that analyzes the received diagnostic results, converts them into simple language that the patient can understand, and sends the converted results to the patient's terminal.

[0658] "Means for displaying or playing back the conversion results and emotional information on the patient's terminal" refers to a function that allows the patient's terminal to display the conversion results and emotional information sent from the server on a screen, or to play them back as audio using speech synthesis technology.

[0659] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate and effective information transmission. This system is built on a network basis, including patient terminals, a server, and healthcare professional terminals.

[0660] Patient's terminal

[0661] The patient's terminal provides a user interface for the patient to input their symptoms. The patient can input via voice or text. The input voice is converted to text using a speech recognition API (e.g., a speech recognition API). Furthermore, an emotion engine (e.g., emotion recognition technology) built into the terminal is used to recognize the patient's emotions from the voice data. This text data and emotion information are transmitted to a server via the network.

[0662] Server-side processing

[0663] The server receives text data and sentiment information sent from the patient and analyzes it using a natural language processing engine (e.g., a natural language processing engine). Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized sentiment information. The analysis results and sentiment information are converted into a format that is easy for medical professionals to understand and sent to the medical professionals' terminals.

[0664] Terminal on the medical professional's side

[0665] The medical professional's terminal displays analysis results and sentiment information sent from the server. The medical professional can use the user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0666] Server-side re-analysis

[0667] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent to the patient's device.

[0668] Patient-side display

[0669] The patient's device displays the translated results and emotional information sent from the server. This allows the patient to accurately understand the instructions from the medical professional. In addition to displaying in text format, it is also possible to play the information back using speech synthesis technology (e.g., speech synthesis technology).

[0670] Specific example

[0671] For example, if a patient voice-inputs "My right knee has been hurting recently," the terminal converts the voice into text data, "My right knee has been hurting recently," and uses emotion recognition technology to recognize the emotion "anxiety." When this text data and emotion information are sent to the server, the server uses a natural language processing engine to analyze the data and extract information such as "right knee pain" and "anxiety." The analysis results are communicated to the medical professional in the form of, "The patient is complaining of right knee pain and is feeling anxious. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "Inflammation of the right knee is suspected. I will prescribe ice and painkillers," and the server re-analyzes this and tells the patient, "There may be inflammation in your right knee. Apply ice and take the medicine."

[0672] Example of a prompt

[0673] "A patient is complaining of pain in their right knee, and I'm feeling anxious. How should I explain this to a medical professional?"

[0674] "Please translate the diagnosis into language that the patient can easily understand. Diagnosis: Inflammation of the right knee; Prescription: Icing and pain medication."

[0675] The above describes the embodiments of the present invention. This embodiment enables effective communication that takes into account not only the patient's physical symptoms but also their emotional state, dramatically improving diagnosis and treatment in medical settings.

[0676] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0677] Step 1:

[0678] The user (patient) enters their symptoms using the terminal's user interface.

[0679] Specific action: The patient inputs by voice, "My right knee has been hurting lately."

[0680] Input: Audio data.

[0681] Output: Audio data.

[0682] Step 2:

[0683] The device sends the input voice data to a speech recognition API, which then converts it to text.

[0684] Specific operation: The speech recognition API converts the voice data "My right knee has been hurting recently" into the text "My right knee has been hurting recently".

[0685] Input: Audio data.

[0686] Output: Text data.

[0687] Step 3:

[0688] The device recognizes emotions from the input voice data.

[0689] Specific operation: The emotion engine recognizes the emotion "anxiety" from the audio data.

[0690] Input: Audio data.

[0691] Output: Emotional information.

[0692] Step 4:

[0693] The device sends text data and sentiment information to the server.

[0694] Specific action: The device sends the text data "My right knee has been hurting lately" and the emotion information "anxiety" to the server.

[0695] Input: Text data and sentiment information.

[0696] Output: Text data and sentiment information sent to the server.

[0697] Step 5:

[0698] The server analyzes the text data and sentiment information it receives.

[0699] Specific actions: The natural language processing engine extracts keywords such as "right knee pain" and "anxiety."

[0700] Input: Text data and sentiment information.

[0701] Output: Analysis results and sentiment information.

[0702] Step 6:

[0703] The server transmits the analysis results and emotional information to the medical professional's terminal for display.

[0704] Specific actions: The analysis results send information to the medical professional's terminal stating, "The patient is complaining of pain in their right knee and is feeling anxious. Please confirm when the pain started and what movements cause the pain."

[0705] Input: Analysis results and sentiment information.

[0706] Output: Analysis results and sentiment information displayed on the medical professional's terminal.

[0707] Step 7:

[0708] Medical professionals input the diagnosis results and treatment plan.

[0709] Specific action: A medical professional enters into the terminal, "Inflammation is suspected in the right knee. I will prescribe ice and pain medication."

[0710] Input: Diagnosis and treatment plan.

[0711] Output: Input diagnostic results and treatment plan.

[0712] Step 8:

[0713] The terminal sends the entered diagnostic results and treatment plan to the server.

[0714] Specific action: The medical professional enters "Inflammation is suspected in the right knee. I will prescribe ice and pain medication" and sends it to the server.

[0715] Input: Diagnosis and treatment plan.

[0716] Output: Diagnostic results and treatment plan sent to the server.

[0717] Step 9:

[0718] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[0719] Specific action: The server converts the diagnosis "Inflammation of the right knee is suspected. We prescribe ice and pain medication" to "There may be inflammation in your right knee. Apply ice and take medication."

[0720] Input: Diagnosis and treatment plan.

[0721] Output: Converted diagnostic results.

[0722] Step 10:

[0723] The server sends the conversion results to the patient's terminal.

[0724] Specific operation: The server sends the converted diagnostic results to the patient's terminal.

[0725] Input: Converted diagnostic results.

[0726] Output: The conversion result sent to the patient's terminal.

[0727] Step 11:

[0728] The patient's device displays or plays back the conversion results and emotional information via audio.

[0729] Specific actions: The patient's device displays the translated message, "You may have inflammation in your right knee. Apply ice and take medicine," or plays it aloud using speech synthesis technology.

[0730] Input: Conversion result and sentiment information.

[0731] Output: The displayed text or the played audio.

[0732] (Application Example 2)

[0733] 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 will be referred to as the "terminal."

[0734] Traditional security systems have struggled to monitor and analyze the psychological state of external visitors and employees in real time. Furthermore, early detection of potential threats is difficult, leading to delays in post-incident response. There has also been a lack of means to analyze emotional information such as employee stress and anxiety, enabling timely and appropriate responses.

[0735] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for recognizing and analyzing emotional information from voice data, means for transmitting and displaying the analysis results on the security guard's terminal, and means for detecting abnormal emotions and issuing warnings. This enables real-time analysis of emotional information of external visitors and employees, early detection of potential threats, and swift and appropriate responses.

[0736] A "user interface for patient symptom input via voice or text" is an input device designed to allow patients to easily input their symptoms as voice or text information.

[0737] "Means for converting input speech to text" refers to a device or software that has the function of converting speech information into corresponding text information using speech recognition technology.

[0738] "Means for sending text data to a server" refers to a communication device or program for sending acquired text information to a designated server via a network.

[0739] "A means of analyzing text data received by a server and converting it into medical terminology" refers to a process in which a program running on the server converts general text data received into specialized medical terminology.

[0740] "Means for transmitting and displaying analysis results on a medical professional's terminal" refers to a device or software that transmits the results of analysis performed on a server to a medical professional's terminal via a network and displays them on that terminal.

[0741] A "user interface for medical professionals to input diagnostic results" refers to a dedicated input device or screen for medical professionals to input diagnostic results and treatment plans.

[0742] "Means for transmitting entered diagnostic results to a server" refers to a device or program that has the function of transmitting diagnostic results entered by a medical professional to a server via a network.

[0743] "Means of converting diagnostic results received by the server into a format that is easy for patients to understand" refers to the process of converting specialized diagnostic results received by the server into everyday language that patients can easily understand.

[0744] "Means for sending and displaying conversion results on the patient's terminal" refers to a device or software that has the function of sending the converted results back to the patient's terminal and displaying them on that terminal.

[0745] "Means for recognizing and analyzing emotional information from collected audio data" refers to a technology or solution for recognizing and analyzing the emotional state of a speaker contained within audio data.

[0746] "Means for transmitting and displaying analysis results including emotional information on a medical professional's terminal" refers to a device or software that transmits and displays analysis results including emotional information on a medical professional's terminal via a network.

[0747] This invention relates to a system for improving communication between patients and healthcare professionals, and in particular to enabling more accurate information transmission by recognizing and analyzing the patient's emotional information. The embodiments for carrying out this invention are as follows.

[0748] System Configuration

[0749] 1. Patient's device:

[0750] It provides a user interface for patients to input their symptoms via voice or text.

[0751] It has the ability to convert speech to text using a speech recognition API (for example, Google Speech-to-Text API).

[0752] To recognize emotional information from speech, incorporate an emotion recognition library (e.g., EmotionRecognizer).

[0753] A communication function that sends input text data and sentiment information to the server.

[0754] 2. Server-side processing:

[0755] A natural language processing engine (e.g., NLPProcessor) is used to analyze the received text data and sentiment information.

[0756] It generates analysis results and converts them into a format that is easy for medical professionals to understand.

[0757] The analysis results, including emotional information, are sent to the terminals of medical professionals.

[0758] 3. Terminals used by medical professionals:

[0759] It has a display interface that allows medical professionals to review analysis results and emotional information.

[0760] It provides a user interface for inputting diagnostic results and treatment plans.

[0761] A communication function that sends the entered diagnostic results to the server.

[0762] 4. Server-side re-analysis:

[0763] The received diagnostic results are reanalyzed and converted into a format that is easy for the patient to understand.

[0764] The conversion results are sent back to the patient's device.

[0765] 5. Patient's display:

[0766] It has a display interface that allows patients to check the conversion results received from the server.

[0767] It has a function that allows instructions to be played back as audio using speech synthesis.

[0768] Examples of specific cases and prompt statements

[0769] For example, consider a scenario where this system is installed in a security guard's smart glasses. When the guard is spoken to by an outside visitor, the audio data is collected and analyzed in real time. If the system detects that the visitor is "slightly panicked," it issues a warning and prompts the guard to take immediate action.

[0770] Also, consider the following example prompts for a generative AI model:

[0771] The system collected audio data and generated the following sentiment and text information:

[0772] Voice: "I'm a little nervous, but I'm okay."

[0773] Emotion: “Tension, anxiety”

[0774] Please send this to the server in the following format:

[0775] {

[0776] "text_input": "I'm a little nervous, but I'm okay",

[0777] "emotion": "tension, anxiety",

[0778] "Analysis": "The visitor appears nervous, but there doesn't seem to be any major problem."

[0779] }

[0780] Thus, the present invention is a system that analyzes voice data and emotional information and provides it to the appropriate user, thereby achieving highly accurate medical support and security management.

