system

Abstract

To provide a system for supporting more accurate and efficient diagnosis and treatment by smoothing communication between a patient and a doctor.SOLUTION: The specific processing unit 290 of the data processing device 12 in the system receives the simple description of the symptom and the symptom degree input and transmitted by the user, automatically generates a medical record using a generation API based on the received data, generates a description of the generated medical record in easy-to-understand words or in a character tone for the patient, and transmits the generated medical record and description to the terminal for display.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In medical settings, some patients, especially children and the elderly, may find it difficult to accurately communicate their symptoms to their doctor. Furthermore, patients may have difficulty understanding explanations from doctors that use a lot of technical terminology. This communication barrier can lead to delays in diagnosis and treatment or misunderstandings. The purpose of this invention is to solve these problems, facilitate communication between patients and doctors, and support more accurate and efficient diagnosis and treatment. [Means for solving the problem]

[0005] The present invention provides a system including a means for inputting a simple description of symptoms and the severity of the symptoms, a means for transmitting the input description and severity to a server, a means for automatically generating a medical record using a generation API based on the received data, a means for generating an explanatory text for the generated medical record in easy-to-understand language and a character-like tone for the patient, and a means for transmitting and displaying the generated medical record and explanatory text to a terminal. This system allows patients to more accurately communicate their symptoms to doctors and makes doctor's explanations easier for patients to understand, improving communication in medical settings.

[0006] A "brief symptom description" is a short, easy-to-understand description of the patient's symptoms.

[0007] "Symptom severity" is a numerical or verbal expression of the strength or degree of symptoms felt by the patient.

[0008] "Input means" refers to an interface or device that allows a patient to input a description and severity of symptoms into a terminal.

[0009] "Means for sending to the server" refers to the communication functions and protocols for transferring data from the terminal to the server.

[0010] "Generation API" refers to an application programming interface for automatically generating medical records and descriptions.

[0011] "Means for automatically generating medical records" refers to the function of automatically creating medical records using a generation API based on the description and severity of symptoms entered.

[0012] "Easy-to-understand words and character tone" refers to a tone that uses simple expressions that avoid technical jargon and friendly characters so that patients can easily understand.

[0013] "Means for sending to the terminal and displaying" refers to the function for transferring the generated medical record and explanatory text from the server to the terminal and displaying it so that the patient and doctor can check it. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The proposed system is designed to improve communication between patients and doctors in medical settings. The system includes the following features:

[0036] Enter a brief description of your symptoms and their severity

[0037] The user uses an input form on the terminal to input a brief description of the symptoms and their severity.

[0038] Example: "User types 'My stomach hurts' and selects pain intensity as 8 / 10"

[0039] Sending data to the server

[0040] The terminal transmits the symptom data collected from the user to the server.

[0041] Example: "The device sends the summarized data, 'Symptom: stomachache, Severity: 8 / 10', to the server."

[0042] Generate medical records using the generation API

[0043] The server calls the generation API based on the data received and automatically generates the medical record.

[0044] Example: "The server uses the generation API to generate a medical record stating, 'The patient complains of abdominal pain, and the pain intensity is 8 / 10.'"

[0045] Generating descriptions using the generation API

[0046] The server also uses the generation API to generate explanatory text for patients using easy-to-understand language and a character-like tone of voice.

[0047] Example: "The server generates the description 'Your stomach feels all fuzzy and painful. Does it feel like a little hedgehog is moving around inside you?'"

[0048] Display on the device

[0049] The server sends the generated medical record and explanation to the terminal.

[0050] The terminal displays the received data to the user.

[0051] Example: "The device displays to the user: 'Patient report: Patient complains of abdominal pain, pain intensity 8 / 10' and 'Explanation: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?'"

[0052] Program processing description

[0053] The program is expected to operate as follows:

[0054] 1. Enter symptoms

[0055] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[0056] 2. Data Transmission

[0057] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[0058] 3. Medical record generation

[0059] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record will state that "the patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0060] 4. Description Generation

[0061] The server uses the same generation API to generate patient-friendly descriptions in language and character-like voice, such as "You're feeling a tingly, painful sensation in your stomach. Does it feel like a little hedgehog is moving around inside you?"

[0062] 5.Display

[0063] The server sends the generated chart and explanation to the terminal, which displays them to the user. "Chart: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed on the terminal.

[0064] Specific examples

[0065] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[0066] User input: "My head hurts," pain intensity "7 / 10"

[0067] Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[0068] Generate medical record: "Patient complains of headache, pain intensity 7 / 10"

[0069] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0070] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[0071] This will enable patients to more accurately describe their symptoms and make it easier for them to understand explanations from doctors, leading to more appropriate diagnoses and treatment.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] A user uses a form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user might enter "My stomach hurts" and rate the pain intensity as 8 / 10.

[0075] Step 2:

[0076] The terminal collects data entered by the user, which is organized as "Symptom: stomachache, Severity: 8 / 10."

[0077] Step 3:

[0078] The terminal sends the collected data to the server. Specifically, the organized data is converted into a data structure that can be sent to the server.

[0079] Step 4:

[0080] The server receives the data sent from the device, checks the received data, and verifies its accuracy.

[0081] Step 5:

[0082] Based on the data received by the server, the symptom description and severity data are sent to the generation API, and a request to generate a medical record is sent.

[0083] Step 6:

[0084] The generation API processes the request and automatically generates a medical record based on the input data. Specifically, it generates a medical record with the content, such as, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0085] Step 7:

[0086] The generation API returns the generated medical record to the server, which includes the text data of the medical record.

[0087] Step 8:

[0088] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[0089] Step 9:

[0090] The generation API receives the request and generates a description using language and a character voice that is easy for the patient to understand, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0091] Step 10:

[0092] The generation API returns the generated description to the server, which includes the text data of the description.

[0093] Step 11:

[0094] The server receives the description returned from the generation API and combines the data with the medical records received previously.

[0095] Step 12:

[0096] The server sends the compiled data to the terminal, which includes the generated medical record and explanation.

[0097] Step 13:

[0098] The terminal displays the data received from the server. Specifically, it displays to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0099] The above steps allow users to accurately input their symptoms, generate a medical record in a format that is easy for doctors to understand, and provide explanations that are easy for patients to understand, facilitating smooth communication in the medical field.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] In medical settings, it can be difficult for patients to accurately communicate their symptoms to medical staff, and it can also be difficult for medical staff to explain things to patients in an easy-to-understand manner. This can lead to insufficient communication between patients and medical staff, which can affect the appropriateness of diagnosis and treatment.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes: a means for a user to input a description and severity of symptoms using a medical terminal; a means for transmitting the input description and severity of symptoms in data format to the server; a means for the server to automatically generate a medical record using a generative AI model based on the received data; a means for the server to generate an explanation for the patient using the generative AI model based on the generated medical record; and a means for the server to transmit the generated medical record and explanation to the terminal and for the terminal to display them. This allows patients to accurately input their symptoms and reliably communicate them to medical staff through the generated medical record and explanation. Furthermore, medical staff can provide explanations to patients in an easy-to-understand manner, improving the appropriateness of diagnosis and treatment.

[0105] "User" refers to a person who uses a medical terminal to input their symptoms and their severity.

[0106] "Medical device" refers to an electronic device, such as a smartphone, tablet, or computer, that a user uses to input a description and severity of their symptoms.

[0107] "Symptom description" refers to a verbal description of the physical or mental abnormality or discomfort the user is experiencing.

[0108] "Degree" refers to the strength or severity of symptoms expressed numerically or verbally.

[0109] "Data format" refers to the structured information format (e.g., JSON or XML) used to transmit the symptom description and severity to the server.

[0110] "Server" refers to the central processing unit that receives data sent by users and generates medical records and explanatory text using generative AI models.

[0111] A "generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate medical records and explanatory text based on input data.

[0112] A "medical record" refers to a document that serves as a medical record and is generated based on the symptoms and their severity entered by the user.

[0113] "Explanatory text" refers to a document generated using a generative AI model to explain symptoms in an easy-to-understand manner for patients.

[0114] "Terminal" refers to a medical terminal operated by a user, which displays the products (medical records and explanatory text) sent from the server.

[0115] This invention is a system designed to improve communication between patients and doctors in medical settings. The system consists of a user, a terminal, and a server, and uses a generative AI model to automatically generate medical records and explanations.

[0116] First, the user uses a medical device (smartphone, tablet, PC, etc.) to enter a description of their symptoms and their severity. The user enters detailed symptoms (e.g., "My stomach hurts") into the application's input form and selects the intensity or level of pain (e.g., 8 / 10) using a slider bar or drop-down menu.

[0117] Next, the terminal sends this input data to the server in a data format (e.g., JSON). Specifically, the terminal uses the HTTPS protocol over an Internet connection to send the input data as a POST request to the server's endpoint.

[0118] The server automatically generates a medical record using a generative AI model (e.g., GPT-3) based on the received data. During the generation process, the server sends a prompt to the generative AI model. This prompt is, "Please describe the patient's symptoms and severity in medical record format." Based on this prompt, the generative AI model generates a medical record such as, "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0119] The server also uses the generative AI model to generate easy-to-understand explanations for patients. The prompt is, "Please explain the patient's symptoms in kind words and in a character-like tone." An example of a generated explanation is, "Your stomach feels all tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0120] The server sends the generated medical record and explanation to the terminal. The terminal receives this and displays it as specific information for the user. The displayed information is in the form of "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0121] Specific examples

[0122] For example, if a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process goes through the following steps:

[0123] 1. User input: "I have a headache," pain intensity "7 / 10"

[0124] A user enters "I have a headache" into an application form and sets the pain intensity to 7 using the slider.

[0125] 2. Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[0126] The terminal sends the input data to the server in JSON format.

[0127] 3. Medical record generation

[0128] The server sends a prompt to the generating AI model saying, "Please describe the patient's symptoms and severity in a medical record format," and generates a medical record stating, "The patient complains of a headache, and the pain intensity is 7 / 10."

[0129] 4. Description Generation

[0130] The server sends a prompt to the generative AI model, asking it to "describe the symptoms the patient reported in kind words or in a character-like tone," and generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0131] 5.Display

[0132] The server sends the generated medical record and explanation to the terminal, which displays it on the screen.

[0133] In this way, patients can accurately record their symptoms and communicate them to medical staff in an understandable manner, improving the quality of diagnosis and treatment.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: User symptom input

[0136] The user uses a medical device to input symptoms and their severity. The user enters symptoms such as "my stomach hurts" into the application's input form and sets the pain intensity to, for example, 8 / 10 using a slider bar or drop-down menu. The input data is stored in the device in text format.

[0137] Input: User-entered symptoms and their severity (e.g., "My stomach hurts" with severity "8 / 10").

[0138] Output: Temporarily saved as structured data (e.g. JSON).

[0139] Step 2: Send data

[0140] The device sends the entered data to the server. The device sends the data as a POST request to the server endpoint using the HTTPS protocol via an internet connection.

[0141] Input: JSON data containing symptoms and their severity entered by the user into the device (e.g., "Symptom: stomachache, Severity: 8 / 10").

[0142] Output: JSON formatted data sent to the server.

[0143] Step 3: Create a medical record

[0144] Based on the data received by the server, a medical record is automatically generated using a generative AI model. The server sends a prompt to the generative AI model, saying, "Please describe the patient's symptoms and severity in medical record format," and retrieves the generated medical record.

[0145] Input: Symptom and severity data received by the server (e.g., "Symptom: stomachache, Severity: 8 / 10").

[0146] Data processing: The generative AI model is invoked using a prompt ("Please describe the patient's symptoms and severity in medical record format").

[0147] Output: An automatically generated medical record (e.g., "The patient complains of abdominal pain, pain intensity is 8 / 10").

[0148] Step 4: Description generation

[0149] The server uses the same generative AI model to generate a patient-oriented explanation. The server sends a prompt, "Please explain the patient's symptoms in a gentle and character-like tone," and retrieves the generated explanation.

[0150] Input: The prompt and medical record contents to be sent to the generative AI model (e.g., "Symptoms: stomachache, Severity: 8 / 10").

[0151] Data processing: The generative AI model is invoked using a prompt ("Please explain the symptoms the patient reported in kind words and in a character-like voice").

[0152] Output: An automatically generated description (e.g. "Your stomach feels all fuzzy and painful. Does it feel like there's a little hedgehog thrashing around inside you?").

[0153] Step 5: View the medical record and explanation

[0154] The server sends the generated chart and explanation to the terminal, which receives it and displays it to the user. The terminal application analyzes the received data and displays it on the screen.

[0155] Input: Medical record and description data sent from the server (e.g., "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10"; "Description: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?").

[0156] Output: Information displayed on the device screen.

[0157] In this way, users can easily record their own symptoms, and the server can provide automatically generated medical records and explanations based on this information, facilitating smooth communication between medical staff and patients.

[0158] (Application example 1)

[0159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0160] In today's food delivery services, it is difficult for users to accurately communicate their preferences and allergy information. Existing systems limit the ways in which users can specify their requests in detail, which can lead to ordering errors or inappropriate menu suggestions. Furthermore, explanations to users are often difficult to understand, making it difficult for them to understand complex information. To solve this problem, a system is needed that allows users to easily input their preferences and allergy information, automatically suggests optimal menus based on that information, and provides easy-to-understand explanations.

[0161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0162] In this invention, the server includes means for inputting a simple explanation of preference information and allergy information, means for transmitting the input preference information and allergy information to the server, means for automatically generating a suggested menu using a generation API based on the received data, means for generating an explanation of the generated suggested menu in easy-to-understand language for the user, and means for transmitting the generated suggested menu and explanation to the terminal and displaying it. This enables users to receive the optimal menu tailored to their preferences and allergies, reduces ordering errors, and provides easy-to-understand explanations.

[0163] The "brief description of preference information" is information about the types of food and seasonings that the user likes.

[0164] "Allergy information" is information about ingredients or substances to which the user is allergic.

[0165] "Input means" refers to a device or software that provides an interface for users to input preference information and allergy information.

[0166] The "means for automatically generating a suggested menu using a generation API" is a method that uses an application programming interface to automatically generate an optimal menu based on the user's preference information and allergy information.

[0167] The "means for generating explanatory text in easy-to-understand language for users" is a method for explaining information about the generated suggested menu in simple language that is easy for users to understand.

[0168] The "means for transmitting to the terminal and displaying" is a method for transmitting the generated suggested menu and explanatory text to the user's terminal and displaying them.

[0169] The embodiments of the present invention will be described below.

[0170] The system for realizing the invention provides a means for users to input a simple description of their preferences and allergy information. This means utilizes a smartphone application. The user inputs their preferences and allergy information using the application. For example, they can input information such as "I like spicy food" or "I'm allergic to nuts."

[0171] The smartphone sends the input preference and allergy information to the server. The server uses a generation API based on the received data to automatically generate a suggested menu that suits the user's preferences and allergies. The generated suggested menu is provided using a generative AI model.

[0172] Next, the server generates an easy-to-understand explanation for the user based on the generated suggested menu. For example, for the menu item "Spicy Tandoori Chicken, Nut-Free," it generates an explanation such as "It's spicy, but it's nut-free, so you can eat it with peace of mind." This explanation is also generated using the generation API.

[0173] Finally, the server sends the generated menu suggestions and explanations to the smartphone, which then displays them to the user, allowing the user to easily check the most suitable menu based on their preferences and allergy information and place their order with confidence.

[0174] The hardware used includes smartphones and servers, and the software used for generation includes a generation API, such as OpenAI's Generative Model API.

[0175] For example, if a user enters "I like spicy food" and specifies "I have a nut allergy," the process will proceed as follows:

[0176] User input: "I like spicy food", allergy information: "nuts"

[0177] Send to device: "Preferences: spicy, Allergies: nuts"

[0178] Generate suggested menu: "Spicy tandoori chicken, nut-free"

[0179] Description generation: "It's spicy, but nut-free so you can eat it with peace of mind."

[0180] Display: "Menu: Spicy Tandoori Chicken, Nut-Free" and "Description: It's spicy, but it's nut-free so you can eat it with peace of mind" will be displayed on your smartphone.

[0181] In this way, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information. This process is realized by inputting a prompt message to the generation API, such as, "If the user likes spicy food and has a nut allergy, please generate the optimal menu suggestion and corresponding explanation."

[0182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0183] Step 1:

[0184] The user enters preference information and allergy information using a smartphone application. Specifically, the user enters "I like spicy food" and selects "I'm allergic to nuts" in the application's input form.

[0185] Input: User preference information (e.g., I like spicy food), allergy information (e.g., I'm allergic to nuts)

[0186] Output: The input information is saved in the application

[0187] Step 2:

[0188] The smartphone sends the user's preference and allergy information to the server, which then formats the data appropriately and sends it to the server.

[0189] Input: Saved input information (preference information, allergy information)

[0190] Output: Formatted data is sent to the server

[0191] Step 3:

[0192] The server calls the generation API based on the received data and automatically generates a menu suggestion. Here, a specific generation AI model is used to analyze the user's input data and generate the optimal menu that meets the conditions.

[0193] Input: Preference and allergy information received by the server

[0194] Output: Generated menu suggestions (e.g. spicy tandoori chicken, nut-free)

[0195] Step 4:

[0196] The server generates a user-friendly description of the proposed menu based on the generated menu suggestion. It uses the generation API again to create a simple and friendly description of the proposed menu.

[0197] Input: Generated suggestion menu

[0198] Output: Generated description (e.g., "It's spicy, but it's nut-free so you can eat it with peace of mind")

[0199] Step 5:

[0200] The server sends the generated suggestion menu and explanation to the smartphone, which then prepares to display this information to the user.

[0201] Input: Generated suggestion menu and description

[0202] Output: Suggested menu and explanations are sent to your smartphone.

[0203] Step 6:

[0204] The smartphone displays the received suggested menu and description to the user, who can then check the suggested menu and description on the screen and decide whether to order.

[0205] Input: Received suggestion menu and description

[0206] Output: A suggestion menu and explanations are displayed on the smartphone screen.

[0207] Through the above steps, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information.

[0208] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0209] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The system includes the following features:

[0210] Enter a brief description of your symptoms and their severity

[0211] A user uses an input form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user enters "I have a stomachache" and sets the pain intensity as 8 / 10.

[0212] Sending data to the server

[0213] The device sends the data collected from the user to the server, which includes information organized in the format "Symptom: stomachache, Severity: 8 / 10."

[0214] Generate medical records using the generation API

[0215] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record includes the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0216] Generating descriptions using the generation API

[0217] The server also uses the generation API to generate explanations in patient-friendly language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0218] Emotion Recognition Using Emotion Engine

[0219] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize the user's emotions. For example, the emotion engine determines that the user is feeling stressed while typing.

[0220] Emotion data sent to server

[0221] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[0222] Adjusting the tone and content of your descriptions

[0223] Based on the emotion data received by the server, the server sends a request to the generation API to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates a gentler explanation.

[0224] Display on the device

[0225] The server sends the compiled data to the device, which includes the generated medical record and an explanation adjusted based on the user's emotions.

[0226] The device displays this information to the user, specifically, "Medical record: Patient complains of stomach pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0227] Specific explanation of program processing

[0228] The program is expected to operate as follows:

[0229] 1. Enter symptoms

[0230] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[0231] 2. Data Transmission

[0232] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[0233] 3. Medical record generation

[0234] Based on the data received by the server, the generation API is called and a medical record is automatically generated. For example, it might state, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0235] 4. Description Generation

[0236] The server uses the same generation API to generate patient-friendly descriptions in a character-like voice, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside you?"

[0237] 5. Emotion recognition

[0238] The device's emotion engine recognizes the user's emotions in real time. For example, the emotion engine recognizes when the user is feeling stressed.

[0239] 6. Emotional Data Transmission

[0240] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[0241] 7. Adjustments to the description

[0242] The server sends a request to the generation API based on the emotion data and adjusts the tone and content of the explanation. For example, if the user is feeling stressed, the explanation will be generated in a gentler tone.

[0243] 8. Display

[0244] The server sends the compiled data to the terminal, which displays it to the user. The medical record reads, "Patient complains of stomach pain, pain intensity 8 / 10," along with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0245] Specific examples

[0246] Symptom input: The user enters "I have a headache" and sets the pain intensity as 7 / 10.

[0247] Generate medical record: "Patient complains of headache, pain intensity 7 / 10"

[0248] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0249] Emotion recognition: The emotion engine recognizes when a user is nervous.

[0250] Adjust the instructions: The user is nervous, so adjust the instructions to make them more relaxed.

[0251] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[0252] In this way, this system, which combines an emotion engine, allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides easy-to-understand explanations that correspond to the patient's emotional state, further improving communication in medical settings.

[0253] The processing flow will be explained below.

[0254] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The specific processing flow of this system is described below.

[0255] Step 1:

[0256] The user uses the input form on the medical device to briefly describe their symptoms and select the severity of the symptoms. For example, the user enters "I have a stomachache" and sets the pain intensity as 8 / 10.

[0257] Step 2:

[0258] The device sends the collected symptom data to the server, which organizes the data in the format "Symptom: stomachache, Severity: 8 / 10."

[0259] Step 3:

[0260] The server receives the data sent from the device, verifies its accuracy, and then calls the generation API to automatically generate the medical record.

[0261] Step 4:

[0262] The generation API generates a medical record based on the input data and sends it back to the server. The medical record contains the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0263] Step 5:

[0264] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[0265] Step 6:

[0266] The API generates a description using words and a character tone that the patient can easily understand, and sends it back to the server. For example, a description such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0267] Step 7:

[0268] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[0269] Step 8:

[0270] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[0271] Step 9:

[0272] The server sends a request to the generation API to adjust the tone and content of the generated description based on the received emotional data. For example, if the user is feeling stressed, the description will be generated in a gentler tone.

[0273] Step 10:

[0274] The generation API generates the adjusted description and sends it back to the server.

[0275] Step 11:

[0276] The server compiles the adjusted explanation and the previously generated medical record and sends it to the terminal.

[0277] Step 12:

[0278] The terminal displays the data received from the server to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0279] Specific examples

[0280] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[0281] Step 1: User types "I have a headache" and sets pain intensity to 7 / 10.

[0282] Step 2: The device sends the organized data, "Symptom: headache, Severity: 7 / 10", to the server.

[0283] Step 3: The server receives the data and sends it to the generation API.

[0284] Step 4: The generation API generates a medical record stating that "the patient complains of a headache and the pain intensity is 7 / 10" and sends it back to the server.

[0285] Step 5: The server receives the medical record and sends a request to the generation API to generate a description.

[0286] Step 6: The generation API generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?" and sends it back to the server.

[0287] Step 7: The emotion engine recognizes the user's tension.

[0288] Step 8: Send the emotion data "user is nervous" to the server.

[0289] Step 9: The server requests the generation API to generate a description of the relaxing content.

[0290] Step 10: The generation API generates the adjusted description and sends it back to the server.

[0291] Step 11: The server sends the adjusted explanation and medical record together to the terminal.

[0292] Step 12: The terminal displays "Chart: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Do I feel like there are ghosts popping in my head?"

[0293] In this way, this system allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides explanations that reflect the patient's emotional state, facilitating smooth communication in medical settings.

[0294] Example 2

[0295] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0296] In modern medical settings, it is often pointed out that communication between patients and doctors is not smooth. In particular, it is often difficult for patients to accurately communicate their symptoms, and the patient's emotional state is often not taken into consideration. As a result, doctors are unable to make appropriate diagnoses or provide appropriate treatment, leading to a decline in patient satisfaction.

[0297] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a brief description of symptoms and the severity of the symptoms using an input form; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generative AI model based on the received data; means for generating an explanation for the generated medical record using a generation API in easy-to-understand words and a character's tone of voice for the patient; means for recognizing the user's emotions in real time using an emotion engine built into the terminal; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation using the generative AI model based on the emotion data; and means for transmitting the generated medical record and the adjusted explanation to the terminal and displaying them. This not only allows patients to accurately input their symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides easy-to-understand explanations that correspond to the patient's emotional state, thereby improving communication in medical settings.

[0298] The "input form" is an interface that allows the user to input a description and severity of the symptoms.