[0781] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0782] Step 1:

[0783] The patient enters their symptoms via voice or text. Specifically, when the patient provides voice input, a speech recognition API (e.g., Google Speech-to-Text API) captures the audio and converts it to text. Here, the input is the patient's voice, and the output is the corresponding text information.

[0784] Step 2:

[0785] The terminal sends text data to the server. This process uses the terminal's communication capabilities to send the converted text data and emotional information recognized from the speech to the server. The input is the text and emotional information acquired by the terminal, and the output is this data sent to the server.

[0786] Step 3:

[0787] The server analyzes the text data and sentiment information it receives. The server uses a natural language processing engine (e.g., NLPProcessor) to extract symptoms and important information from the text data, and also analyzes the sentiment information. The input is the text data and sentiment information sent to the server, and the output is the analysis result.

[0788] Step 4:

[0789] The server sends and displays the analysis results on the medical professional's terminal. The analysis results include symptom information and emotion information in text data. Using the server's communication function, this data is sent to the medical professional's terminal, which then displays it. The input is the server's analysis results, and the output is the information displayed on the medical professional's terminal.

[0790] Step 5:

[0791] Medical professionals input the diagnostic results. They input the diagnostic results and treatment plan using a user interface on their terminal. This input is diagnostic information based on the analysis results provided by the medical professionals.

[0792] Step 6:

[0793] The medical professional's terminal sends the entered diagnostic results to the server. The terminal's communication function is used to send the diagnostic results to the server. The input is the diagnostic information entered on the medical professional's terminal, and the output is the data sent to the server.

[0794] Step 7:

[0795] The server re-analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Within the server, complex medical terminology is translated into everyday language, and instructions are summarized concisely. The input is the diagnostic results sent by medical professionals, and the output is text converted into a format easily understood by patients.

[0796] Step 8:

[0797] The server sends and displays the conversion results on the patient's terminal. The conversion results are sent to the patient's terminal using the server's communication function, and the terminal displays them. Audio playback is also performed using speech synthesis technology. The input is the conversion result, and the output is the information displayed on the patient's terminal and the audio playback.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] [Third Embodiment]

[0802] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0803] 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.

[0804] 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).

[0805] 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.

[0806] 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.

[0807] 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).

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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".

[0814] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it is a system that appropriately conveys information entered by the patient to the healthcare professional and provides the results entered by the healthcare professional to the patient in an easy-to-understand manner. This system consists of the following programs and processes.

[0815] System Overview

[0816] 1. Patient's terminal

[0817] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. This text data is sent to the server.

[0818] 2. Server-side processing

[0819] The server receives text data sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms and converts them into a format that is easy for medical professionals to understand. The analysis results are generated in a format using medical terminology and sent to the medical professionals' terminals.

[0820] 3. Terminals on the medical professional's side

[0821] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0822] 4. Server-side re-analysis

[0823] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[0824] 5. Patient-side display

[0825] The patient's device displays the conversion results sent from the server. These results are displayed not only in text format but can also be played back using speech synthesis. This allows patients to accurately understand the instructions from medical professionals.

[0826] Specific example

[0827] Specifically, the following operations are performed:

[0828] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the data and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then check this information on their device and take appropriate action.

[0829] The above describes the "mode for carrying out the invention" of this invention. This mode dramatically improves communication between patients and medical professionals, enabling accurate diagnosis and appropriate treatment.

[0830] The following describes the processing flow.

[0831] Step 1:

[0832] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[0833] Step 2:

[0834] The device uses a speech recognition API to convert the input speech into text data: "My right knee has been hurting lately."

[0835] Step 3:

[0836] The terminal sends the converted text data to the server.

[0837] Step 4:

[0838] The server analyzes the received text data, "My right knee has been hurting recently," and uses a natural language processing engine to extract keywords related to the patient's symptoms (e.g., "right knee," "painful," "recently").

[0839] Step 5:

[0840] Based on the extracted information, the server generates a message in a format that is easy for medical professionals to understand (e.g., "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain").

[0841] Step 6:

[0842] The server sends the generated message to the medical professional's terminal.

[0843] Step 7:

[0844] The device displays the received message to a medical professional, who then reviews it.

[0845] Step 8:

[0846] The user (medical professional) enters the diagnosis into the terminal. Example: "Inflammation is suspected in the right knee. I prescribe ice packs and pain medication."

[0847] Step 9:

[0848] The terminal sends the entered diagnostic results to the server.

[0849] Step 10:

[0850] The server analyzes the received diagnostic results and uses a natural language processing engine to convert them into a format that is easy for the patient to understand. Example: "You may have inflammation in your right knee. Apply ice and take medication."

[0851] Step 11:

[0852] The server sends the converted message to the patient's terminal.

[0853] Step 12:

[0854] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis.

[0855] The above outlines the specific processing steps involved in each stage.

[0856] (Example 1)

[0857] 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."

[0858] Traditionally, communication between patients and healthcare professionals has been fraught with problems. Patients often struggled to accurately describe their symptoms, and the specialized terminology used by healthcare professionals was often difficult to understand, leading to misunderstandings of diagnoses and treatment plans. This increased the risk of delays in proper diagnosis and treatment, potentially leading to a deterioration of the patient's health.

[0859] 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.

[0860] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for analyzing the received text data using a natural language processing engine, extracting keywords and important information related to the symptoms, and converting them into medical terminology, means for transmitting and displaying the analysis results on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for converting the received diagnostic results into a form that is easy for the patient to understand and replacing complex medical terminology with everyday language, and means for transmitting and displaying and playing the conversion results on the patient's terminal. This enables smooth information exchange between the patient and the medical professional, and allows for prompt and appropriate diagnosis and treatment.

[0861] A "user interface" is a mechanism that provides screens and input methods for users to interact with a system.

[0862] A "speech recognition API" is an application programming interface for converting speech data into text data.

[0863] A "server" is a computer system used to receive and process data over a network.

[0864] A "natural language processing engine" is a software program that analyzes text data and extracts its meaning.

[0865] A "keyword" is a word or phrase that indicates important information in data analysis.

[0866] "Medical terminology" refers to specialized words and expressions used in the medical field.

[0867] A "medical professional" is someone who possesses specialized knowledge in the medical field, such as a doctor or nurse.

[0868] A "diagnosis" is a judgment or conclusion made by a medical professional based on a patient's symptoms and test results.

[0869] "Conversion result" refers to information that shows how the analyzed data was ultimately represented.

[0870] "Speech synthesis" is a technology that converts text data into speech data.

[0871] This invention is a system for improving communication between patients and healthcare professionals, aiming to enable patients to describe their symptoms in detail and for healthcare professionals to communicate diagnostic results accurately and clearly to patients. This system consists of the following components and associated processes.

[0872] 1. Entering patient information

[0873] For user (patient) information input, the terminal provides a user interface that allows symptom input via voice or text. In the case of voice input, the terminal uses a speech recognition API to convert speech to text. For example, the Google Speech-to-Text API is used. The converted text data is sent from the terminal to the server.

[0874] 2. Initial analysis on the server

[0875] The server receives text data sent from the patient and stores it. Next, a natural language processing engine is used to analyze this text data and extract important keywords and information. Python's natural language processing library, such as spaCy, is used. The extracted information is converted into medical terminology in a format easily understood by healthcare professionals.

[0876] 3. Notification and input to medical professionals

[0877] Medical professionals review the analysis results sent from the server on a terminal. The terminal provides a user interface for medical professionals to input diagnostic results and treatment plans. The entered information is transmitted to the server via the electronic medical record system (EMR system).

[0878] 4. Re-analysis and conversion on the server

[0879] The server receives diagnostic results sent from medical professionals and performs a re-analysis. This re-analysis involves replacing medical terminology with everyday language. For example, the Gensim library is used to simplify the text. The converted information is then sent to the patient's terminal.

[0880] 5. Display and confirmation by the patient.

[0881] The patient's device receives the conversion results sent from the server and displays them in text format. Furthermore, it can also play the instructions audibly using speech synthesis functionality (e.g., Amazon Polly or Google Text-to-Speech API).

[0882] Specific example

[0883] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the message, and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then view this on their device and also hear the instructions by voice.

[0884] Example of a prompt

[0885] Below are examples of prompts for a generative AI model:

[0886] "Please describe in detail the processing steps of a system that improves communication between patients and healthcare professionals. Describe the entire process, from patient information input to the re-analysis of the healthcare professional's diagnosis and its subsequent communication to the patient."

[0887] The above describes the "mode for carrying out the invention" of the present invention. This mode enables smooth communication between patients and medical professionals, and allows for prompt and appropriate diagnosis and treatment.

[0888] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0889] Step 1:

[0890] The user (patient) inputs their symptoms using the terminal's user interface. In the case of voice input, the patient might say, "My right knee has been hurting lately." This voice data is input to the terminal's speech recognition API and converted into text data. This text data then becomes the input data for subsequent processing.

[0891] Step 2:

[0892] The terminal sends the converted text data to the server via an HTTP request. The server receives this request and temporarily stores the text data.

[0893] Step 3:

[0894] The server analyzes the received text data using a natural language processing engine (for example, Python's spaCy library). Specifically, it extracts keywords such as "right knee" and "painful" from the text data and converts them into a structured data format. This analyzed data becomes the input data for subsequent processing.

[0895] Step 4:

[0896] The server converts the analyzed data into medical terminology. For example, it converts "pain" to "pain" and generates sentences like "I have pain in my right knee." This makes the data easier for medical professionals to understand. This converted data is then sent to the medical professionals' terminals.

[0897] Step 5:

[0898] Medical professionals use the terminal's user interface to review the analysis data sent from the server. Next, they input the diagnosis and treatment plan. For example, they might enter, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication." This input data is then sent back to the server.

[0899] Step 6:

[0900] The server re-analyzes the received diagnostic results and converts them into everyday language that patients can easily understand. Specifically, it converts "inflammation of the right knee is suspected" to "there may be inflammation in your right knee," and further converts "we will prescribe painkillers" to "please take the medicine." The converted data becomes the input data for subsequent processing.

[0901] Step 7:

[0902] The server sends the re-analyzed and converted data to the patient's device. The device displays this data in text format and also plays it back as audio using a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech API). This allows the patient to confirm medical instructions both visually and aurally.

[0903] The above outlines the specific processing steps of this system's program.

[0904] (Application Example 1)

[0905] 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."

[0906] In traditional healthcare systems, communication between patients and healthcare professionals was often inefficient, particularly in verbalizing symptoms and conveying treatment plans. Furthermore, physical distance and time constraints made rapid diagnosis and treatment difficult, resulting in delays in patients receiving appropriate care. Additionally, obtaining necessary products and services for treatment after diagnosis was cumbersome.

[0907] 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.

[0908] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for the server to analyze the received text data and convert it into medical terminology, means for transmitting and displaying the analysis results on the terminal of a medical professional, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for the server to convert the received diagnostic results into a format that is easy for the patient to understand, means for transmitting and displaying the conversion results on the patient's terminal, and means for the patient to check and purchase necessary products and services for treatment within a virtual healthcare store. This enables smooth communication between the patient and the medical professional, facilitating rapid diagnosis and communication of treatment plans, and allowing for consistent acquisition of necessary products and services for treatment.

[0909] "Text data" refers to data that represents speech or text input in a digital format.

[0910] "Analysis results" refer to information obtained after it has been processed by the server using natural language processing.

[0911] "Medical terminology" refers to specialized vocabulary and phrases commonly used in the medical field.

[0912] A "user interface" refers to the interactive screens or forms that allow users (patients or healthcare professionals) to interact directly with the system.

[0913] A "server" is a computer system that receives input data, processes it, and sends the analysis results to each terminal.

[0914] A "terminal" is a device used by a patient or medical professional to display analysis results or diagnostic results.

[0915] "Diagnosis results" refer to information about a diagnosis entered by a medical professional.

[0916] A "virtual healthcare store" is a virtual marketplace that provides medical-related products and services online.

[0917] "Input means" refers to the methods or devices by which a user inputs information into a system, either by voice or text.

[0918] "Display means" refers to methods or devices for visually displaying analysis results or diagnostic results on a terminal.

[0919] "Products and services necessary for treatment" refer to medications and medical services that a patient needs based on a diagnosis made by a medical professional.

[0920] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it appropriately conveys information entered by patients to healthcare professionals and provides patients with easily understandable results entered by healthcare professionals. The following shows a specific form for realizing this system.

[0921] System Overview

[0922] 1. Patient's terminal

[0923] Patients can use a user interface to input their symptoms. They can use either voice or text input; the voice input is converted to text using the device's speech recognition API. The converted text data is then sent to the server.

[0924] 2. Server-side processing

[0925] The server receives text data sent from patients and analyzes it using a generative AI model. Using natural language processing, it extracts keywords and important information related to symptoms and generates analysis results in a format using medical terminology. These analysis results are then sent to the terminals of medical professionals.

[0926] 3. Terminals on the medical professional's side

[0927] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[0928] 4. Server-side re-analysis

[0929] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[0930] 5. Patient-side display

[0931] The patient's device displays the conversion results sent from the server. This allows the patient to accurately understand the instructions from the medical professional and take appropriate action. Furthermore, they can view and purchase necessary products and services within the virtual healthcare store.

[0932] Specific example

[0933] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server analyzes the received data and notifies a healthcare professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the healthcare professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then re-analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take medication." The patient can then review this on their device and take appropriate action. During this process, they can also purchase necessary medications and medical equipment from a virtual healthcare store.

[0934] Example of a prompt

[0935] Please analyze the symptoms of the following patient:

[0936] My right knee has been hurting lately.

[0937] Analysis results:

[0938] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0939] Step 1:

[0940] The patient enters their symptoms via voice or text.

[0941] Input: Audio or text describing the patient's symptoms.

[0942] Specific action: The patient uses the terminal's user interface to input voice commands such as, "My right knee has been hurting lately."

[0943] Output: Input audio or text data.

[0944] Step 2:

[0945] Converts the input audio into text.

[0946] Input: Audio data.

[0947] Specific action: The device uses a speech recognition API to convert the speech into text, "My right knee has been hurting lately."

[0948] Output: Text data.

[0949] Step 3:

[0950] Send text data to the server.

[0951] Input: Text data.

[0952] Specific action: The terminal sends the text data "My right knee has been hurting lately" to the server.

[0953] Output: Text data received by the server.

[0954] Step 4:

[0955] The server analyzes the received text data and converts it into medical terminology.

[0956] Input: Received text data.

[0957] Specific operation: The server uses a generated AI model to analyze text data and convert it into medical terminology such as, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain."

[0958] Output: Analysis results converted into medical terminology.

[0959] Step 5:

[0960] The analysis results are sent to the terminals of medical professionals for display.

[0961] Input: Analysis results converted into medical terminology.

[0962] Specific operation: The server sends a message to the medical professional's terminal stating, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain," and this message is displayed on the terminal.

[0963] Output: Analysis results displayed on the medical professional's terminal.

[0964] Step 6:

[0965] It uses a user interface where medical professionals input diagnostic results.

[0966] Input: Diagnosis from a medical professional.

[0967] Specific operation: A medical professional uses the terminal's user interface to input a diagnosis such as, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[0968] Output: The entered diagnostic result.

[0969] Step 7:

[0970] The entered diagnostic results are sent to the server.

[0971] Input: Diagnostic result.

[0972] Specific action: A medical professional's terminal sends a diagnosis to the server stating, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[0973] Output: Diagnostic results received by the server.

[0974] Step 8:

[0975] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[0976] Input: Diagnostic result.

[0977] Specific operation: The server uses a natural language processing engine to convert the diagnostic results into a format that is easy for the patient to understand, such as "You may have inflammation in your right knee. Apply ice and take medication."

[0978] Output: Diagnostic results converted into a format that is easy for the patient to understand.

[0979] Step 9:

[0980] The conversion results are sent to the patient's device and displayed.

[0981] Input: Diagnostic results converted into a format that is easy for the patient to understand.

[0982] Specific operation: The server sends a message to the patient's device saying, "You may have inflammation in your right knee. Apply ice and take medication," and this message is displayed on the device.

[0983] Output: Diagnostic results displayed on the patient's device.

[0984] Step 10:

[0985] Patients can view and purchase necessary products and services for their treatment within a virtual healthcare store.

[0986] Input: Information about a virtual healthcare store.

[0987] Specific operation: Patients use the terminal's virtual healthcare store function to check and purchase necessary medications and medical devices.

[0988] Output: Information about the purchased goods or services.

[0989] 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.

[0990] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate information transmission. This system consists of the following programs and processes.

[0991] System Overview

[0992] 1. Patient's terminal

[0993] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. The device also has a built-in emotion engine that recognizes the patient's emotions from the voice. This text data and emotion information are sent to the server.

[0994] 2. Server-side processing

[0995] The server receives text data and emotional information sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized emotional information. The analysis results are converted into a format that is easy for medical professionals to understand.

[0996] 3. Terminals on the medical professional's side

[0997] Medical professionals can view analysis results and emotional information transmitted from the server on their terminals. This allows them to understand not only the symptoms but also the patient's emotions, leading to more appropriate diagnoses and communication. A user interface is also provided for inputting diagnostic results and treatment plans, and the entered information is transmitted to the server.

[0998] 4. Server-side re-analysis

[0999] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent back to the patient's device.

[1000] 5. Patient-side display

[1001] The patient's device displays the conversion results and emotional information sent from the server. This information is displayed not only in text format but can also be played back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[1002] Specific example

[1003] For example, if a patient voice-inputs "My right knee has been hurting recently," the system recognizes the emotion of "anxiety" from the voice input. The terminal converts this to text and sends the text "My right knee has been hurting recently" along with the emotion information of "anxiety" to the server. The server receives and analyzes the input and notifies the medical professional, "The patient is complaining of right knee pain and is feeling anxious. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "Inflammation of the right knee is suspected. I will prescribe ice and painkillers," which is analyzed by the server and notified to the patient, "There may be inflammation in your right knee. Apply ice and take the medication." The patient can then check this on the terminal and take appropriate action.

[1004] The above describes the "modes for carrying out the invention" of this invention. This mode enables communication that takes into account not only the patient's physical symptoms but also their emotional state, dramatically improving communication in medical settings.

[1005] The following describes the processing flow.

[1006] Step 1:

[1007] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[1008] Step 2:

[1009] The device converts the input voice data into text using a speech recognition API. The text generated is "My right knee has been hurting lately."

[1010] Step 3:

[1011] The device analyzes voice data using an emotion engine to recognize the emotions the patient is feeling. For example, it can recognize the emotion of "anxiety."

[1012] Step 4:

[1013] The device sends the converted text data and recognized emotion information to the server.

[1014] Step 5:

[1015] The server analyzes the received text data and sentiment information. Using a natural language processing engine, it extracts keywords and important information related to symptoms. For example, it extracts keywords such as "right knee," "painful," and "recently."

[1016] Step 6:

[1017] The server generates messages in a format easily understood by medical professionals, based on extracted information and emotional data. For example, it might generate a message such as, "The patient is complaining of pain in their right knee and is feeling anxious. Please note when the pain started and what movements cause it."

[1018] Step 7:

[1019] The server sends the generated message to the medical professional's terminal.

[1020] Step 8:

[1021] The device displays the received message to a medical professional, who then reviews it.

[1022] Step 9:

[1023] The user (medical professional) enters the diagnosis and treatment plan into the terminal. For example, they might enter, "Inflammation is suspected in the right knee. I will prescribe ice packs and pain medication."

[1024] Step 10:

[1025] The terminal sends the entered diagnostic results to the server.

[1026] Step 11:

[1027] The server analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Using a natural language processing engine, it replaces complex medical jargon with everyday language. For example, it might generate a message like, "You may have inflammation in your right knee. Apply ice and take medication."

[1028] Step 12:

[1029] The server sends the converted message to the patient's terminal.

[1030] Step 13:

[1031] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[1032] The above outlines the specific processing steps involved in each stage.

[1033] (Example 2)

[1034] 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."

[1035] Conventional medical communication systems need to not only accurately understand a patient's symptoms but also consider their emotional information to enable more accurate and effective diagnosis and treatment. However, current systems lack the technology to appropriately recognize and analyze a patient's emotional information, resulting in a decline in the quality of communication and often placing a burden on diagnosis and treatment. This invention aims to solve these problems and significantly improve communication between patients and medical professionals.

[1036] 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.

[1037] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for recognizing emotions from the input voice data, means for transmitting text data and emotional information to the server, means for analyzing the received text data and emotional information and extracting keywords and important information related to the symptoms, means for transmitting and displaying the analysis results and emotional information on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnosis results and treatment plans, means for transmitting the input diagnosis results and treatment plans to the server, means for converting the received diagnosis results into a format that is easy for the patient to understand and transmitting the conversion results to the patient's terminal, and means for displaying or playing the conversion results and emotional information on the patient's terminal. This makes it possible to diagnose and treat patients while considering not only their physical symptoms but also their emotional state, and significantly improves the quality of communication in medical settings.

[1038] A "user interface for patient symptom input via voice or text" refers to an interface that allows patients to input their symptoms via voice or text, and is an input device for interaction between the system and the patient.

[1039] "Means for converting input speech to text" refers to a processing function that uses speech recognition technology to convert voice input data into text data.

[1040] "Means of recognizing emotions from input audio data" refers to a processing function that uses audio analysis technology to extract emotional information from audio data and determine the emotion being expressed.

[1041] "Means for sending text data and sentiment information to a server" refers to communication means for sending input text data and sentiment information to a server via a network.

[1042] "Means for the server to analyze received text data and sentiment information and extract keywords and important information related to symptoms" refers to a processing function in which the server uses natural language processing technology to analyze text data and sentiment information and identify important keywords and information.

[1043] "Means for transmitting and displaying analysis results and emotional information on a medical professional's terminal" refers to a function that transmits the analysis results and emotional information from the server to a medical professional's terminal via the network and displays them.