[0299] The "server" is a computer system that receives data entered by the user, generates medical records and explanatory text using a generative AI model, and sends them to the terminal.

[0300] A "generative AI model" is an artificial intelligence model that automatically generates medical records and explanatory text based on the data it receives.

[0301] A medical record is a document that organizes information such as the symptoms a patient complains of and their severity, and is used by doctors to make diagnoses.

[0302] A "generation API" is a program interface for sending data to a generative AI model and generating medical records, explanatory text, etc.

[0303] The "explanation" is a sentence that explains the contents of the generated medical record to the patient in an easy-to-understand manner.

[0304] The "emotion engine" is a system that recognizes emotions in real time from physiological data such as a user's facial expressions, voice, and heart rate.

[0305] "Tone" refers to the emotional expression and tone of the content of an explanation or other text.

[0306] A "terminal" is a device that allows a user to input data and display generated charts and explanations.

[0307] "Emotion data" is information about the user's emotional state as recognized by the emotion engine.

[0308] This invention is a system designed to improve communication between patients and doctors in medical settings. The system inputs a user's symptoms, automatically generates medical records and explanations using a generative AI model, and also includes the ability to recognize and respond to the user's emotions in real time.

[0309] Hardware and software used

[0310] Hardware:

[0311] Terminal: A device (e.g., personal computer, tablet, smartphone, etc.) used to enter user data and display the generated chart and narrative.

[0312] Server: A computer system that processes and calculates the received data and generates medical records and explanatory text using a generative AI model.

[0313] software:

[0314] Generative AI model: For example, OpenAI's GPT-3 is used to analyze data on the server and generate medical records and explanatory text.

[0315] Generative API: A program interface that sends input data to a generative AI model and receives the generated medical records and descriptions.

[0316] Emotion engine: Software that analyzes physiological data such as a user's facial expressions, voice, and heart rate in real time to recognize emotions (e.g., Emotion Recognition API).

[0317] Specific Embodiments of the System

[0318] 1. Symptom input:

[0319] The user inputs their symptoms using the device. For example, the user might input "my stomach hurts" and rate the pain intensity as 8 / 10. This data is then used as an input form on the device using a JavaScript framework such as React or Vue.js.

[0320] 2. Data transmission:

[0321] The device sends the entered symptom and severity data to the server. The data is organized in JSON format and sent in a format such as {"Symptoms": "Stomachache", "Severity": 8}. This process uses HTTP request libraries such as fetch and axios.

[0322] 3. Medical record generation:

[0323] The server analyzes the received data and calls the generative AI model to automatically generate a medical record. The generated medical record will state that "the patient complains of stomach pain, and the pain intensity is 8 / 10." The data is sent using the generation API, and the generated medical record is received.

[0324] 4. Description generation:

[0325] The server uses the same generative AI model to generate explanatory text in patient-friendly language and a character-like tone, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside you?"

[0326] 5. Emotion recognition:

[0327] The device's built-in emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize the user's emotional state. For example, the emotion engine may determine that the user is feeling stressed while typing.

[0328] 6. Emotional Data Transmission:

[0329] The device organizes the recognized emotion data and sends it to the server. The data sent includes information that the user is feeling stressed. The emotion data is also sent in JSON format.

[0330] 7. Description adjustments:

[0331] Based on the emotion data received, the server sends a request to the generation API to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the API will generate a gentler explanation.

[0332] 8. Display:

[0333] The server sends the generated medical record and the adjusted explanation to the terminal, and the terminal displays this information to the user.Specific examples of the information provided include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0334] Specific examples

[0335] Symptom entry example

[0336] A user types in "I have a headache" and sets the pain intensity to 7 / 10.

[0337] Example of medical record generation

[0338] "The patient complains of a headache and the pain intensity is 7 / 10."

[0339] Example of description generation

[0340] "My head is throbbing. Does it feel like ghosts are snapping around in my head?"

[0341] Emotion Recognition Example

[0342] The emotion engine recognizes that the user is nervous.

[0343] Example of adjusting the description

[0344] The user is nervous, so adjust the instructions to make them more relaxed.

[0345] Display example

[0346] The device displays "Medical record: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0347] In this way, this system not only accurately inputs the user's symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides explanations that correspond to the user's emotional state, thereby improving communication in the medical field.

[0348] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0349] Step 1:

[0350] The user accesses the input form on the medical device and enters their symptoms. For example, the user enters "my stomach hurts" and sets the pain intensity to 8 / 10. The input data is saved in text format on the device. This process uses a user interface (e.g., React or Vue.js).

[0351] Input: The user enters the text "My stomach hurts" and sets the pain level to 8.

[0352] Output: JSON data: {"Symptom": "Stomachache", "Pain level": 8}.

[0353] Action: A user accesses a form, enters "My stomach hurts" into the form field, and uses the slider to set the pain intensity to 8.

[0354] Step 2:

[0355] The device sends the user input data to the server using an HTTP POST request, with the data sent in JSON format. Specifically, an HTTP library such as fetch or axios is used.

[0356] Input: JSON data entered by the user: {"Symptom": "Stomachache", "Pain level": 8}

[0357] Output: The data sent to the server.

[0358] Specific operation: The device uses fetch to create an HTTP POST request and send data to the server.

[0359] Step 3:

[0360] The server analyzes the received data and sends it as prompts to a generative AI model, which is used to generate a medical record. The generative AI model uses, for example, GPT-3.

[0361] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[0362] Output: Text data from the medical record: "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0363] Specific operation: The server executes a script written in Python, uses the requests library to send a prompt to the generation API, and saves the returned text as a medical record.

[0364] Step 4:

[0365] The server uses the same generative AI model to generate a prompt, which includes the symptom and severity information entered by the user.

[0366] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[0367] Output: Description: "Your stomach feels all tingly and painful. It feels like there's a little hedgehog thrashing around inside you."

[0368] Specific operation: The server calls the generation API again, sends the input data as a prompt, and saves the returned explanation.

[0369] Step 5:

[0370] The device's emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[0371] Input: Real-time video and audio data from the user.

[0372] Output: Emotion data "feeling stressed."

[0373] What it does: The device collects data using the user's webcam and microphone, and analyzes emotions using the Emotion Recognition API.

[0374] Step 6:

[0375] The device organizes the recognized emotion data and sends it to the server. The data is sent in JSON format, for example, {"emotion": "stress"}.

[0376] Input: Emotional data of "feeling stressed."

[0377] Output: JSON of emotion data sent to the server.

[0378] Specific operation: The device uses fetch to create an HTTP POST request and send emotion data to the server.

[0379] Step 7:

[0380] The server sends a request to the generative AI model based on the emotional data to adjust the tone and content of the explanation. Specifically, if the user is feeling stressed, it will generate a gentler explanation.

[0381] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8} and {"Emotion": "Stress"}.

[0382] Output: A gentle description: "Your stomach feels all tingly and painful. Does it feel like there's a little hedgehog thrashing around inside you?"

[0383] Specific operation: The server generates a prompt including emotion data, sends a request to the generation API, and saves the adjusted explanation that is returned.

[0384] Step 8:

[0385] The server sends the generated medical record and the adjusted explanation to the terminal, which displays them to the user. The medical record and explanation are formatted in HTML format and displayed in the user interface.

[0386] Input: Text data: "The patient complains of stomach pain, pain intensity is 8 / 10" and "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0387] Output: Medical record and explanation displayed on the terminal screen.

[0388] Specific operation: The terminal formats the data received from the server in HTML format and displays it on the screen. Specifically, the medical record displayed is, "The patient complains of stomach pain, and the pain intensity is 8 / 10," with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0389] (Application example 2)

[0390] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0391] Conventional food delivery services have had difficulty providing meal menus that correspond to the user's physical and emotional state. This has led to problems such as not being able to suggest appropriate meals when the user is feeling unwell, or not being able to provide services that are sensitive to the user's emotions. In particular, there is a need for services that suggest optimal meals and provide consideration to ease the user's emotions when the user is feeling unwell or stressed.

[0392] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a brief description of symptoms and the severity of the symptoms; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generation API based on the received data; means for generating an explanation of the generated medical record for the user in easy-to-understand words or a character's tone of voice; means having an emotion engine that recognizes the user's emotions in real time; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation based on the emotion data received by the server; and means for transmitting the generated medical record and the explanation adjusted based on the emotion data to the terminal and displaying it. This makes it possible to propose a personalized meal menu based on the user's physical condition and emotions, and to provide a service that takes emotions into consideration.

[0393] "Brief explanation of symptoms" is information in which the user briefly describes their own physical condition or illness.

[0394] "Symptom severity" is information that indicates the strength or degree of the symptoms felt by the user using a numerical value or a scale.

[0395] "Generation API" means an application programming interface for automatically generating information based on input data.

[0396] A "medical record" is a detailed record of a patient's or user's physical condition and symptoms, and is a document containing information useful for providing medical care and services.

[0397] "Character tone" refers to the way a character speaks and expresses themselves, with the aim of conveying information in a user-friendly and engaging format.

[0398] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and other physiological data to recognize their emotional state in real time.

[0399] "Emotion data" is information that indicates the emotional state of the user recognized by the emotion engine.

[0400] "Means to adjust the tone and content of descriptions" refers to a function that changes the way information is expressed and worded based on emotional data.

[0401] A "terminal" is a device that allows a user to use the system and is capable of inputting and displaying data.

[0402] This invention provides a system for suggesting personalized meal menus and providing emotionally sensitive service in a food delivery service. The system includes the following main means.

[0403] 1. How to enter a brief description of your symptoms and their severity:

[0404] It is a means for users to briefly describe their physical condition or discomfort and input numerical values ​​to indicate the strength and degree of the condition. For example, a user can input a symptom such as "my stomach hurts" and the degree of the pain.

[0405] 2. Means of data transmission:

[0406] This is a means to send the entered symptom description and severity to the server. In this example, the information entered by the user is sent to the server in the format "Stomachache, severity: 8 / 10".

[0407] 3. Automatic generation of medical records using the generation API:

[0408] The server calls a generation API based on the received data and automatically generates a medical record. This medical record contains information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." A possible generation API would be the "OpenAI API" using the "GPT-4" model.

[0409] 4. How to generate a description using the generation API:

[0410] The server uses the generation API to generate explanatory text for patients in easy-to-understand language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0411] 5. Emotion recognition using emotion engine:

[0412] The device is equipped with an emotion engine that analyzes physiological data such as the user's facial expressions and voice in real time to recognize the user's emotions. Possible software for emotion recognition includes "OpenFace" and "IBM Watson Emotion Analysis."

[0413] 6. Means of sending emotional data:

[0414] This is a means for transmitting the recognized emotion data to the server. The transmitted data includes, for example, information that "the user is feeling stressed."

[0415] 7. Adjust the tone and content of your description:

[0416] The server sends a request to the generation API based on the received emotional data to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates an explanation in a gentler tone.

[0417] 8. Display of generated medical records and explanations:

[0418] This is a means of sending and displaying a medical record generated by the server and an explanation adjusted based on emotion data to the terminal. Examples of displayed content include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0419] Examples:

[0420] When a user enters the symptom "stomach ache" and rates the pain intensity as 8 / 10 through a food delivery application, this information is sent to the server. The server then uses a generation API to automatically generate a medical record and suggests a meal menu suitable for the user. If the emotion engine recognizes that the user is feeling stressed, it adjusts the tone of the explanation to a gentler one and displays it to the user along with a relaxing menu.

[0421] Example prompt sentence:

[0422] "Please suggest a meal plan for a user who is experiencing stomach pain. The pain level is 8 / 10 and the user is currently feeling stressed. Please suggest a meal that is easy to digest and explain it to them in a gentle tone."

[0423] Such a system would enable the provision of personalized meal menus and appropriate services according to the user's physical condition and emotions.

[0424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0425] Step 1:

[0426] A user launches a food delivery application and inputs information about their health condition and emotions. Specifically, they input their physical condition and symptoms (e.g., "I have a stomachache") and their severity (on a scale of 1 to 10). This input data is prepared as transmission data in the format "Symptom: stomachache, Severity: 8 / 10."