[1044] "Means of providing a user interface for medical professionals to input diagnostic results and treatment plans" refers to an interface for medical professionals to input diagnostic results and treatment plans, and an input device for interaction between the system and medical professionals.

[1045] "Means for transmitting entered diagnostic results and treatment plans to a server" refers to communication means for transmitting diagnostic results and treatment plans entered by medical professionals to a server via a network.

[1046] "A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand and sends the converted results to the patient's terminal" refers to a function that analyzes the received diagnostic results, converts them into simple language that the patient can understand, and sends the converted results to the patient's terminal.

[1047] "Means for displaying or playing back the conversion results and emotional information on the patient's terminal" refers to a function that allows the patient's terminal to display the conversion results and emotional information sent from the server on a screen, or to play them back as audio using speech synthesis technology.

[1048] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate and effective information transmission. This system is built on a network basis, including patient terminals, a server, and healthcare professional terminals.

[1049] Patient's terminal

[1050] The patient's terminal provides a user interface for the patient to input their symptoms. The patient can input via voice or text. The input voice is converted to text using a speech recognition API (e.g., a speech recognition API). Furthermore, an emotion engine (e.g., emotion recognition technology) built into the terminal is used to recognize the patient's emotions from the voice data. This text data and emotion information are transmitted to a server via the network.

[1051] Server-side processing

[1052] The server receives text data and sentiment information sent from the patient and analyzes it using a natural language processing engine (e.g., a natural language processing engine). Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized sentiment information. The analysis results and sentiment information are converted into a format that is easy for medical professionals to understand and sent to the medical professionals' terminals.

[1053] Terminal on the medical professional's side

[1054] The medical professional's terminal displays analysis results and sentiment information sent from the server. The medical professional can use the user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[1055] Server-side re-analysis

[1056] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent to the patient's device.

[1057] Patient-side display

[1058] The patient's device displays the translated results and emotional information sent from the server. This allows the patient to accurately understand the instructions from the medical professional. In addition to displaying in text format, it is also possible to play the information back using speech synthesis technology (e.g., speech synthesis technology).

[1059] Specific example

[1060] For example, if a patient voice-inputs "My right knee has been hurting recently," the terminal converts the voice into text data, "My right knee has been hurting recently," and uses emotion recognition technology to recognize the emotion "anxiety." When this text data and emotion information are sent to the server, the server uses a natural language processing engine to analyze the data and extract information such as "right knee pain" and "anxiety." The analysis results are communicated to the medical professional in the form of, "The patient is complaining of right knee pain and is feeling anxious. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "Inflammation of the right knee is suspected. I will prescribe ice and painkillers," and the server re-analyzes this and tells the patient, "There may be inflammation in your right knee. Apply ice and take the medicine."

[1061] Example of a prompt

[1062] "A patient is complaining of pain in their right knee, and I'm feeling anxious. How should I explain this to a medical professional?"

[1063] "Please translate the diagnosis into language that the patient can easily understand. Diagnosis: Inflammation of the right knee; Prescription: Icing and pain medication."

[1064] The above describes the embodiments of the present invention. This embodiment enables effective communication that takes into account not only the patient's physical symptoms but also their emotional state, dramatically improving diagnosis and treatment in medical settings.

[1065] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1066] Step 1:

[1067] The user (patient) enters their symptoms using the terminal's user interface.

[1068] Specific action: The patient inputs by voice, "My right knee has been hurting lately."

[1069] Input: Audio data.

[1070] Output: Audio data.

[1071] Step 2:

[1072] The device sends the input voice data to a speech recognition API, which then converts it to text.

[1073] Specific operation: The speech recognition API converts the voice data "My right knee has been hurting recently" into the text "My right knee has been hurting recently".

[1074] Input: Audio data.

[1075] Output: Text data.

[1076] Step 3:

[1077] The device recognizes emotions from the input voice data.

[1078] Specific operation: The emotion engine recognizes the emotion "anxiety" from the audio data.

[1079] Input: Audio data.

[1080] Output: Emotional information.

[1081] Step 4:

[1082] The device sends text data and sentiment information to the server.

[1083] Specific action: The device sends the text data "My right knee has been hurting lately" and the emotion information "anxiety" to the server.

[1084] Input: Text data and sentiment information.

[1085] Output: Text data and sentiment information sent to the server.

[1086] Step 5:

[1087] The server analyzes the text data and sentiment information it receives.

[1088] Specific actions: The natural language processing engine extracts keywords such as "right knee pain" and "anxiety."

[1089] Input: Text data and sentiment information.

[1090] Output: Analysis results and sentiment information.

[1091] Step 6:

[1092] The server transmits the analysis results and emotional information to the medical professional's terminal for display.

[1093] Specific actions: The analysis results send information to the medical professional's terminal stating, "The patient is complaining of pain in their right knee and is feeling anxious. Please confirm when the pain started and what movements cause the pain."

[1094] Input: Analysis results and sentiment information.

[1095] Output: Analysis results and sentiment information displayed on the medical professional's terminal.

[1096] Step 7:

[1097] Medical professionals input the diagnosis results and treatment plan.

[1098] Specific action: A medical professional enters into the terminal, "Inflammation is suspected in the right knee. I will prescribe ice and pain medication."

[1099] Input: Diagnosis and treatment plan.

[1100] Output: Input diagnostic results and treatment plan.

[1101] Step 8:

[1102] The terminal sends the entered diagnostic results and treatment plan to the server.

[1103] Specific action: The medical professional enters "Inflammation is suspected in the right knee. I will prescribe ice and pain medication" and sends it to the server.

[1104] Input: Diagnosis and treatment plan.

[1105] Output: Diagnostic results and treatment plan sent to the server.

[1106] Step 9:

[1107] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[1108] Specific action: The server converts the diagnosis "Inflammation of the right knee is suspected. We prescribe ice and pain medication" to "There may be inflammation in your right knee. Apply ice and take medication."

[1109] Input: Diagnosis and treatment plan.

[1110] Output: Converted diagnostic results.

[1111] Step 10:

[1112] The server sends the conversion results to the patient's terminal.

[1113] Specific operation: The server sends the converted diagnostic results to the patient's terminal.

[1114] Input: Converted diagnostic results.

[1115] Output: The conversion result sent to the patient's terminal.

[1116] Step 11:

[1117] The patient's device displays or plays back the conversion results and emotional information via audio.

[1118] Specific actions: The patient's device displays the translated message, "You may have inflammation in your right knee. Apply ice and take medicine," or plays it aloud using speech synthesis technology.

[1119] Input: Conversion result and sentiment information.

[1120] Output: The displayed text or the played audio.

[1121] (Application Example 2)

[1122] 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."

[1123] Traditional security systems have struggled to monitor and analyze the psychological state of external visitors and employees in real time. Furthermore, early detection of potential threats is difficult, leading to delays in post-incident response. There has also been a lack of means to analyze emotional information such as employee stress and anxiety, enabling timely and appropriate responses.

[1124] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for recognizing and analyzing emotional information from voice data, means for transmitting and displaying the analysis results on the security guard's terminal, and means for detecting abnormal emotions and issuing warnings. This enables real-time analysis of emotional information of external visitors and employees, early detection of potential threats, and swift and appropriate responses.

[1125] A "user interface for patient symptom input via voice or text" is an input device designed to allow patients to easily input their symptoms as voice or text information.

[1126] "Means for converting input speech to text" refers to a device or software that has the function of converting speech information into corresponding text information using speech recognition technology.

[1127] "Means for sending text data to a server" refers to a communication device or program for sending acquired text information to a designated server via a network.

[1128] "A means of analyzing text data received by a server and converting it into medical terminology" refers to a process in which a program running on the server converts general text data received into specialized medical terminology.

[1129] "Means for transmitting and displaying analysis results on a medical professional's terminal" refers to a device or software that transmits the results of analysis performed on a server to a medical professional's terminal via a network and displays them on that terminal.

[1130] A "user interface for medical professionals to input diagnostic results" refers to a dedicated input device or screen for medical professionals to input diagnostic results and treatment plans.

[1131] "Means for transmitting entered diagnostic results to a server" refers to a device or program that has the function of transmitting diagnostic results entered by a medical professional to a server via a network.

[1132] "Means of converting diagnostic results received by the server into a format that is easy for patients to understand" refers to the process of converting specialized diagnostic results received by the server into everyday language that patients can easily understand.

[1133] "Means for sending and displaying conversion results on the patient's terminal" refers to a device or software that has the function of sending the converted results back to the patient's terminal and displaying them on that terminal.

[1134] "Means for recognizing and analyzing emotional information from collected audio data" refers to a technology or solution for recognizing and analyzing the emotional state of a speaker contained within audio data.

[1135] "Means for transmitting and displaying analysis results including emotional information on a medical professional's terminal" refers to a device or software that transmits and displays analysis results including emotional information on a medical professional's terminal via a network.

[1136] This invention relates to a system for improving communication between patients and healthcare professionals, and in particular to enabling more accurate information transmission by recognizing and analyzing the patient's emotional information. The embodiments for carrying out this invention are as follows.

[1137] System Configuration

[1138] 1. Patient's device:

[1139] It provides a user interface for patients to input their symptoms via voice or text.

[1140] It has the ability to convert speech to text using a speech recognition API (for example, Google Speech-to-Text API).

[1141] To recognize emotional information from speech, incorporate an emotion recognition library (e.g., EmotionRecognizer).

[1142] A communication function that sends input text data and sentiment information to the server.

[1143] 2. Server-side processing:

[1144] A natural language processing engine (e.g., NLPProcessor) is used to analyze the received text data and sentiment information.

[1145] It generates analysis results and converts them into a format that is easy for medical professionals to understand.

[1146] The analysis results, including emotional information, are sent to the terminals of medical professionals.

[1147] 3. Terminals used by medical professionals:

[1148] It has a display interface that allows medical professionals to review analysis results and emotional information.

[1149] It provides a user interface for inputting diagnostic results and treatment plans.

[1150] A communication function that sends the entered diagnostic results to the server.

[1151] 4. Server-side re-analysis:

[1152] The received diagnostic results are reanalyzed and converted into a format that is easy for the patient to understand.

[1153] The conversion results are sent back to the patient's device.

[1154] 5. Patient's display:

[1155] It has a display interface that allows patients to check the conversion results received from the server.

[1156] It has a function that allows instructions to be played back as audio using speech synthesis.

[1157] Examples of specific cases and prompt statements

[1158] For example, consider a scenario where this system is installed in a security guard's smart glasses. When the guard is spoken to by an outside visitor, the audio data is collected and analyzed in real time. If the system detects that the visitor is "slightly panicked," it issues a warning and prompts the guard to take immediate action.

[1159] Also, consider the following example prompts for a generative AI model:

[1160] The system collected audio data and generated the following sentiment and text information:

[1161] Voice: "I'm a little nervous, but I'm okay."