[0427] Step 2:

[0428] The device sends the data entered by the user to the server. The input data includes information on symptoms and symptom severity, and is received as "Symptoms: stomachache, Severity: 8 / 10" when sent to the server. This data is stored on the server for subsequent processing.

[0429] Step 3:

[0430] The server calls a generation API based on the received data and automatically generates a medical record. At this stage, a generative AI model (for example, an API using GPT-4) is called and generates medical record information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." The generated medical record is saved for use in the next step.

[0431] Step 4:

[0432] The server uses the same generation API to generate explanatory text for the user in easy-to-understand language and a character-like tone. The input data for this is composed of the generated medical record information and existing templates, and an explanatory text such as "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?" is generated. This explanatory text is also used in subsequent processing.

[0433] Step 5:

[0434] The device analyzes physiological data such as the user's facial expressions and voice in real time and recognizes the user's emotions using an emotion engine. For example, an emotion engine (such as OpenFace or IBM Watson Emotion Analysis) can be used to determine whether the user is feeling stressed while performing input operations. This emotion data is collected as "the user is feeling stressed" and sent to the server.

[0435] Step 6:

[0436] The server adjusts the tone and content of the description based on the recognized emotion data. Here, the emotion data is used as input and processing is performed to change the tone of the existing description. Specifically, the generative AI model is given a prompt such as "Generate a gentler description for users who are feeling stressed," and a description with an adjusted tone is obtained.

[0437] Step 7:

[0438] The server sends the generated medical record along with the adjusted explanation to the terminal. This information is sent in the form of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0439] Step 8:

[0440] The terminal displays the medical record sent from the server and the adjusted explanation to the user. On the terminal screen, "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed, and the user confirms them.

[0441] Step 9:

[0442] The user can then review the suggested meal menu based on the displayed content and select the most suitable option, thereby providing a personalized meal menu that is tailored to the user's physical condition and emotions.

[0443] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0444] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0445] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0446] [Second embodiment]

[0447] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0448] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0449] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0450] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0451] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0453] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0454] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0455] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0456] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0457] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0458] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0459] The proposed system is designed to improve communication between patients and doctors in medical settings. The system includes the following features:

[0460] Enter a brief description of your symptoms and their severity

[0461] The user uses an input form on the terminal to input a brief description of the symptoms and their severity.

[0462] Example: "User types 'My stomach hurts' and selects pain intensity as 8 / 10"

[0463] Sending data to the server

[0464] The terminal transmits the symptom data collected from the user to the server.

[0465] Example: "The device sends the summarized data, 'Symptom: stomachache, Severity: 8 / 10', to the server."

[0466] Generate medical records using the generation API

[0467] The server calls the generation API based on the data received and automatically generates the medical record.

[0468] Example: "The server uses the generation API to generate a medical record stating, 'The patient complains of abdominal pain, and the pain intensity is 8 / 10.'"

[0469] Generating descriptions using the generation API

[0470] The server also uses the generation API to generate explanatory text for patients using easy-to-understand language and a character-like tone of voice.

[0471] Example: "The server generates the description 'Your stomach feels all fuzzy and painful. Does it feel like a little hedgehog is moving around inside you?'"

[0472] Display on the device

[0473] The server sends the generated medical record and explanation to the terminal.

[0474] The terminal displays the received data to the user.

[0475] Example: "The device displays to the user: 'Patient report: Patient complains of abdominal pain, pain intensity 8 / 10' and 'Explanation: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?'"

[0476] Program processing description

[0477] The program is expected to operate as follows:

[0478] 1. Enter symptoms

[0479] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[0480] 2. Data Transmission

[0481] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[0482] 3. Medical record generation

[0483] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record will state that "the patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0484] 4. Description Generation

[0485] The server uses the same generation API to generate patient-friendly descriptions in language and character-like voice, such as "You're feeling a tingly, painful sensation in your stomach. Does it feel like a little hedgehog is moving around inside you?"

[0486] 5.Display

[0487] The server sends the generated chart and explanation to the terminal, which displays them to the user. "Chart: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed on the terminal.

[0488] Specific examples

[0489] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[0490] User input: "My head hurts," pain intensity "7 / 10"

[0491] Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[0492] Generate medical record: "Patient complains of headache, pain intensity 7 / 10"

[0493] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0494] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[0495] This will enable patients to more accurately describe their symptoms and make it easier for them to understand explanations from doctors, leading to more appropriate diagnoses and treatment.

[0496] The processing flow will be explained below.

[0497] Step 1:

[0498] A user uses a form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user might enter "My stomach hurts" and rate the pain intensity as 8 / 10.

[0499] Step 2:

[0500] The terminal collects data entered by the user, which is organized as "Symptom: stomachache, Severity: 8 / 10."

[0501] Step 3:

[0502] The terminal sends the collected data to the server. Specifically, the organized data is converted into a data structure that can be sent to the server.

[0503] Step 4:

[0504] The server receives the data sent from the device, checks the received data, and verifies its accuracy.

[0505] Step 5:

[0506] Based on the data received by the server, the symptom description and severity data are sent to the generation API, and a request to generate a medical record is sent.

[0507] Step 6:

[0508] The generation API processes the request and automatically generates a medical record based on the input data. Specifically, it generates a medical record with the content, such as, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0509] Step 7:

[0510] The generation API returns the generated medical record to the server, which includes the text data of the medical record.

[0511] Step 8:

[0512] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[0513] Step 9:

[0514] The generation API receives the request and generates a description using language and a character voice that is easy for the patient to understand, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0515] Step 10:

[0516] The generation API returns the generated description to the server, which includes the text data of the description.

[0517] Step 11:

[0518] The server receives the description returned from the generation API and combines the data with the medical records received previously.

[0519] Step 12:

[0520] The server sends the compiled data to the terminal, which includes the generated medical record and explanation.

[0521] Step 13:

[0522] The terminal displays the data received from the server. Specifically, it displays to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0523] The above steps allow users to accurately input their symptoms, generate a medical record in a format that is easy for doctors to understand, and provide explanations that are easy for patients to understand, facilitating smooth communication in the medical field.

[0524] Example 1

[0525] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0526] In medical settings, it can be difficult for patients to accurately communicate their symptoms to medical staff, and it can also be difficult for medical staff to explain things to patients in an easy-to-understand manner. This can lead to insufficient communication between patients and medical staff, which can affect the appropriateness of diagnosis and treatment.

[0527] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0528] In this invention, the server includes: a means for a user to input a description and severity of symptoms using a medical terminal; a means for transmitting the input description and severity of symptoms in data format to the server; a means for the server to automatically generate a medical record using a generative AI model based on the received data; a means for the server to generate an explanation for the patient using the generative AI model based on the generated medical record; and a means for the server to transmit the generated medical record and explanation to the terminal and for the terminal to display them. This allows patients to accurately input their symptoms and reliably communicate them to medical staff through the generated medical record and explanation. Furthermore, medical staff can provide explanations to patients in an easy-to-understand manner, improving the appropriateness of diagnosis and treatment.

[0529] "User" refers to a person who uses a medical terminal to input their symptoms and their severity.

[0530] "Medical device" refers to an electronic device, such as a smartphone, tablet, or computer, that a user uses to input a description and severity of their symptoms.

[0531] "Symptom description" refers to a verbal description of the physical or mental abnormality or discomfort the user is experiencing.

[0532] "Degree" refers to the strength or severity of symptoms expressed numerically or verbally.

[0533] "Data format" refers to the structured information format (e.g., JSON or XML) used to transmit the symptom description and severity to the server.

[0534] "Server" refers to the central processing unit that receives data sent by users and generates medical records and explanatory text using generative AI models.

[0535] A "generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate medical records and explanatory text based on input data.

[0536] A "medical record" refers to a document that serves as a medical record and is generated based on the symptoms and their severity entered by the user.

[0537] "Explanatory text" refers to a document generated using a generative AI model to explain symptoms in an easy-to-understand manner for patients.

[0538] "Terminal" refers to a medical terminal operated by a user, which displays the products (medical records and explanatory text) sent from the server.

[0539] This invention is a system designed to improve communication between patients and doctors in medical settings. The system consists of a user, a terminal, and a server, and uses a generative AI model to automatically generate medical records and explanations.

[0540] First, the user uses a medical device (smartphone, tablet, PC, etc.) to enter a description of their symptoms and their severity. The user enters detailed symptoms (e.g., "My stomach hurts") into the application's input form and selects the intensity or level of pain (e.g., 8 / 10) using a slider bar or drop-down menu.

[0541] Next, the terminal sends this input data to the server in a data format (e.g., JSON). Specifically, the terminal uses the HTTPS protocol over an Internet connection to send the input data as a POST request to the server's endpoint.

[0542] The server automatically generates a medical record using a generative AI model (e.g., GPT-3) based on the received data. During the generation process, the server sends a prompt to the generative AI model. This prompt is, "Please describe the patient's symptoms and severity in medical record format." Based on this prompt, the generative AI model generates a medical record such as, "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0543] The server also uses the generative AI model to generate easy-to-understand explanations for patients. The prompt is, "Please explain the patient's symptoms in kind words and in a character-like tone." An example of a generated explanation is, "Your stomach feels all tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0544] The server sends the generated medical record and explanation to the terminal. The terminal receives this and displays it as specific information for the user. The displayed information is in the form of "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0545] Specific examples

[0546] For example, if a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process goes through the following steps:

[0547] 1. User input: "I have a headache," pain intensity "7 / 10"

[0548] A user enters "I have a headache" into an application form and sets the pain intensity to 7 using the slider.

[0549] 2. Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[0550] The terminal sends the input data to the server in JSON format.

[0551] 3. Medical record generation

[0552] The server sends a prompt to the generating AI model saying, "Please describe the patient's symptoms and severity in a medical record format," and generates a medical record stating, "The patient complains of a headache, and the pain intensity is 7 / 10."

[0553] 4. Description Generation

[0554] The server sends a prompt to the generative AI model, asking it to "describe the symptoms the patient reported in kind words or in a character-like tone," and generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0555] 5.Display

[0556] The server sends the generated medical record and explanation to the terminal, which displays it on the screen.

[0557] In this way, patients can accurately record their symptoms and communicate them to medical staff in an understandable manner, improving the quality of diagnosis and treatment.

[0558] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0559] Step 1: User symptom input

[0560] The user uses a medical device to input symptoms and their severity. The user enters symptoms such as "my stomach hurts" into the application's input form and sets the pain intensity to, for example, 8 / 10 using a slider bar or drop-down menu. The input data is stored in the device in text format.

[0561] Input: User-entered symptoms and their severity (e.g., "My stomach hurts" with severity "8 / 10").

[0562] Output: Temporarily saved as structured data (e.g. JSON).

[0563] Step 2: Send data

[0564] The device sends the entered data to the server. The device sends the data as a POST request to the server endpoint using the HTTPS protocol via an internet connection.

[0565] Input: JSON data containing symptoms and their severity entered by the user into the device (e.g., "Symptom: stomachache, Severity: 8 / 10").

[0566] Output: JSON formatted data sent to the server.

[0567] Step 3: Create a medical record

[0568] Based on the data received by the server, a medical record is automatically generated using a generative AI model. The server sends a prompt to the generative AI model, saying, "Please describe the patient's symptoms and severity in medical record format," and retrieves the generated medical record.

[0569] Input: Symptom and severity data received by the server (e.g., "Symptom: stomachache, Severity: 8 / 10").

[0570] Data processing: The generative AI model is invoked using a prompt ("Please describe the patient's symptoms and severity in medical record format").

[0571] Output: An automatically generated medical record (e.g., "The patient complains of abdominal pain, pain intensity is 8 / 10").

[0572] Step 4: Description generation

[0573] The server uses the same generative AI model to generate a patient-oriented explanation. The server sends a prompt, "Please explain the patient's symptoms in a gentle and character-like tone," and retrieves the generated explanation.

[0574] Input: The prompt and medical record contents to be sent to the generative AI model (e.g., "Symptoms: stomachache, Severity: 8 / 10").

[0575] Data processing: The generative AI model is invoked using a prompt ("Please explain the symptoms the patient reported in kind words and in a character-like voice").

[0576] Output: An automatically generated description (e.g. "Your stomach feels all fuzzy and painful. Does it feel like there's a little hedgehog thrashing around inside you?").