[1162] Emotion: “Tension, anxiety”

[1163] Please send this to the server in the following format:

[1164] {

[1165] "text_input": "I'm a little nervous, but I'm okay",

[1166] "emotion": "tension, anxiety",

[1167] "Analysis": "The visitor appears nervous, but there doesn't seem to be any major problem."

[1168] }

[1169] Thus, the present invention is a system that analyzes voice data and emotional information and provides it to the appropriate user, thereby achieving highly accurate medical support and security management.

[1170] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1171] Step 1:

[1172] The patient enters their symptoms via voice or text. Specifically, when the patient provides voice input, a speech recognition API (e.g., Google Speech-to-Text API) captures the audio and converts it to text. Here, the input is the patient's voice, and the output is the corresponding text information.

[1173] Step 2:

[1174] The terminal sends text data to the server. This process uses the terminal's communication capabilities to send the converted text data and emotional information recognized from the speech to the server. The input is the text and emotional information acquired by the terminal, and the output is this data sent to the server.

[1175] Step 3:

[1176] The server analyzes the text data and sentiment information it receives. The server uses a natural language processing engine (e.g., NLPProcessor) to extract symptoms and important information from the text data, and also analyzes the sentiment information. The input is the text data and sentiment information sent to the server, and the output is the analysis result.

[1177] Step 4:

[1178] The server sends and displays the analysis results on the medical professional's terminal. The analysis results include symptom information and emotion information in text data. Using the server's communication function, this data is sent to the medical professional's terminal, which then displays it. The input is the server's analysis results, and the output is the information displayed on the medical professional's terminal.

[1179] Step 5:

[1180] Medical professionals input the diagnostic results. They input the diagnostic results and treatment plan using a user interface on their terminal. This input is diagnostic information based on the analysis results provided by the medical professionals.

[1181] Step 6:

[1182] The medical professional's terminal sends the entered diagnostic results to the server. The terminal's communication function is used to send the diagnostic results to the server. The input is the diagnostic information entered on the medical professional's terminal, and the output is the data sent to the server.

[1183] Step 7:

[1184] The server re-analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Within the server, complex medical terminology is translated into everyday language, and instructions are summarized concisely. The input is the diagnostic results sent by medical professionals, and the output is text converted into a format easily understood by patients.

[1185] Step 8:

[1186] The server sends and displays the conversion results on the patient's terminal. The conversion results are sent to the patient's terminal using the server's communication function, and the terminal displays them. Audio playback is also performed using speech synthesis technology. The input is the conversion result, and the output is the information displayed on the patient's terminal and the audio playback.

[1187] 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.

[1188] 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.

[1189] 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.

[1190] [Fourth Embodiment]

[1191] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1192] 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.

[1193] 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).

[1194] 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.

[1195] 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.

[1196] 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).

[1197] 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.

[1198] 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.

[1199] 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.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] 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".

[1204] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it is a system that appropriately conveys information entered by the patient to the healthcare professional and provides the results entered by the healthcare professional to the patient in an easy-to-understand manner. This system consists of the following programs and processes.

[1205] System Overview

[1206] 1. Patient's terminal

[1207] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. This text data is sent to the server.

[1208] 2. Server-side processing

[1209] The server receives text data sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms and converts them into a format that is easy for medical professionals to understand. The analysis results are generated in a format using medical terminology and sent to the medical professionals' terminals.

[1210] 3. Terminals on the medical professional's side

[1211] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[1212] 4. Server-side re-analysis

[1213] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[1214] 5. Patient-side display

[1215] The patient's device displays the conversion results sent from the server. These results are displayed not only in text format but can also be played back using speech synthesis. This allows patients to accurately understand the instructions from medical professionals.

[1216] Specific example

[1217] Specifically, the following operations are performed:

[1218] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the data and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then check this information on their device and take appropriate action.

[1219] The above describes the "mode for carrying out the invention" of this invention. This mode dramatically improves communication between patients and medical professionals, enabling accurate diagnosis and appropriate treatment.

[1220] The following describes the processing flow.

[1221] Step 1:

[1222] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[1223] Step 2:

[1224] The device uses a speech recognition API to convert the input speech into text data: "My right knee has been hurting lately."

[1225] Step 3:

[1226] The terminal sends the converted text data to the server.

[1227] Step 4:

[1228] The server analyzes the received text data, "My right knee has been hurting recently," and uses a natural language processing engine to extract keywords related to the patient's symptoms (e.g., "right knee," "painful," "recently").

[1229] Step 5:

[1230] Based on the extracted information, the server generates a message in a format that is easy for medical professionals to understand (e.g., "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain").

[1231] Step 6:

[1232] The server sends the generated message to the medical professional's terminal.

[1233] Step 7:

[1234] The device displays the received message to a medical professional, who then reviews it.

[1235] Step 8:

[1236] The user (medical professional) enters the diagnosis into the terminal. Example: "Inflammation is suspected in the right knee. I prescribe ice packs and pain medication."

[1237] Step 9:

[1238] The terminal sends the entered diagnostic results to the server.

[1239] Step 10:

[1240] The server analyzes the received diagnostic results and uses a natural language processing engine to convert them into a format that is easy for the patient to understand. Example: "You may have inflammation in your right knee. Apply ice and take medication."

[1241] Step 11:

[1242] The server sends the converted message to the patient's terminal.

[1243] Step 12:

[1244] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis.

[1245] The above outlines the specific processing steps involved in each stage.

[1246] (Example 1)

[1247] 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".

[1248] Traditionally, communication between patients and healthcare professionals has been fraught with problems. Patients often struggled to accurately describe their symptoms, and the specialized terminology used by healthcare professionals was often difficult to understand, leading to misunderstandings of diagnoses and treatment plans. This increased the risk of delays in proper diagnosis and treatment, potentially leading to a deterioration of the patient's health.

[1249] 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.

[1250] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for analyzing the received text data using a natural language processing engine, extracting keywords and important information related to the symptoms, and converting them into medical terminology, means for transmitting and displaying the analysis results on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for converting the received diagnostic results into a form that is easy for the patient to understand and replacing complex medical terminology with everyday language, and means for transmitting and displaying and playing the conversion results on the patient's terminal. This enables smooth information exchange between the patient and the medical professional, and allows for prompt and appropriate diagnosis and treatment.

[1251] A "user interface" is a mechanism that provides screens and input methods for users to interact with a system.

[1252] A "speech recognition API" is an application programming interface for converting speech data into text data.

[1253] A "server" is a computer system used to receive and process data over a network.

[1254] A "natural language processing engine" is a software program that analyzes text data and extracts its meaning.

[1255] A "keyword" is a word or phrase that indicates important information in data analysis.

[1256] "Medical terminology" refers to specialized words and expressions used in the medical field.

[1257] A "medical professional" is someone who possesses specialized knowledge in the medical field, such as a doctor or nurse.

[1258] A "diagnosis" is a judgment or conclusion made by a medical professional based on a patient's symptoms and test results.

[1259] "Conversion result" refers to information that shows how the analyzed data was ultimately represented.

[1260] "Speech synthesis" is a technology that converts text data into speech data.

[1261] This invention is a system for improving communication between patients and healthcare professionals, aiming to enable patients to describe their symptoms in detail and for healthcare professionals to communicate diagnostic results accurately and clearly to patients. This system consists of the following components and associated processes.

[1262] 1. Entering patient information

[1263] For user (patient) information input, the terminal provides a user interface that allows symptom input via voice or text. In the case of voice input, the terminal uses a speech recognition API to convert speech to text. For example, the Google Speech-to-Text API is used. The converted text data is sent from the terminal to the server.

[1264] 2. Initial analysis on the server

[1265] The server receives text data sent from the patient and stores it. Next, a natural language processing engine is used to analyze this text data and extract important keywords and information. Python's natural language processing library, such as spaCy, is used. The extracted information is converted into medical terminology in a format easily understood by healthcare professionals.

[1266] 3. Notification and input to medical professionals

[1267] Medical professionals review the analysis results sent from the server on a terminal. The terminal provides a user interface for medical professionals to input diagnostic results and treatment plans. The entered information is transmitted to the server via the electronic medical record system (EMR system).

[1268] 4. Re-analysis and conversion on the server

[1269] The server receives diagnostic results sent from medical professionals and performs a re-analysis. This re-analysis involves replacing medical terminology with everyday language. For example, the Gensim library is used to simplify the text. The converted information is then sent to the patient's terminal.

[1270] 5. Display and confirmation by the patient.

[1271] The patient's device receives the conversion results sent from the server and displays them in text format. Furthermore, it can also play the instructions audibly using speech synthesis functionality (e.g., Amazon Polly or Google Text-to-Speech API).

[1272] Specific example

[1273] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server receives and analyzes the message, and notifies a medical professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take the medication." The patient can then view this on their device and also hear the instructions by voice.

[1274] Example of a prompt

[1275] Below are examples of prompts for a generative AI model:

[1276] "Please describe in detail the processing steps of a system that improves communication between patients and healthcare professionals. Describe the entire process, from patient information input to the re-analysis of the healthcare professional's diagnosis and its subsequent communication to the patient."

[1277] The above describes the "mode for carrying out the invention" of the present invention. This mode enables smooth communication between patients and medical professionals, and allows for prompt and appropriate diagnosis and treatment.

[1278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1279] Step 1:

[1280] The user (patient) inputs their symptoms using the terminal's user interface. In the case of voice input, the patient might say, "My right knee has been hurting lately." This voice data is input to the terminal's speech recognition API and converted into text data. This text data then becomes the input data for subsequent processing.

[1281] Step 2:

[1282] The terminal sends the converted text data to the server via an HTTP request. The server receives this request and temporarily stores the text data.

[1283] Step 3:

[1284] The server analyzes the received text data using a natural language processing engine (for example, Python's spaCy library). Specifically, it extracts keywords such as "right knee" and "painful" from the text data and converts them into a structured data format. This analyzed data becomes the input data for subsequent processing.

[1285] Step 4:

[1286] The server converts the analyzed data into medical terminology. For example, it converts "pain" to "pain" and generates sentences like "I have pain in my right knee." This makes the data easier for medical professionals to understand. This converted data is then sent to the medical professionals' terminals.

[1287] Step 5:

[1288] Medical professionals use the terminal's user interface to review the analysis data sent from the server. Next, they input the diagnosis and treatment plan. For example, they might enter, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication." This input data is then sent back to the server.

[1289] Step 6:

[1290] The server re-analyzes the received diagnostic results and converts them into everyday language that patients can easily understand. Specifically, it converts "inflammation of the right knee is suspected" to "there may be inflammation in your right knee," and further converts "we will prescribe painkillers" to "please take the medicine." The converted data becomes the input data for subsequent processing.

[1291] Step 7:

[1292] The server sends the re-analyzed and converted data to the patient's device. The device displays this data in text format and also plays it back as audio using a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech API). This allows the patient to confirm medical instructions both visually and aurally.

[1293] The above outlines the specific processing steps of this system's program.

[1294] (Application Example 1)

[1295] 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".

[1296] In traditional healthcare systems, communication between patients and healthcare professionals was often inefficient, particularly in verbalizing symptoms and conveying treatment plans. Furthermore, physical distance and time constraints made rapid diagnosis and treatment difficult, resulting in delays in patients receiving appropriate care. Additionally, obtaining necessary products and services for treatment after diagnosis was cumbersome.

[1297] 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.

[1298] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for transmitting the text data to the server, means for the server to analyze the received text data and convert it into medical terminology, means for transmitting and displaying the analysis results on the terminal of a medical professional, means for providing a user interface in which a medical professional inputs diagnostic results, means for transmitting the input diagnostic results to the server, means for the server to convert the received diagnostic results into a format that is easy for the patient to understand, means for transmitting and displaying the conversion results on the patient's terminal, and means for the patient to check and purchase necessary products and services for treatment within a virtual healthcare store. This enables smooth communication between the patient and the medical professional, facilitating rapid diagnosis and communication of treatment plans, and allowing for consistent acquisition of necessary products and services for treatment.

[1299] "Text data" refers to data that represents speech or text input in a digital format.

[1300] "Analysis results" refer to information obtained after it has been processed by the server using natural language processing.

[1301] "Medical terminology" refers to specialized vocabulary and phrases commonly used in the medical field.

[1302] A "user interface" refers to the interactive screens or forms that allow users (patients or healthcare professionals) to interact directly with the system.

[1303] A "server" is a computer system that receives input data, processes it, and sends the analysis results to each terminal.

[1304] A "terminal" is a device used by a patient or medical professional to display analysis results or diagnostic results.

[1305] "Diagnosis results" refer to information about a diagnosis entered by a medical professional.

[1306] A "virtual healthcare store" is a virtual marketplace that provides medical-related products and services online.

[1307] "Input means" refers to the methods or devices by which a user inputs information into a system, either by voice or text.

[1308] "Display means" refers to methods or devices for visually displaying analysis results or diagnostic results on a terminal.

[1309] "Products and services necessary for treatment" refer to medications and medical services that a patient needs based on a diagnosis made by a medical professional.

[1310] This invention is a system for improving communication between patients and healthcare professionals. Specifically, it appropriately conveys information entered by patients to healthcare professionals and provides patients with easily understandable results entered by healthcare professionals. The following shows a specific form for realizing this system.

[1311] System Overview

[1312] 1. Patient's terminal

[1313] Patients can use a user interface to input their symptoms. They can use either voice or text input; the voice input is converted to text using the device's speech recognition API. The converted text data is then sent to the server.

[1314] 2. Server-side processing

[1315] The server receives text data sent from patients and analyzes it using a generative AI model. Using natural language processing, it extracts keywords and important information related to symptoms and generates analysis results in a format using medical terminology. These analysis results are then sent to the terminals of medical professionals.

[1316] 3. Terminals on the medical professional's side

[1317] Medical professionals view the analysis results sent from the server on their terminals and use a user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[1318] 4. Server-side re-analysis

[1319] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. The converted results are then sent to the patient's device.

[1320] 5. Patient-side display

[1321] The patient's device displays the conversion results sent from the server. This allows the patient to accurately understand the instructions from the medical professional and take appropriate action. Furthermore, they can view and purchase necessary products and services within the virtual healthcare store.

[1322] Specific example

[1323] For example, if a patient voice-inputs, "My right knee has been hurting recently," the device converts this to text and sends it to the server. The server analyzes the received data and notifies a healthcare professional, "The patient is complaining of pain in their right knee. Please confirm when the pain started and what movements cause the pain." After the examination, the healthcare professional inputs, "I suspect inflammation in the right knee. I will apply ice and prescribe pain medication," which is then re-analyzed by the server and notified to the patient, "You may have inflammation in your right knee. Apply ice and take medication." The patient can then review this on their device and take appropriate action. During this process, they can also purchase necessary medications and medical equipment from a virtual healthcare store.

[1324] Example of a prompt

[1325] Please analyze the symptoms of the following patient:

[1326] My right knee has been hurting lately.

[1327] Analysis results:

[1328] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1329] Step 1:

[1330] The patient enters their symptoms via voice or text.

[1331] Input: Audio or text describing the patient's symptoms.

[1332] Specific action: The patient uses the terminal's user interface to input voice commands such as, "My right knee has been hurting lately."

[1333] Output: Input audio or text data.

[1334] Step 2:

[1335] Converts the input audio into text.

[1336] Input: Audio data.

[1337] Specific action: The device uses a speech recognition API to convert the speech into text, "My right knee has been hurting lately."

[1338] Output: Text data.

[1339] Step 3:

[1340] Send text data to the server.

[1341] Input: Text data.

[1342] Specific action: The terminal sends the text data "My right knee has been hurting lately" to the server.

[1343] Output: Text data received by the server.

[1344] Step 4:

[1345] The server analyzes the received text data and converts it into medical terminology.

[1346] Input: Received text data.

[1347] Specific operation: The server uses a generated AI model to analyze text data and convert it into medical terminology such as, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain."

[1348] Output: Analysis results converted into medical terminology.

[1349] Step 5:

[1350] The analysis results are sent to the terminals of medical professionals for display.

[1351] Input: Analysis results converted into medical terminology.

[1352] Specific operation: The server sends a message to the medical professional's terminal stating, "The patient is complaining of pain in their right knee. Please note when the pain started and what movements cause the pain," and this message is displayed on the terminal.

[1353] Output: Analysis results displayed on the medical professional's terminal.

[1354] Step 6:

[1355] It uses a user interface where medical professionals input diagnostic results.

[1356] Input: Diagnosis from a medical professional.

[1357] Specific operation: A medical professional uses the terminal's user interface to input a diagnosis such as, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[1358] Output: The entered diagnostic result.

[1359] Step 7:

[1360] The entered diagnostic results are sent to the server.

[1361] Input: Diagnostic result.

[1362] Specific action: A medical professional's terminal sends a diagnosis to the server stating, "Inflammation is suspected in the right knee. Apply ice and prescribe pain medication."

[1363] Output: Diagnostic results received by the server.

[1364] Step 8:

[1365] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[1366] Input: Diagnostic result.

[1367] Specific operation: The server uses a natural language processing engine to convert the diagnostic results into a format that is easy for the patient to understand, such as "You may have inflammation in your right knee. Apply ice and take medication."

[1368] Output: Diagnostic results converted into a format that is easy for the patient to understand.

[1369] Step 9:

[1370] The conversion results are sent to the patient's device and displayed.

[1371] Input: Diagnostic results converted into a format that is easy for the patient to understand.

[1372] Specific operation: The server sends a message to the patient's device saying, "You may have inflammation in your right knee. Apply ice and take medication," and this message is displayed on the device.

[1373] Output: Diagnostic results displayed on the patient's device.

[1374] Step 10:

[1375] Patients can view and purchase necessary products and services for their treatment within a virtual healthcare store.

[1376] Input: Information about a virtual healthcare store.

[1377] Specific operation: Patients use the terminal's virtual healthcare store function to check and purchase necessary medications and medical devices.

[1378] Output: Information about the purchased goods or services.

[1379] 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.

[1380] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate information transmission. This system consists of the following programs and processes.

[1381] System Overview

[1382] 1. Patient's terminal

[1383] The system provides a user interface for patients to input their symptoms. Users (patients) can input via voice or text. The input voice is converted to text using the device's speech recognition API. The device also has a built-in emotion engine that recognizes the patient's emotions from the voice. This text data and emotion information are sent to the server.

[1384] 2. Server-side processing

[1385] The server receives text data and emotional information sent from patients and analyzes it using a natural language processing engine. Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized emotional information. The analysis results are converted into a format that is easy for medical professionals to understand.

[1386] 3. Terminals on the medical professional's side

[1387] Medical professionals can view analysis results and emotional information transmitted from the server on their terminals. This allows them to understand not only the symptoms but also the patient's emotions, leading to more appropriate diagnoses and communication. A user interface is also provided for inputting diagnostic results and treatment plans, and the entered information is transmitted to the server.

[1388] 4. Server-side re-analysis

[1389] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent back to the patient's device.

[1390] 5. Patient-side display

[1391] The patient's device displays the conversion results and emotional information sent from the server. This information is displayed not only in text format but can also be played back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[1392] Specific example

[1393] For example, if a patient voice-inputs "My right knee has been hurting recently," the system recognizes the emotion of "anxiety" from the voice input. The terminal converts this to text and sends the text "My right knee has been hurting recently" along with the emotion information of "anxiety" to the server. The server receives and analyzes the input and notifies the medical professional, "The patient is complaining of right knee pain and is feeling anxious. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "Inflammation of the right knee is suspected. I will prescribe ice and painkillers," which is analyzed by the server and notified to the patient, "There may be inflammation in your right knee. Apply ice and take the medication." The patient can then check this on the terminal and take appropriate action.

[1394] The above describes the "modes for carrying out the invention" of this invention. This mode enables communication that takes into account not only the patient's physical symptoms but also their emotional state, dramatically improving communication in medical settings.

[1395] The following describes the processing flow.

[1396] Step 1:

[1397] The user (patient) uses the device's microphone to input a voice message saying, "My right knee has been hurting lately."

[1398] Step 2:

[1399] The device converts the input voice data into text using a speech recognition API. The text generated is "My right knee has been hurting lately."

[1400] Step 3:

[1401] The device analyzes voice data using an emotion engine to recognize the emotions the patient is feeling. For example, it can recognize the emotion of "anxiety."

[1402] Step 4:

[1403] The device sends the converted text data and recognized emotion information to the server.

[1404] Step 5:

[1405] The server analyzes the received text data and sentiment information. Using a natural language processing engine, it extracts keywords and important information related to symptoms. For example, it extracts keywords such as "right knee," "painful," and "recently."

[1406] Step 6:

[1407] The server generates messages in a format easily understood by medical professionals, based on extracted information and emotional data. For example, it might generate a message such as, "The patient is complaining of pain in their right knee and is feeling anxious. Please note when the pain started and what movements cause it."

[1408] Step 7:

[1409] The server sends the generated message to the medical professional's terminal.

[1410] Step 8:

[1411] The device displays the received message to a medical professional, who then reviews it.

[1412] Step 9:

[1413] The user (medical professional) enters the diagnosis and treatment plan into the terminal. For example, they might enter, "Inflammation is suspected in the right knee. I will prescribe ice packs and pain medication."

[1414] Step 10:

[1415] The terminal sends the entered diagnostic results to the server.

[1416] Step 11:

[1417] The server analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Using a natural language processing engine, it replaces complex medical jargon with everyday language. For example, it might generate a message like, "You may have inflammation in your right knee. Apply ice and take medication."

[1418] Step 12:

[1419] The server sends the converted message to the patient's terminal.

[1420] Step 13:

[1421] The terminal displays received messages to the patient. If necessary, it plays them back using speech synthesis. This allows the user (patient) to accurately understand the instructions from the medical professional.

[1422] The above outlines the specific processing steps involved in each stage.

[1423] (Example 2)

[1424] 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".