[0577] Step 5: View the medical record and explanation

[0578] The server sends the generated chart and explanation to the terminal, which receives it and displays it to the user. The terminal application analyzes the received data and displays it on the screen.

[0579] Input: Medical record and description data sent from the server (e.g., "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10"; "Description: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?").

[0580] Output: Information displayed on the device screen.

[0581] In this way, users can easily record their own symptoms, and the server can provide automatically generated medical records and explanations based on this information, facilitating smooth communication between medical staff and patients.

[0582] (Application example 1)

[0583] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0584] In today's food delivery services, it is difficult for users to accurately communicate their preferences and allergy information. Existing systems limit the ways in which users can specify their requests in detail, which can lead to ordering errors or inappropriate menu suggestions. Furthermore, explanations to users are often difficult to understand, making it difficult for them to understand complex information. To solve this problem, a system is needed that allows users to easily input their preferences and allergy information, automatically suggests optimal menus based on that information, and provides easy-to-understand explanations.

[0585] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0586] In this invention, the server includes means for inputting a simple explanation of preference information and allergy information, means for transmitting the input preference information and allergy information to the server, means for automatically generating a suggested menu using a generation API based on the received data, means for generating an explanation of the generated suggested menu in easy-to-understand language for the user, and means for transmitting the generated suggested menu and explanation to the terminal and displaying it. This enables users to receive the optimal menu tailored to their preferences and allergies, reduces ordering errors, and provides easy-to-understand explanations.

[0587] The "brief description of preference information" is information about the types of food and seasonings that the user likes.

[0588] "Allergy information" is information about ingredients or substances to which the user is allergic.

[0589] "Input means" refers to a device or software that provides an interface for users to input preference information and allergy information.

[0590] The "means for automatically generating a suggested menu using a generation API" is a method that uses an application programming interface to automatically generate an optimal menu based on the user's preference information and allergy information.

[0591] The "means for generating explanatory text in easy-to-understand language for users" is a method for explaining information about the generated suggested menu in simple language that is easy for users to understand.

[0592] The "means for transmitting to the terminal and displaying" is a method for transmitting the generated suggested menu and explanatory text to the user's terminal and displaying them.

[0593] The embodiments of the present invention will be described below.

[0594] The system for realizing the invention provides a means for users to input a simple description of their preferences and allergy information. This means utilizes a smartphone application. The user inputs their preferences and allergy information using the application. For example, they can input information such as "I like spicy food" or "I'm allergic to nuts."

[0595] The smartphone sends the input preference and allergy information to the server. The server uses a generation API based on the received data to automatically generate a suggested menu that suits the user's preferences and allergies. The generated suggested menu is provided using a generative AI model.

[0596] Next, the server generates an easy-to-understand explanation for the user based on the generated suggested menu. For example, for the menu item "Spicy Tandoori Chicken, Nut-Free," it generates an explanation such as "It's spicy, but it's nut-free, so you can eat it with peace of mind." This explanation is also generated using the generation API.

[0597] Finally, the server sends the generated menu suggestions and explanations to the smartphone, which then displays them to the user, allowing the user to easily check the most suitable menu based on their preferences and allergy information and place their order with confidence.

[0598] The hardware used includes smartphones and servers, and the software used for generation includes a generation API, such as OpenAI's Generative Model API.

[0599] For example, if a user enters "I like spicy food" and specifies "I have a nut allergy," the process will proceed as follows:

[0600] User input: "I like spicy food", allergy information: "nuts"

[0601] Send to device: "Preferences: spicy, Allergies: nuts"

[0602] Generate suggested menu: "Spicy tandoori chicken, nut-free"

[0603] Description generation: "It's spicy, but nut-free so you can eat it with peace of mind."

[0604] Display: "Menu: Spicy Tandoori Chicken, Nut-Free" and "Description: It's spicy, but it's nut-free so you can eat it with peace of mind" will be displayed on your smartphone.

[0605] In this way, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information. This process is realized by inputting a prompt message to the generation API, such as, "If the user likes spicy food and has a nut allergy, please generate the optimal menu suggestion and corresponding explanation."

[0606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0607] Step 1:

[0608] The user enters preference information and allergy information using a smartphone application. Specifically, the user enters "I like spicy food" and selects "I'm allergic to nuts" in the application's input form.

[0609] Input: User preference information (e.g., I like spicy food), allergy information (e.g., I'm allergic to nuts)

[0610] Output: The input information is saved in the application

[0611] Step 2:

[0612] The smartphone sends the user's preference and allergy information to the server, which then formats the data appropriately and sends it to the server.

[0613] Input: Saved input information (preference information, allergy information)

[0614] Output: Formatted data is sent to the server

[0615] Step 3:

[0616] The server calls the generation API based on the received data and automatically generates a menu suggestion. Here, a specific generation AI model is used to analyze the user's input data and generate the optimal menu that meets the conditions.

[0617] Input: Preference and allergy information received by the server

[0618] Output: Generated menu suggestions (e.g. spicy tandoori chicken, nut-free)

[0619] Step 4:

[0620] The server generates a user-friendly description of the proposed menu based on the generated menu suggestion. It uses the generation API again to create a simple and friendly description of the proposed menu.

[0621] Input: Generated suggestion menu

[0622] Output: Generated description (e.g., "It's spicy, but it's nut-free so you can eat it with peace of mind")

[0623] Step 5:

[0624] The server sends the generated suggestion menu and explanation to the smartphone, which then prepares to display this information to the user.

[0625] Input: Generated suggestion menu and description

[0626] Output: Suggested menu and explanations are sent to your smartphone.

[0627] Step 6:

[0628] The smartphone displays the received suggested menu and description to the user, who can then check the suggested menu and description on the screen and decide whether to order.

[0629] Input: Received suggestion menu and description

[0630] Output: A suggestion menu and explanations are displayed on the smartphone screen.

[0631] Through the above steps, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information.

[0632] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0633] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The system includes the following features:

[0634] Enter a brief description of your symptoms and their severity

[0635] A user uses an input form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user enters "I have a stomachache" and sets the pain intensity as 8 / 10.

[0636] Sending data to the server

[0637] The device sends the data collected from the user to the server, which includes information organized in the format "Symptom: stomachache, Severity: 8 / 10."

[0638] Generate medical records using the generation API

[0639] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record includes the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0640] Generating descriptions using the generation API

[0641] The server also uses the generation API to generate explanations in patient-friendly language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0642] Emotion Recognition Using Emotion Engine

[0643] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize the user's emotions. For example, the emotion engine determines that the user is feeling stressed while typing.

[0644] Emotion data sent to server

[0645] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[0646] Adjusting the tone and content of your descriptions

[0647] Based on the emotion data received by the server, the server sends a request to the generation API to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates a gentler explanation.

[0648] Display on the device

[0649] The server sends the compiled data to the device, which includes the generated medical record and an explanation adjusted based on the user's emotions.

[0650] The device displays this information to the user, specifically, "Medical record: Patient complains of stomach pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0651] Specific explanation of program processing

[0652] The program is expected to operate as follows:

[0653] 1. Enter symptoms

[0654] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[0655] 2. Data Transmission

[0656] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[0657] 3. Medical record generation

[0658] Based on the data received by the server, the generation API is called and a medical record is automatically generated. For example, it might state, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0659] 4. Description Generation

[0660] The server uses the same generation API to generate patient-friendly descriptions in a character-like voice, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside you?"

[0661] 5. Emotion recognition

[0662] The device's emotion engine recognizes the user's emotions in real time. For example, the emotion engine recognizes when the user is feeling stressed.

[0663] 6. Emotional Data Transmission

[0664] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[0665] 7. Adjustments to the description

[0666] The server sends a request to the generation API based on the emotion data and adjusts the tone and content of the explanation. For example, if the user is feeling stressed, the explanation will be generated in a gentler tone.

[0667] 8. Display

[0668] The server sends the compiled data to the terminal, which displays it to the user. The medical record reads, "Patient complains of stomach pain, pain intensity 8 / 10," along with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0669] Specific examples

[0670] Symptom input: The user enters "I have a headache" and sets the pain intensity as 7 / 10.

[0671] Generate medical record: "Patient complains of headache, pain intensity 7 / 10"

[0672] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0673] Emotion recognition: The emotion engine recognizes when a user is nervous.

[0674] Adjust the instructions: The user is nervous, so adjust the instructions to make them more relaxed.

[0675] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[0676] In this way, this system, which combines an emotion engine, allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides easy-to-understand explanations that correspond to the patient's emotional state, further improving communication in medical settings.

[0677] The processing flow will be explained below.

[0678] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The specific processing flow of this system is described below.

[0679] Step 1:

[0680] The user uses the input form on the medical device to briefly describe their symptoms and select the severity of the symptoms. For example, the user enters "I have a stomachache" and sets the pain intensity as 8 / 10.

[0681] Step 2:

[0682] The device sends the collected symptom data to the server, which organizes the data in the format "Symptom: stomachache, Severity: 8 / 10."

[0683] Step 3:

[0684] The server receives the data sent from the device, verifies its accuracy, and then calls the generation API to automatically generate the medical record.

[0685] Step 4:

[0686] The generation API generates a medical record based on the input data and sends it back to the server. The medical record contains the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0687] Step 5:

[0688] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[0689] Step 6:

[0690] The API generates a description using words and a character tone that the patient can easily understand, and sends it back to the server. For example, a description such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0691] Step 7:

[0692] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[0693] Step 8:

[0694] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[0695] Step 9:

[0696] The server sends a request to the generation API to adjust the tone and content of the generated description based on the received emotional data. For example, if the user is feeling stressed, the description will be generated in a gentler tone.

[0697] Step 10:

[0698] The generation API generates the adjusted description and sends it back to the server.

[0699] Step 11:

[0700] The server compiles the adjusted explanation and the previously generated medical record and sends it to the terminal.

[0701] Step 12:

[0702] The terminal displays the data received from the server to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0703] Specific examples

[0704] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[0705] Step 1: User types "I have a headache" and sets pain intensity to 7 / 10.

[0706] Step 2: The device sends the organized data, "Symptom: headache, Severity: 7 / 10", to the server.

[0707] Step 3: The server receives the data and sends it to the generation API.

[0708] Step 4: The generation API generates a medical record stating that "the patient complains of a headache and the pain intensity is 7 / 10" and sends it back to the server.

[0709] Step 5: The server receives the medical record and sends a request to the generation API to generate a description.

[0710] Step 6: The generation API generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?" and sends it back to the server.

[0711] Step 7: The emotion engine recognizes the user's tension.

[0712] Step 8: Send the emotion data "user is nervous" to the server.

[0713] Step 9: The server requests the generation API to generate a description of the relaxing content.

[0714] Step 10: The generation API generates the adjusted description and sends it back to the server.

[0715] Step 11: The server sends the adjusted explanation and medical record together to the terminal.

[0716] Step 12: The terminal displays "Chart: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Do I feel like there are ghosts popping in my head?"

[0717] In this way, this system allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides explanations that reflect the patient's emotional state, facilitating smooth communication in medical settings.

[0718] Example 2

[0719] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0720] In modern medical settings, it is often pointed out that communication between patients and doctors is not smooth. In particular, it is often difficult for patients to accurately communicate their symptoms, and the patient's emotional state is often not taken into consideration. As a result, doctors are unable to make appropriate diagnoses or provide appropriate treatment, leading to a decline in patient satisfaction.

[0721] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a brief description of symptoms and the severity of the symptoms using an input form; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generative AI model based on the received data; means for generating an explanation for the generated medical record using a generation API in easy-to-understand words and a character's tone of voice for the patient; means for recognizing the user's emotions in real time using an emotion engine built into the terminal; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation using the generative AI model based on the emotion data; and means for transmitting the generated medical record and the adjusted explanation to the terminal and displaying them. This not only allows patients to accurately input their symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides easy-to-understand explanations that correspond to the patient's emotional state, thereby improving communication in medical settings.

[0722] The "input form" is an interface that allows the user to input a description and severity of the symptoms.

[0723] The "server" is a computer system that receives data entered by the user, generates medical records and explanatory text using a generative AI model, and sends them to the terminal.

[0724] A "generative AI model" is an artificial intelligence model that automatically generates medical records and explanatory text based on the data it receives.

[0725] A medical record is a document that organizes information such as the symptoms a patient complains of and their severity, and is used by doctors to make diagnoses.

[0726] A "generation API" is a program interface for sending data to a generative AI model and generating medical records, explanatory text, etc.

[0727] The "explanation" is a sentence that explains the contents of the generated medical record to the patient in an easy-to-understand manner.

[0728] The "emotion engine" is a system that recognizes emotions in real time from physiological data such as a user's facial expressions, voice, and heart rate.

[0729] "Tone" refers to the emotional expression and tone of the content of an explanation or other text.

[0730] A "terminal" is a device that allows a user to input data and display generated charts and explanations.

[0731] "Emotion data" is information about the user's emotional state as recognized by the emotion engine.

[0732] This invention is a system designed to improve communication between patients and doctors in medical settings. The system inputs a user's symptoms, automatically generates medical records and explanations using a generative AI model, and also includes the ability to recognize and respond to the user's emotions in real time.

[0733] Hardware and software used

[0734] Hardware:

[0735] Terminal: A device (e.g., personal computer, tablet, smartphone, etc.) used to enter user data and display the generated chart and narrative.

[0736] Server: A computer system that processes and calculates the received data and generates medical records and explanatory text using a generative AI model.

[0737] software:

[0738] Generative AI model: For example, OpenAI's GPT-3 is used to analyze data on the server and generate medical records and explanatory text.

[0739] Generative API: A program interface that sends input data to a generative AI model and receives the generated medical records and descriptions.

[0740] Emotion engine: Software that analyzes physiological data such as a user's facial expressions, voice, and heart rate in real time to recognize emotions (e.g., Emotion Recognition API).

[0741] Specific Embodiments of the System

[0742] 1. Symptom input:

[0743] The user inputs their symptoms using the device. For example, the user might input "my stomach hurts" and rate the pain intensity as 8 / 10. This data is then used as an input form on the device using a JavaScript framework such as React or Vue.js.

[0744] 2. Data transmission:

[0745] The device sends the entered symptom and severity data to the server. The data is organized in JSON format and sent in a format such as {"Symptoms": "Stomachache", "Severity": 8}. This process uses HTTP request libraries such as fetch and axios.

[0746] 3. Medical record generation:

[0747] The server analyzes the received data and calls the generative AI model to automatically generate a medical record. The generated medical record will state that "the patient complains of stomach pain, and the pain intensity is 8 / 10." The data is sent using the generation API, and the generated medical record is received.

[0748] 4. Description generation:

[0749] The server uses the same generative AI model to generate explanatory text in patient-friendly language and a character-like tone, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside you?"

[0750] 5. Emotion recognition:

[0751] The device's built-in emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize the user's emotional state. For example, the emotion engine may determine that the user is feeling stressed while typing.

[0752] 6. Emotional Data Transmission:

[0753] The device organizes the recognized emotion data and sends it to the server. The data sent includes information that the user is feeling stressed. The emotion data is also sent in JSON format.

[0754] 7. Description adjustments:

[0755] Based on the emotion data received, the server sends a request to the generation API to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the API will generate a gentler explanation.

[0756] 8. Display:

[0757] The server sends the generated medical record and the adjusted explanation to the terminal, and the terminal displays this information to the user.Specific examples of the information provided include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0758] Specific examples

[0759] Symptom entry example

[0760] A user types in "I have a headache" and sets the pain intensity to 7 / 10.

[0761] Example of medical record generation

[0762] "The patient complains of a headache and the pain intensity is 7 / 10."

[0763] Example of description generation

[0764] "My head is throbbing. Does it feel like ghosts are snapping around in my head?"

[0765] Emotion Recognition Example

[0766] The emotion engine recognizes that the user is nervous.

[0767] Example of adjusting the description

[0768] The user is nervous, so adjust the instructions to make them more relaxed.

[0769] Display example

[0770] The device displays "Medical record: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0771] In this way, this system not only accurately inputs the user's symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides explanations that correspond to the user's emotional state, thereby improving communication in the medical field.

[0772] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0773] Step 1:

[0774] The user accesses the input form on the medical device and enters their symptoms. For example, the user enters "my stomach hurts" and sets the pain intensity to 8 / 10. The input data is saved in text format on the device. This process uses a user interface (e.g., React or Vue.js).

[0775] Input: The user enters the text "My stomach hurts" and sets the pain level to 8.

[0776] Output: JSON data: {"Symptom": "Stomachache", "Pain level": 8}.

[0777] Action: A user accesses a form, enters "My stomach hurts" into the form field, and uses the slider to set the pain intensity to 8.

[0778] Step 2:

[0779] The device sends the user input data to the server using an HTTP POST request, with the data sent in JSON format. Specifically, an HTTP library such as fetch or axios is used.

[0780] Input: JSON data entered by the user: {"Symptom": "Stomachache", "Pain level": 8}

[0781] Output: The data sent to the server.

[0782] Specific operation: The device uses fetch to create an HTTP POST request and send data to the server.

[0783] Step 3:

[0784] The server analyzes the received data and sends it as prompts to a generative AI model, which is used to generate a medical record. The generative AI model uses, for example, GPT-3.

[0785] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[0786] Output: Text data from the medical record: "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0787] Specific operation: The server executes a script written in Python, uses the requests library to send a prompt to the generation API, and saves the returned text as a medical record.

[0788] Step 4:

[0789] The server uses the same generative AI model to generate a prompt, which includes the symptom and severity information entered by the user.

[0790] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[0791] Output: Description: "Your stomach feels all tingly and painful. It feels like there's a little hedgehog thrashing around inside you."

[0792] Specific operation: The server calls the generation API again, sends the input data as a prompt, and saves the returned explanation.

[0793] Step 5:

[0794] The device's emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[0795] Input: Real-time video and audio data from the user.

[0796] Output: Emotion data "feeling stressed."

[0797] What it does: The device collects data using the user's webcam and microphone, and analyzes emotions using the Emotion Recognition API.

[0798] Step 6:

[0799] The device organizes the recognized emotion data and sends it to the server. The data is sent in JSON format, for example, {"emotion": "stress"}.

[0800] Input: Emotional data of "feeling stressed."

[0801] Output: JSON of emotion data sent to the server.

[0802] Specific operation: The device uses fetch to create an HTTP POST request and send emotion data to the server.

[0803] Step 7:

[0804] The server sends a request to the generative AI model based on the emotional data to adjust the tone and content of the explanation. Specifically, if the user is feeling stressed, it will generate a gentler explanation.

[0805] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8} and {"Emotion": "Stress"}.

[0806] Output: A gentle description: "Your stomach feels all tingly and painful. Does it feel like there's a little hedgehog thrashing around inside you?"

[0807] Specific operation: The server generates a prompt including emotion data, sends a request to the generation API, and saves the adjusted explanation that is returned.

[0808] Step 8:

[0809] The server sends the generated medical record and the adjusted explanation to the terminal, which displays them to the user. The medical record and explanation are formatted in HTML format and displayed in the user interface.

[0810] Input: Text data: "The patient complains of stomach pain, pain intensity is 8 / 10" and "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0811] Output: Medical record and explanation displayed on the terminal screen.

[0812] Specific operation: The terminal formats the data received from the server in HTML format and displays it on the screen. Specifically, the medical record displayed is, "The patient complains of stomach pain, and the pain intensity is 8 / 10," with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0813] (Application example 2)

[0814] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0815] Conventional food delivery services have had difficulty providing meal menus that correspond to the user's physical and emotional state. This has led to problems such as not being able to suggest appropriate meals when the user is feeling unwell, or not being able to provide services that are sensitive to the user's emotions. In particular, there is a need for services that suggest optimal meals and provide consideration to ease the user's emotions when the user is feeling unwell or stressed.

[0816] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a brief description of symptoms and the severity of the symptoms; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generation API based on the received data; means for generating an explanation of the generated medical record for the user in easy-to-understand words or a character's tone of voice; means having an emotion engine that recognizes the user's emotions in real time; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation based on the emotion data received by the server; and means for transmitting the generated medical record and the explanation adjusted based on the emotion data to the terminal and displaying it. This makes it possible to propose a personalized meal menu based on the user's physical condition and emotions, and to provide a service that takes emotions into consideration.

[0817] "Brief explanation of symptoms" is information in which the user briefly describes their own physical condition or illness.

[0818] "Symptom severity" is information that indicates the strength or degree of the symptoms felt by the user using a numerical value or a scale.

[0819] "Generation API" means an application programming interface for automatically generating information based on input data.

[0820] A "medical record" is a detailed record of a patient's or user's physical condition and symptoms, and is a document containing information useful for providing medical care and services.

[0821] "Character tone" refers to the way a character speaks and expresses themselves, with the aim of conveying information in a user-friendly and engaging format.

[0822] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and other physiological data to recognize their emotional state in real time.

[0823] "Emotion data" is information that indicates the emotional state of the user recognized by the emotion engine.

[0824] "Means to adjust the tone and content of descriptions" refers to a function that changes the way information is expressed and worded based on emotional data.

[0825] A "terminal" is a device that allows a user to use the system and is capable of inputting and displaying data.

[0826] This invention provides a system for suggesting personalized meal menus and providing emotionally sensitive service in a food delivery service. The system includes the following main means.

[0827] 1. How to enter a brief description of your symptoms and their severity:

[0828] It is a means for users to briefly describe their physical condition or discomfort and input numerical values ​​to indicate the strength and degree of the condition. For example, a user can input a symptom such as "my stomach hurts" and the degree of the pain.

[0829] 2. Means of data transmission:

[0830] This is a means to send the entered symptom description and severity to the server. In this example, the information entered by the user is sent to the server in the format "Stomachache, severity: 8 / 10".

[0831] 3. Automatic generation of medical records using the generation API:

[0832] The server calls a generation API based on the received data and automatically generates a medical record. This medical record contains information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." A possible generation API would be the "OpenAI API" using the "GPT-4" model.

[0833] 4. How to generate a description using the generation API:

[0834] The server uses the generation API to generate explanatory text for patients in easy-to-understand language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0835] 5. Emotion recognition using emotion engine:

[0836] The device is equipped with an emotion engine that analyzes physiological data such as the user's facial expressions and voice in real time to recognize the user's emotions. Possible software for emotion recognition includes "OpenFace" and "IBM Watson Emotion Analysis."

[0837] 6. Means of sending emotional data:

[0838] This is a means for transmitting the recognized emotion data to the server. The transmitted data includes, for example, information that "the user is feeling stressed."

[0839] 7. Adjust the tone and content of your description:

[0840] The server sends a request to the generation API based on the received emotional data to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates an explanation in a gentler tone.

[0841] 8. Display of generated medical records and explanations:

[0842] This is a means of sending and displaying a medical record generated by the server and an explanation adjusted based on emotion data to the terminal. Examples of displayed content include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0843] Examples:

[0844] When a user enters the symptom "stomach ache" and rates the pain intensity as 8 / 10 through a food delivery application, this information is sent to the server. The server then uses a generation API to automatically generate a medical record and suggests a meal menu suitable for the user. If the emotion engine recognizes that the user is feeling stressed, it adjusts the tone of the explanation to a gentler one and displays it to the user along with a relaxing menu.

[0845] Example prompt sentence:

[0846] "Please suggest a meal plan for a user who is experiencing stomach pain. The pain level is 8 / 10 and the user is currently feeling stressed. Please suggest a meal that is easy to digest and explain it to them in a gentle tone."

[0847] Such a system would enable the provision of personalized meal menus and appropriate services according to the user's physical condition and emotions.

[0848] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0849] Step 1:

[0850] A user launches a food delivery application and inputs information about their health condition and emotions. Specifically, they input their physical condition and symptoms (e.g., "I have a stomachache") and their severity (on a scale of 1 to 10). This input data is prepared as transmission data in the format "Symptom: stomachache, Severity: 8 / 10."

[0851] Step 2:

[0852] The device sends the data entered by the user to the server. The input data includes information on symptoms and symptom severity, and is received as "Symptoms: stomachache, Severity: 8 / 10" when sent to the server. This data is stored on the server for subsequent processing.