[1425] Conventional medical communication systems need to not only accurately understand a patient's symptoms but also consider their emotional information to enable more accurate and effective diagnosis and treatment. However, current systems lack the technology to appropriately recognize and analyze a patient's emotional information, resulting in a decline in the quality of communication and often placing a burden on diagnosis and treatment. This invention aims to solve these problems and significantly improve communication between patients and medical professionals.

[1426] 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.

[1427] In this invention, the server includes means for providing a user interface in which a patient inputs symptoms by voice or text, means for converting the input voice into text, means for recognizing emotions from the input voice data, means for transmitting text data and emotional information to the server, means for analyzing the received text data and emotional information and extracting keywords and important information related to the symptoms, means for transmitting and displaying the analysis results and emotional information on a medical professional's terminal, means for providing a user interface in which a medical professional inputs diagnosis results and treatment plans, means for transmitting the input diagnosis results and treatment plans to the server, means for converting the received diagnosis results into a format that is easy for the patient to understand and transmitting the conversion results to the patient's terminal, and means for displaying or playing the conversion results and emotional information on the patient's terminal. This makes it possible to diagnose and treat patients while considering not only their physical symptoms but also their emotional state, and significantly improves the quality of communication in medical settings.

[1428] A "user interface for patient symptom input via voice or text" refers to an interface that allows patients to input their symptoms via voice or text, and is an input device for interaction between the system and the patient.

[1429] "Means for converting input speech to text" refers to a processing function that uses speech recognition technology to convert voice input data into text data.

[1430] "Means of recognizing emotions from input audio data" refers to a processing function that uses audio analysis technology to extract emotional information from audio data and determine the emotion being expressed.

[1431] "Means for sending text data and sentiment information to a server" refers to communication means for sending input text data and sentiment information to a server via a network.

[1432] "Means for the server to analyze received text data and sentiment information and extract keywords and important information related to symptoms" refers to a processing function in which the server uses natural language processing technology to analyze text data and sentiment information and identify important keywords and information.

[1433] "Means for transmitting and displaying analysis results and emotional information on a medical professional's terminal" refers to a function that transmits the analysis results and emotional information from the server to a medical professional's terminal via the network and displays them.

[1434] "Means of providing a user interface for medical professionals to input diagnostic results and treatment plans" refers to an interface for medical professionals to input diagnostic results and treatment plans, and an input device for interaction between the system and medical professionals.

[1435] "Means for transmitting entered diagnostic results and treatment plans to a server" refers to communication means for transmitting diagnostic results and treatment plans entered by medical professionals to a server via a network.

[1436] "A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand and sends the converted results to the patient's terminal" refers to a function that analyzes the received diagnostic results, converts them into simple language that the patient can understand, and sends the converted results to the patient's terminal.

[1437] "Means for displaying or playing back the conversion results and emotional information on the patient's terminal" refers to a function that allows the patient's terminal to display the conversion results and emotional information sent from the server on a screen, or to play them back as audio using speech synthesis technology.

[1438] This invention is a system for improving communication between patients and healthcare professionals, and in particular, by recognizing and analyzing patients' emotional information, it enables more accurate and effective information transmission. This system is built on a network basis, including patient terminals, a server, and healthcare professional terminals.

[1439] Patient's terminal

[1440] The patient's terminal provides a user interface for the patient to input their symptoms. The patient can input via voice or text. The input voice is converted to text using a speech recognition API (e.g., a speech recognition API). Furthermore, an emotion engine (e.g., emotion recognition technology) built into the terminal is used to recognize the patient's emotions from the voice data. This text data and emotion information are transmitted to a server via the network.

[1441] Server-side processing

[1442] The server receives text data and sentiment information sent from the patient and analyzes it using a natural language processing engine (e.g., a natural language processing engine). Specifically, it extracts keywords and important information related to symptoms, and also analyzes the recognized sentiment information. The analysis results and sentiment information are converted into a format that is easy for medical professionals to understand and sent to the medical professionals' terminals.

[1443] Terminal on the medical professional's side

[1444] The medical professional's terminal displays analysis results and sentiment information sent from the server. The medical professional can use the user interface to input diagnostic results and treatment plans. The entered information is then sent back to the server.

[1445] Server-side re-analysis

[1446] The server re-analyzes the received diagnostic results and converts them into a format that is easy for the patient to understand. Specifically, it replaces complex medical jargon with everyday language and summarizes the instructions concisely. This converted result is then sent to the patient's device.

[1447] Patient-side display

[1448] The patient's device displays the translated results and emotional information sent from the server. This allows the patient to accurately understand the instructions from the medical professional. In addition to displaying in text format, it is also possible to play the information back using speech synthesis technology (e.g., speech synthesis technology).

[1449] Specific example

[1450] For example, if a patient voice-inputs "My right knee has been hurting recently," the terminal converts the voice into text data, "My right knee has been hurting recently," and uses emotion recognition technology to recognize the emotion "anxiety." When this text data and emotion information are sent to the server, the server uses a natural language processing engine to analyze the data and extract information such as "right knee pain" and "anxiety." The analysis results are communicated to the medical professional in the form of, "The patient is complaining of right knee pain and is feeling anxious. Please confirm when the pain started and what movements cause the pain." After the examination, the medical professional inputs, "Inflammation of the right knee is suspected. I will prescribe ice and painkillers," and the server re-analyzes this and tells the patient, "There may be inflammation in your right knee. Apply ice and take the medicine."

[1451] Example of a prompt

[1452] "A patient is complaining of pain in their right knee, and I'm feeling anxious. How should I explain this to a medical professional?"

[1453] "Please translate the diagnosis into language that the patient can easily understand. Diagnosis: Inflammation of the right knee; Prescription: Icing and pain medication."

[1454] The above describes the embodiments of the present invention. This embodiment enables effective communication that takes into account not only the patient's physical symptoms but also their emotional state, dramatically improving diagnosis and treatment in medical settings.

[1455] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1456] Step 1:

[1457] The user (patient) enters their symptoms using the terminal's user interface.

[1458] Specific action: The patient inputs by voice, "My right knee has been hurting lately."

[1459] Input: Audio data.

[1460] Output: Audio data.

[1461] Step 2:

[1462] The device sends the input voice data to a speech recognition API, which then converts it to text.

[1463] Specific operation: The speech recognition API converts the voice data "My right knee has been hurting recently" into the text "My right knee has been hurting recently".

[1464] Input: Audio data.

[1465] Output: Text data.

[1466] Step 3:

[1467] The device recognizes emotions from the input voice data.

[1468] Specific operation: The emotion engine recognizes the emotion "anxiety" from the audio data.

[1469] Input: Audio data.

[1470] Output: Emotional information.

[1471] Step 4:

[1472] The device sends text data and sentiment information to the server.

[1473] Specific action: The device sends the text data "My right knee has been hurting lately" and the emotion information "anxiety" to the server.

[1474] Input: Text data and sentiment information.

[1475] Output: Text data and sentiment information sent to the server.

[1476] Step 5:

[1477] The server analyzes the text data and sentiment information it receives.

[1478] Specific actions: The natural language processing engine extracts keywords such as "right knee pain" and "anxiety."

[1479] Input: Text data and sentiment information.

[1480] Output: Analysis results and sentiment information.

[1481] Step 6:

[1482] The server transmits the analysis results and emotional information to the medical professional's terminal for display.

[1483] Specific actions: The analysis results send information to the medical professional's terminal stating, "The patient is complaining of pain in their right knee and is feeling anxious. Please confirm when the pain started and what movements cause the pain."

[1484] Input: Analysis results and sentiment information.

[1485] Output: Analysis results and sentiment information displayed on the medical professional's terminal.

[1486] Step 7:

[1487] Medical professionals input the diagnosis results and treatment plan.

[1488] Specific action: A medical professional enters into the terminal, "Inflammation is suspected in the right knee. I will prescribe ice and pain medication."

[1489] Input: Diagnosis and treatment plan.

[1490] Output: Input diagnostic results and treatment plan.

[1491] Step 8:

[1492] The terminal sends the entered diagnostic results and treatment plan to the server.

[1493] Specific action: The medical professional enters "Inflammation is suspected in the right knee. I will prescribe ice and pain medication" and sends it to the server.

[1494] Input: Diagnosis and treatment plan.

[1495] Output: Diagnostic results and treatment plan sent to the server.

[1496] Step 9:

[1497] The server converts the received diagnostic results into a format that is easy for the patient to understand.

[1498] Specific action: The server converts the diagnosis "Inflammation of the right knee is suspected. We prescribe ice and pain medication" to "There may be inflammation in your right knee. Apply ice and take medication."

[1499] Input: Diagnosis and treatment plan.

[1500] Output: Converted diagnostic results.

[1501] Step 10:

[1502] The server sends the conversion results to the patient's terminal.

[1503] Specific operation: The server sends the converted diagnostic results to the patient's terminal.

[1504] Input: Converted diagnostic results.

[1505] Output: The conversion result sent to the patient's terminal.

[1506] Step 11:

[1507] The patient's device displays or plays back the conversion results and emotional information via audio.

[1508] Specific actions: The patient's device displays the translated message, "You may have inflammation in your right knee. Apply ice and take medicine," or plays it aloud using speech synthesis technology.

[1509] Input: Conversion result and sentiment information.

[1510] Output: The displayed text or the played audio.

[1511] (Application Example 2)

[1512] 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".

[1513] Traditional security systems have struggled to monitor and analyze the psychological state of external visitors and employees in real time. Furthermore, early detection of potential threats is difficult, leading to delays in post-incident response. There has also been a lack of means to analyze emotional information such as employee stress and anxiety, enabling timely and appropriate responses.

[1514] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for recognizing and analyzing emotional information from voice data, means for transmitting and displaying the analysis results on the security guard's terminal, and means for detecting abnormal emotions and issuing warnings. This enables real-time analysis of emotional information of external visitors and employees, early detection of potential threats, and swift and appropriate responses.

[1515] A "user interface for patient symptom input via voice or text" is an input device designed to allow patients to easily input their symptoms as voice or text information.

[1516] "Means for converting input speech to text" refers to a device or software that has the function of converting speech information into corresponding text information using speech recognition technology.

[1517] "Means for sending text data to a server" refers to a communication device or program for sending acquired text information to a designated server via a network.

[1518] "A means of analyzing text data received by a server and converting it into medical terminology" refers to a process in which a program running on the server converts general text data received into specialized medical terminology.

[1519] "Means for transmitting and displaying analysis results on a medical professional's terminal" refers to a device or software that transmits the results of analysis performed on a server to a medical professional's terminal via a network and displays them on that terminal.

[1520] A "user interface for medical professionals to input diagnostic results" refers to a dedicated input device or screen for medical professionals to input diagnostic results and treatment plans.

[1521] "Means for transmitting entered diagnostic results to a server" refers to a device or program that has the function of transmitting diagnostic results entered by a medical professional to a server via a network.

[1522] "Means of converting diagnostic results received by the server into a format that is easy for patients to understand" refers to the process of converting specialized diagnostic results received by the server into everyday language that patients can easily understand.