[0853] Step 3:

[0854] The server calls a generation API based on the received data and automatically generates a medical record. At this stage, a generative AI model (for example, an API using GPT-4) is called and generates medical record information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." The generated medical record is saved for use in the next step.

[0855] Step 4:

[0856] The server uses the same generation API to generate explanatory text for the user in easy-to-understand language and a character-like tone. The input data for this is composed of the generated medical record information and existing templates, and an explanatory text such as "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?" is generated. This explanatory text is also used in subsequent processing.

[0857] Step 5:

[0858] The device analyzes physiological data such as the user's facial expressions and voice in real time and recognizes the user's emotions using an emotion engine. For example, an emotion engine (such as OpenFace or IBM Watson Emotion Analysis) can be used to determine whether the user is feeling stressed while performing input operations. This emotion data is collected as "the user is feeling stressed" and sent to the server.

[0859] Step 6:

[0860] The server adjusts the tone and content of the description based on the recognized emotion data. Here, the emotion data is used as input and processing is performed to change the tone of the existing description. Specifically, the generative AI model is given a prompt such as "Generate a gentler description for users who are feeling stressed," and a description with an adjusted tone is obtained.

[0861] Step 7:

[0862] The server sends the generated medical record along with the adjusted explanation to the terminal. This information is sent in the form of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0863] Step 8:

[0864] The terminal displays the medical record sent from the server and the adjusted explanation to the user. On the terminal screen, "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed, and the user confirms them.

[0865] Step 9:

[0866] The user can then review the suggested meal menu based on the displayed content and select the most suitable option, thereby providing a personalized meal menu that is tailored to the user's physical condition and emotions.

[0867] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0868] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0869] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0870] [Third embodiment]

[0871] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0872] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0873] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0874] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0875] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0876] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0877] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0878] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0879] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0880] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0881] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0882] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0883] The proposed system is designed to improve communication between patients and doctors in medical settings and includes the following features:

[0884] Enter a brief description of your symptoms and their severity

[0885] The user uses an input form on the terminal to input a brief description of the symptoms and their severity.

[0886] Example: "User types 'My stomach hurts' and selects pain intensity as 8 / 10"

[0887] Sending data to the server

[0888] The terminal transmits the symptom data collected from the user to the server.

[0889] Example: "The device sends the summarized data, 'Symptom: stomachache, Severity: 8 / 10', to the server."

[0890] Generate medical records using the generation API

[0891] The server calls the generation API based on the data received and automatically generates the medical record.

[0892] Example: "The server uses the generation API to generate a medical record stating, 'The patient complains of abdominal pain, and the pain intensity is 8 / 10.'"

[0893] Generating descriptions using the generation API

[0894] The server also uses the generation API to generate explanatory text for patients using easy-to-understand language and a character-like tone of voice.

[0895] Example: "The server generates the description 'Your stomach feels all fuzzy and painful. Does it feel like a little hedgehog is moving around inside you?'"

[0896] Display on the device

[0897] The server sends the generated medical record and explanation to the terminal.

[0898] The terminal displays the received data to the user.

[0899] Example: "The device displays to the user: 'Patient report: Patient complains of abdominal pain, pain intensity 8 / 10' and 'Explanation: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?'"

[0900] Program processing description

[0901] The program is expected to operate as follows:

[0902] 1. Enter symptoms

[0903] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[0904] 2. Data Transmission

[0905] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[0906] 3. Medical record generation

[0907] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record will state that "the patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0908] 4. Description Generation

[0909] The server uses the same generation API to generate patient-friendly descriptions in language and character-like voice, such as "You're feeling a tingly, painful sensation in your stomach. Does it feel like a little hedgehog is moving around inside you?"

[0910] 5.Display

[0911] The server sends the generated chart and explanation to the terminal, which displays them to the user. "Chart: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed on the terminal.

[0912] Specific examples

[0913] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[0914] User input: "My head hurts," pain intensity "7 / 10"

[0915] Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[0916] Chart generation: "Patient complains of headache, pain intensity 7 / 10"

[0917] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0918] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[0919] This will enable patients to more accurately describe their symptoms and make it easier for them to understand explanations from doctors, leading to more appropriate diagnoses and treatment.

[0920] The processing flow will be explained below.

[0921] Step 1:

[0922] A user uses a form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user might enter "I have a stomachache" and rate the pain intensity as 8 / 10.

[0923] Step 2:

[0924] The terminal collects data entered by the user, which is organized as "Symptom: stomachache, Severity: 8 / 10."

[0925] Step 3:

[0926] The terminal sends the collected data to the server. Specifically, the organized data is converted into a data structure that can be sent to the server.

[0927] Step 4:

[0928] The server receives the data sent from the device, checks the received data, and verifies its accuracy.

[0929] Step 5:

[0930] Based on the data received by the server, the symptom description and severity data are sent to the generation API, and a request to generate a medical record is sent.

[0931] Step 6:

[0932] The generation API processes the request and automatically generates a medical record based on the input data. Specifically, it generates a medical record with the content, such as, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[0933] Step 7:

[0934] The generation API returns the generated medical record to the server, which includes the text data of the medical record.

[0935] Step 8:

[0936] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[0937] Step 9:

[0938] The generation API receives the request and generates a description using language and a character voice that is easy for the patient to understand, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0939] Step 10:

[0940] The generation API returns the generated description to the server, which includes the text data of the description.

[0941] Step 11:

[0942] The server receives the description returned from the generation API and combines the data with the medical records received previously.

[0943] Step 12:

[0944] The server sends the compiled data to the terminal, which includes the generated medical record and explanation.

[0945] Step 13:

[0946] The terminal displays the data received from the server. Specifically, it displays to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0947] The above steps allow users to accurately input their symptoms, generate a medical record in a format that is easy for doctors to understand, and provide explanations that are easy for patients to understand, facilitating smooth communication in the medical field.

[0948] Example 1

[0949] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0950] In medical settings, it can be difficult for patients to accurately communicate their symptoms to medical staff, and it can also be difficult for medical staff to explain things to patients in an easy-to-understand manner. This can lead to insufficient communication between patients and medical staff, which can affect the appropriateness of diagnosis and treatment.

[0951] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0952] In this invention, the server includes: a means for a user to input a description and severity of symptoms using a medical terminal; a means for transmitting the input description and severity of symptoms in data format to the server; a means for the server to automatically generate a medical record using a generative AI model based on the received data; a means for the server to generate an explanation for the patient using the generative AI model based on the generated medical record; and a means for the server to transmit the generated medical record and explanation to the terminal and for the terminal to display them. This allows patients to accurately input their symptoms and reliably communicate them to medical staff through the generated medical record and explanation. Furthermore, medical staff can provide explanations to patients in an easy-to-understand manner, improving the appropriateness of diagnosis and treatment.

[0953] "User" refers to a person who uses a medical terminal to input their symptoms and their severity.

[0954] "Medical device" refers to an electronic device, such as a smartphone, tablet, or computer, that a user uses to input a description and severity of their symptoms.

[0955] "Symptom description" refers to a verbal description of the physical or mental abnormality or discomfort the user is experiencing.

[0956] "Degree" refers to the strength or severity of symptoms expressed numerically or verbally.

[0957] "Data format" refers to the structured information format (e.g., JSON or XML) used to transmit the symptom description and severity to the server.

[0958] "Server" refers to the central processing unit that receives data sent by users and generates medical records and explanatory text using generative AI models.

[0959] A "generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate medical records and explanatory text based on input data.

[0960] A "medical record" refers to a document that serves as a medical record and is generated based on the symptoms and their severity entered by the user.

[0961] "Explanatory text" refers to a document generated using a generative AI model to explain symptoms in an easy-to-understand manner for patients.

[0962] "Terminal" refers to a medical terminal operated by a user, which displays the products (medical records and explanatory text) sent from the server.

[0963] This invention is a system designed to improve communication between patients and doctors in medical settings. The system consists of a user, a terminal, and a server, and uses a generative AI model to automatically generate medical records and explanations.

[0964] First, the user uses a medical device (smartphone, tablet, PC, etc.) to enter a description of their symptoms and their severity. The user enters detailed symptoms (e.g., "My stomach hurts") into the application's input form and selects the intensity or level of pain (e.g., 8 / 10) using a slider bar or drop-down menu.

[0965] Next, the terminal sends this input data to the server in a data format (e.g., JSON). Specifically, the terminal uses the HTTPS protocol over an Internet connection to send the input data as a POST request to the server's endpoint.

[0966] The server automatically generates a medical record using a generative AI model (e.g., GPT-3) based on the received data. During the generation process, the server sends a prompt to the generative AI model. This prompt is, "Please describe the patient's symptoms and severity in medical record format." Based on this prompt, the generative AI model generates a medical record such as, "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[0967] The server also uses the generative AI model to generate easy-to-understand explanations for patients. The prompt is, "Please explain the patient's symptoms in kind words and in a character-like tone." An example of a generated explanation is, "Your stomach feels all tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[0968] The server sends the generated medical record and explanation to the terminal. The terminal receives this and displays it as specific information for the user. The displayed information is in the form of "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[0969] Specific examples

[0970] For example, if a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process goes through the following steps:

[0971] 1. User input: "I have a headache," pain intensity "7 / 10"

[0972] A user enters "I have a headache" into an application form and sets the pain intensity to 7 using the slider.

[0973] 2. Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[0974] The terminal sends the input data to the server in JSON format.

[0975] 3. Medical record generation

[0976] The server sends a prompt to the generating AI model saying, "Please describe the patient's symptoms and severity in a medical record format," and generates a medical record stating, "The patient complains of a headache, and the pain intensity is 7 / 10."

[0977] 4. Description Generation

[0978] The server sends a prompt to the generative AI model, asking it to "describe the symptoms the patient reported in kind words or in a character-like tone," and generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[0979] 5.Display

[0980] The server sends the generated medical record and explanation to the terminal, which displays it on the screen.

[0981] In this way, patients can accurately record their symptoms and communicate them to medical staff in an understandable manner, improving the quality of diagnosis and treatment.

[0982] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0983] Step 1: User symptom input

[0984] The user uses a medical device to input symptoms and their severity. The user enters symptoms such as "my stomach hurts" into the application's input form and sets the pain intensity to, for example, 8 / 10 using a slider bar or drop-down menu. The input data is stored in the device in text format.

[0985] Input: User-entered symptoms and their severity (e.g., "My stomach hurts" with severity "8 / 10").

[0986] Output: Temporarily saved as structured data (e.g. JSON).

[0987] Step 2: Send data

[0988] The device sends the entered data to the server. The device sends the data as a POST request to the server endpoint using the HTTPS protocol via an internet connection.

[0989] Input: JSON data containing symptoms and their severity entered by the user into the device (e.g., "Symptom: stomachache, Severity: 8 / 10").

[0990] Output: JSON formatted data sent to the server.

[0991] Step 3: Create a medical record

[0992] Based on the data received by the server, a medical record is automatically generated using a generative AI model. The server sends a prompt to the generative AI model, saying, "Please describe the patient's symptoms and severity in medical record format," and retrieves the generated medical record.

[0993] Input: Symptom and severity data received by the server (e.g., "Symptom: stomachache, Severity: 8 / 10").

[0994] Data processing: The generative AI model is invoked using a prompt ("Please describe the patient's symptoms and severity in medical record format").

[0995] Output: An automatically generated medical record (e.g., "The patient complains of abdominal pain, pain intensity is 8 / 10").

[0996] Step 4: Description generation

[0997] The server uses the same generative AI model to generate a patient-oriented explanation. The server sends a prompt, "Please explain the patient's symptoms in a gentle and character-like tone," and retrieves the generated explanation.

[0998] Input: The prompt and medical record contents to be sent to the generative AI model (e.g., "Symptoms: stomachache, Severity: 8 / 10").

[0999] Data processing: The generative AI model is invoked using a prompt ("Please explain the symptoms the patient reported in kind words and in a character-like voice").

[1000] Output: An automatically generated description (e.g. "Your stomach feels all fuzzy and painful. Does it feel like there's a little hedgehog thrashing around inside you?").

[1001] Step 5: View the medical record and explanation

[1002] The server sends the generated chart and explanation to the terminal, which receives it and displays it to the user. The terminal application analyzes the received data and displays it on the screen.