[1523] "Means for sending and displaying conversion results on the patient's terminal" refers to a device or software that has the function of sending the converted results back to the patient's terminal and displaying them on that terminal.

[1524] "Means for recognizing and analyzing emotional information from collected audio data" refers to a technology or solution for recognizing and analyzing the emotional state of a speaker contained within audio data.

[1525] "Means for transmitting and displaying analysis results including emotional information on a medical professional's terminal" refers to a device or software that transmits and displays analysis results including emotional information on a medical professional's terminal via a network.

[1526] This invention relates to a system for improving communication between patients and healthcare professionals, and in particular to enabling more accurate information transmission by recognizing and analyzing the patient's emotional information. The embodiments for carrying out this invention are as follows.

[1527] System Configuration

[1528] 1. Patient's device:

[1529] It provides a user interface for patients to input their symptoms via voice or text.

[1530] It has the ability to convert speech to text using a speech recognition API (for example, Google Speech-to-Text API).

[1531] To recognize emotional information from speech, incorporate an emotion recognition library (e.g., EmotionRecognizer).

[1532] A communication function that sends input text data and sentiment information to the server.

[1533] 2. Server-side processing:

[1534] A natural language processing engine (e.g., NLPProcessor) is used to analyze the received text data and sentiment information.

[1535] It generates analysis results and converts them into a format that is easy for medical professionals to understand.

[1536] The analysis results, including emotional information, are sent to the terminals of medical professionals.

[1537] 3. Terminals used by medical professionals:

[1538] It has a display interface that allows medical professionals to review analysis results and emotional information.

[1539] It provides a user interface for inputting diagnostic results and treatment plans.

[1540] A communication function that sends the entered diagnostic results to the server.

[1541] 4. Server-side re-analysis:

[1542] The received diagnostic results are reanalyzed and converted into a format that is easy for the patient to understand.

[1543] The conversion results are sent back to the patient's device.

[1544] 5. Patient's display:

[1545] It has a display interface that allows patients to check the conversion results received from the server.

[1546] It has a function that allows instructions to be played back as audio using speech synthesis.

[1547] Examples of specific cases and prompt statements

[1548] For example, consider a scenario where this system is installed in a security guard's smart glasses. When the guard is spoken to by an outside visitor, the audio data is collected and analyzed in real time. If the system detects that the visitor is "slightly panicked," it issues a warning and prompts the guard to take immediate action.

[1549] Also, consider the following example prompts for a generative AI model:

[1550] The system collected audio data and generated the following sentiment and text information:

[1551] Voice: "I'm a little nervous, but I'm okay."

[1552] Emotion: “Tension, anxiety”

[1553] Please send this to the server in the following format:

[1554] {

[1555] "text_input": "I'm a little nervous, but I'm okay",

[1556] "emotion": "tension, anxiety",

[1557] "Analysis": "The visitor appears nervous, but there doesn't seem to be any major problem."

[1558] }

[1559] Thus, the present invention is a system that analyzes voice data and emotional information and provides it to the appropriate user, thereby achieving highly accurate medical support and security management.

[1560] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1561] Step 1:

[1562] The patient enters their symptoms via voice or text. Specifically, when the patient provides voice input, a speech recognition API (e.g., Google Speech-to-Text API) captures the audio and converts it to text. Here, the input is the patient's voice, and the output is the corresponding text information.

[1563] Step 2:

[1564] The terminal sends text data to the server. This process uses the terminal's communication capabilities to send the converted text data and emotional information recognized from the speech to the server. The input is the text and emotional information acquired by the terminal, and the output is this data sent to the server.

[1565] Step 3:

[1566] The server analyzes the text data and sentiment information it receives. The server uses a natural language processing engine (e.g., NLPProcessor) to extract symptoms and important information from the text data, and also analyzes the sentiment information. The input is the text data and sentiment information sent to the server, and the output is the analysis result.

[1567] Step 4:

[1568] The server sends and displays the analysis results on the medical professional's terminal. The analysis results include symptom information and emotion information in text data. Using the server's communication function, this data is sent to the medical professional's terminal, which then displays it. The input is the server's analysis results, and the output is the information displayed on the medical professional's terminal.

[1569] Step 5:

[1570] Medical professionals input the diagnostic results. They input the diagnostic results and treatment plan using a user interface on their terminal. This input is diagnostic information based on the analysis results provided by the medical professionals.

[1571] Step 6:

[1572] The medical professional's terminal sends the entered diagnostic results to the server. The terminal's communication function is used to send the diagnostic results to the server. The input is the diagnostic information entered on the medical professional's terminal, and the output is the data sent to the server.

[1573] Step 7:

[1574] The server re-analyzes the received diagnostic results and converts them into a format that is easy for patients to understand. Within the server, complex medical terminology is translated into everyday language, and instructions are summarized concisely. The input is the diagnostic results sent by medical professionals, and the output is text converted into a format easily understood by patients.

[1575] Step 8:

[1576] The server sends and displays the conversion results on the patient's terminal. The conversion results are sent to the patient's terminal using the server's communication function, and the terminal displays them. Audio playback is also performed using speech synthesis technology. The input is the conversion result, and the output is the information displayed on the patient's terminal and the audio playback.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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."

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] 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.

[1592] 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.

[1593] 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.

[1594] 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.

[1595] 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.

[1596] 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.

[1597] 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.

[1598] The following is further disclosed regarding the embodiments described above.

[1599] (Claim 1)

[1600] Means for providing a user interface in which patients input symptoms via voice or text,

[1601] A means of converting input audio into text,

[1602] A means of sending text data to a server,

[1603] A means of analyzing text data received by the server and converting it into medical terminology,

[1604] A means of transmitting and displaying the analysis results on a medical professional's terminal,

[1605] A means of providing a user interface for medical professionals to input diagnostic results,

[1606] A means for sending the entered diagnostic results to the server,

[1607] A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand,

[1608] A means of sending and displaying the conversion result on the patient's terminal,

[1609] A system that includes this.

[1610] (Claim 2)

[1611] The system according to claim 1, which converts speech to text using a speech recognition API.

[1612] (Claim 3)

[1613] The system according to claim 1, which analyzes text data using a natural language processing engine and extracts information.

[1614] "Example 1"

[1615] (Claim 1)

[1616] Means for providing a user interface in which patients input symptoms via voice or text,

[1617] A means of converting input audio into text,

[1618] A means of sending text data to a server,

[1619] A means of analyzing text data received by a server using a natural language processing engine, extracting keywords and important information related to symptoms, and converting them into medical terminology,

[1620] A means of transmitting and displaying the analysis results on a medical professional's terminal,

[1621] A means of providing a user interface for medical professionals to input diagnostic results,

[1622] A means for sending the entered diagnostic results to the server,

[1623] A means of converting the diagnostic results received by the server into a format that is easy for patients to understand, and replacing complex medical jargon with everyday language,

[1624] A means for transmitting the conversion result to the patient's terminal and playing it back with display and audio,

[1625] A system that includes this.

[1626] (Claim 2)

[1627] The system according to claim 1, which converts speech to text using a speech recognition API.

[1628] (Claim 3)

[1629] The system according to claim 1, which uses a natural language processing engine to analyze text data, extract information, and convert it into medical terminology.

[1630] "Application Example 1"

[1631] (Claim 1)

[1632] Means for providing a user interface in which patients input symptoms via voice or text,

[1633] A means of converting input audio into text,

[1634] A means of sending text data to a server,

[1635] A means of analyzing text data received by the server and converting it into medical terminology,

[1636] A means of transmitting and displaying the analysis results on a medical professional's terminal,

[1637] A means of providing a user interface for medical professionals to input diagnostic results,

[1638] A means for sending the entered diagnostic results to the server,

[1639] A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand,

[1640] A means of sending and displaying the conversion result on the patient's terminal,

[1641] A means for patients to view and purchase necessary products and services for treatment within a virtual healthcare store,

[1642] A system that includes this.

[1643] (Claim 2)

[1644] The system according to claim 1, which converts speech to text using a speech recognition API.

[1645] (Claim 3)

[1646] The system according to claim 1, which analyzes text data using a generative AI model and extracts information.

[1647] "Example 2 of combining an emotion engine"

[1648] (Claim 1)

[1649] Means for providing a user interface in which patients input symptoms via voice or text,

[1650] A means of converting input audio into text,

[1651] A means of recognizing emotions from input audio data,

[1652] Means for sending text data and sentiment information to a server,

[1653] A means for analyzing text data and emotional information received by the server and extracting keywords and important information related to symptoms,

[1654] A means for transmitting and displaying analysis results and emotional information on a medical professional's terminal,

[1655] A means of providing a user interface in which medical professionals input diagnostic results and treatment plans,

[1656] A means for transmitting the entered diagnostic results and treatment plan to a server,

[1657] A means for the server to convert the received diagnostic results into a format that is easy for the patient to understand, and to send the converted results to the patient's terminal,

[1658] A means for displaying the conversion results and emotional information on the patient's terminal or playing them aloud,

[1659] A system that includes this.

[1660] (Claim 2)

[1661] The system according to claim 1, which converts speech to text using a speech recognition API and obtains emotional information using emotion recognition technology.

[1662] (Claim 3)

[1663] The system according to claim 1, which uses a natural language processing engine to analyze text data and sentiment information and extract keywords and important information related to symptoms.

[1664] "Application example 2 when combining with an emotional engine"

[1665] (Claim 1)

[1666] Means for providing a user interface in which patients input symptoms via voice or text,

[1667] A means of converting input audio into text,

[1668] A means of sending text data to a server,

[1669] A means of analyzing text data received by the server and converting it into medical terminology,

[1670] A means of transmitting and displaying the analysis results on a medical professional's terminal,

[1671] A means of providing a user interface for medical professionals to input diagnostic results,

[1672] A means for sending the entered diagnostic results to the server,

[1673] A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand,

[1674] A means of sending and displaying the conversion result on the patient's terminal,

[1675] A method for recognizing and analyzing emotional information from collected audio data,

[1676] A means of transmitting and displaying analysis results, including emotional information, on a medical professional's terminal,

[1677] A system that includes this.

[1678] (Claim 2)

[1679] The system according to claim 1, which converts speech to text using a speech recognition API.

[1680] (Claim 3)

[1681] The system according to claim 1, which uses a natural language processing engine to analyze text data and sentiment information and extract information. [Explanation of symbols]

[1682] 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. Means for providing a user interface in which patients input symptoms via voice or text, A means of converting input audio into text, A means of sending text data to a server, A means of analyzing text data received by the server and converting it into medical terminology, A means of transmitting and displaying the analysis results on a medical professional's terminal, A means of providing a user interface for medical professionals to input diagnostic results, A means for sending the entered diagnostic results to the server, A means by which the server converts the received diagnostic results into a format that is easy for the patient to understand, A means of sending and displaying the conversion result on the patient's terminal, A system that includes this.

2. The system according to claim 1, which converts speech to text using a speech recognition API.

3. The system according to claim 1, which analyzes text data using a natural language processing engine and extracts information.

Images