[1003] Input: Medical record and description data sent from the server (e.g., "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10"; "Description: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?").

[1004] Output: Information displayed on the device screen.

[1005] In this way, users can easily record their own symptoms, and the server can provide automatically generated medical records and explanations based on this information, facilitating smooth communication between medical staff and patients.

[1006] (Application example 1)

[1007] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1008] In today's food delivery services, it is difficult for users to accurately communicate their preferences and allergy information. Existing systems limit the ways in which users can specify their requests in detail, which can lead to ordering errors or inappropriate menu suggestions. Furthermore, explanations to users are often difficult to understand, making it difficult for them to understand complex information. To solve this problem, a system is needed that allows users to easily input their preferences and allergy information, automatically suggests optimal menus based on that information, and provides easy-to-understand explanations.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1010] In this invention, the server includes means for inputting a simple explanation of preference information and allergy information, means for transmitting the input preference information and allergy information to the server, means for automatically generating a suggested menu using a generation API based on the received data, means for generating an explanation of the generated suggested menu in easy-to-understand language for the user, and means for transmitting the generated suggested menu and explanation to the terminal and displaying it. This enables users to receive the optimal menu tailored to their preferences and allergies, reduces ordering errors, and provides easy-to-understand explanations.

[1011] The "brief description of preference information" is information about the types of food and seasonings that the user likes.

[1012] "Allergy information" is information about ingredients or substances to which the user is allergic.

[1013] "Input means" refers to a device or software that provides an interface for users to input preference information and allergy information.

[1014] The "means for automatically generating a suggested menu using a generation API" is a method that uses an application programming interface to automatically generate an optimal menu based on the user's preference information and allergy information.

[1015] The "means for generating explanatory text in easy-to-understand language for users" is a method for explaining information about the generated suggested menu in simple language that is easy for users to understand.

[1016] The "means for transmitting to the terminal and displaying" is a method for transmitting the generated suggested menu and explanatory text to the user's terminal and displaying them.

[1017] The embodiments of the present invention will be described below.

[1018] The system for realizing the invention provides a means for users to input a simple description of their preferences and allergy information. This means utilizes a smartphone application. The user inputs their preferences and allergy information using the application. For example, they can input information such as "I like spicy food" or "I'm allergic to nuts."

[1019] The smartphone sends the input preference and allergy information to the server. The server uses a generation API based on the received data to automatically generate a suggested menu that suits the user's preferences and allergies. The generated suggested menu is provided using a generative AI model.

[1020] Next, the server generates an easy-to-understand explanation for the user based on the generated suggested menu. For example, for the menu item "Spicy Tandoori Chicken, Nut-Free," it generates an explanation such as "It's spicy, but it's nut-free, so you can eat it with peace of mind." This explanation is also generated using the generation API.

[1021] Finally, the server sends the generated menu suggestions and explanations to the smartphone, which then displays them to the user, allowing the user to easily check the most suitable menu based on their preferences and allergy information and place their order with confidence.

[1022] The hardware used includes smartphones and servers, and the software used for generation includes a generation API, such as OpenAI's Generative Model API.

[1023] For example, if a user enters "I like spicy food" and specifies "I have a nut allergy," the process will proceed as follows:

[1024] User input: "I like spicy food", allergy information: "nuts"

[1025] Send to device: "Preferences: spicy, Allergies: nuts"

[1026] Generate suggested menu: "Spicy tandoori chicken, nut-free"

[1027] Description generation: "It's spicy, but nut-free so you can eat it with peace of mind."

[1028] Display: "Menu: Spicy Tandoori Chicken, Nut-Free" and "Description: It's spicy, but it's nut-free so you can eat it with peace of mind" will be displayed on your smartphone.

[1029] In this way, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information. This process is achieved by inputting a prompt message to the generation API, such as, "If the user likes spicy food and has a nut allergy, please generate the optimal menu suggestion and corresponding explanation."

[1030] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1031] Step 1:

[1032] A user enters preference information and allergy information using a smartphone application. Specifically, the user enters "I like spicy food" and selects "I'm allergic to nuts" in the application's input form.

[1033] Input: User preference information (e.g., I like spicy food), allergy information (e.g., I'm allergic to nuts)

[1034] Output: The input information is saved in the application

[1035] Step 2:

[1036] The smartphone sends the user's preference and allergy information to the server, which then formats the data appropriately and sends it to the server.

[1037] Input: Saved input information (preference information, allergy information)

[1038] Output: Formatted data is sent to the server

[1039] Step 3:

[1040] The server calls the generation API based on the received data and automatically generates a menu suggestion. Here, a specific generation AI model is used to analyze the user's input data and generate the optimal menu that meets the conditions.

[1041] Input: Preference and allergy information received by the server

[1042] Output: Generated menu suggestions (e.g. spicy tandoori chicken, nut-free)

[1043] Step 4:

[1044] The server generates a user-friendly description of the proposed menu based on the generated menu suggestion. It uses the generation API again to create a simple and friendly description of the proposed menu.

[1045] Input: Generated suggestion menu

[1046] Output: Generated description (e.g., "It's spicy, but it's nut-free so you can eat it with peace of mind")

[1047] Step 5:

[1048] The server sends the generated suggestion menu and explanation to the smartphone, which then prepares to display this information to the user.

[1049] Input: Generated suggestion menu and description

[1050] Output: Suggested menu and explanations are sent to your smartphone.

[1051] Step 6:

[1052] The smartphone displays the received suggested menu and description to the user, who can then check the suggested menu and description on the screen and decide whether to order.

[1053] Input: Received suggestion menu and description

[1054] Output: A suggestion menu and explanations are displayed on the smartphone screen.

[1055] Through the above steps, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information.

[1056] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1057] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The system includes the following features:

[1058] Enter a brief description of your symptoms and their severity

[1059] A user uses an input form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user enters "I have a stomachache" and sets the pain intensity as 8 / 10.

[1060] Sending data to the server

[1061] The device sends the data collected from the user to the server, which includes information organized in the format "Symptom: stomachache, Severity: 8 / 10."

[1062] Generate medical records using the generation API

[1063] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record includes the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[1064] Generating descriptions using the generation API

[1065] The server also uses the generation API to generate explanations in patient-friendly language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1066] Emotion Recognition Using Emotion Engine

[1067] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize the user's emotions. For example, the emotion engine determines that the user is feeling stressed while typing.

[1068] Emotion data sent to server

[1069] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[1070] Adjusting the tone and content of your descriptions

[1071] Based on the emotion data received by the server, the server sends a request to the generation API to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates a gentler explanation.

[1072] Display on the device

[1073] The server sends the compiled data to the device, which includes the generated medical record and an explanation adjusted based on the user's emotions.

[1074] The device displays this information to the user, specifically, "Medical record: Patient complains of stomach pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1075] Specific explanation of program processing

[1076] The program is expected to operate as follows:

[1077] 1. Enter symptoms

[1078] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[1079] 2. Data Transmission

[1080] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[1081] 3. Medical record generation

[1082] Based on the data received by the server, the generation API is called and a medical record is automatically generated. For example, it might state, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[1083] 4. Description Generation

[1084] The server uses the same generation API to generate patient-friendly descriptions in a character-like voice, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside you?"

[1085] 5. Emotion recognition

[1086] The device's emotion engine recognizes the user's emotions in real time. For example, the emotion engine recognizes when the user is feeling stressed.

[1087] 6. Emotional Data Transmission

[1088] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[1089] 7. Adjustments to the description

[1090] The server sends a request to the generation API based on the emotion data and adjusts the tone and content of the explanation. For example, if the user is feeling stressed, the explanation will be generated in a gentler tone.

[1091] 8. Display

[1092] The server sends the compiled data to the terminal, which displays it to the user. The medical record reads, "Patient complains of stomach pain, pain intensity 8 / 10," along with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1093] Specific examples

[1094] Symptom input: The user enters "I have a headache" and sets the pain intensity as 7 / 10.

[1095] Chart generation: "Patient complains of headache, pain intensity 7 / 10"

[1096] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[1097] Emotion recognition: The emotion engine recognizes when a user is nervous.

[1098] Adjust the instructions: The user is nervous, so adjust the instructions to make them more relaxed.

[1099] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[1100] In this way, this system, which combines an emotion engine, allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides easy-to-understand explanations that correspond to the patient's emotional state, further improving communication in medical settings.

[1101] The processing flow will be explained below.

[1102] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The specific processing flow of this system is described below.

[1103] Step 1:

[1104] The user uses the input form on the medical device to briefly describe their symptoms and select the severity of the symptoms. For example, the user enters "My stomach hurts" and sets the pain intensity as 8 / 10.

[1105] Step 2:

[1106] The device sends the collected symptom data to the server, which organizes the data in the format "Symptom: stomachache, Severity: 8 / 10."

[1107] Step 3:

[1108] The server receives the data sent from the device, verifies its accuracy, and then calls the generation API to automatically generate the medical record.

[1109] Step 4:

[1110] The generation API generates a medical record based on the input data and sends it back to the server. The medical record contains the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[1111] Step 5:

[1112] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[1113] Step 6:

[1114] The generation API generates a description using words and a character tone that the patient can easily understand, and sends it back to the server. For example, a description such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1115] Step 7:

[1116] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[1117] Step 8:

[1118] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[1119] Step 9:

[1120] The server sends a request to the generation API to adjust the tone and content of the generated description based on the received emotional data. For example, if the user is feeling stressed, the description will be generated in a gentler tone.

[1121] Step 10:

[1122] The generation API generates the adjusted description and sends it back to the server.

[1123] Step 11:

[1124] The server compiles the adjusted explanation and the previously generated medical record and sends it to the terminal.

[1125] Step 12:

[1126] The terminal displays the data received from the server to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1127] Specific examples

[1128] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[1129] Step 1: User types "I have a headache" and sets pain intensity to 7 / 10.

[1130] Step 2: The device sends the organized data, "Symptom: headache, Severity: 7 / 10", to the server.

[1131] Step 3: The server receives the data and sends it to the generation API.

[1132] Step 4: The generation API generates a medical record stating that "the patient complains of a headache and the pain intensity is 7 / 10" and sends it back to the server.

[1133] Step 5: The server receives the medical record and sends a request to the generation API to generate a description.

[1134] Step 6: The generation API generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?" and sends it back to the server.

[1135] Step 7: The emotion engine recognizes the user's tension.

[1136] Step 8: Send the emotion data "user is nervous" to the server.

[1137] Step 9: The server requests the generation API to generate a description of the relaxing content.

[1138] Step 10: The generation API generates the adjusted description and sends it back to the server.

[1139] Step 11: The server sends the adjusted explanation and medical record together to the terminal.

[1140] Step 12: The terminal displays "Chart: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Do I feel like there are ghosts popping in my head?"

[1141] In this way, this system allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides explanations that reflect the patient's emotional state, facilitating smooth communication in medical settings.

[1142] Example 2

[1143] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1144] In modern medical settings, it is often pointed out that communication between patients and doctors is not smooth. In particular, it is often difficult for patients to accurately communicate their symptoms, and the patient's emotional state is often not taken into consideration. As a result, doctors are unable to make appropriate diagnoses or provide appropriate treatment, leading to a decline in patient satisfaction.

[1145] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a brief description of symptoms and the severity of the symptoms using an input form; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generative AI model based on the received data; means for generating an explanation for the generated medical record using a generation API in easy-to-understand words and a character's tone of voice for the patient; means for recognizing the user's emotions in real time using an emotion engine built into the terminal; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation using the generative AI model based on the emotion data; and means for transmitting the generated medical record and the adjusted explanation to the terminal and displaying them. This not only allows patients to accurately input their symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides easy-to-understand explanations that correspond to the patient's emotional state, thereby improving communication in medical settings.

[1146] The "input form" is an interface that allows the user to input a description and severity of the symptoms.

[1147] The "server" is a computer system that receives data entered by the user, generates medical records and explanatory text using a generative AI model, and sends them to the terminal.

[1148] A "generative AI model" is an artificial intelligence model that automatically generates medical records and explanatory text based on the data it receives.

[1149] A medical record is a document that organizes information such as the symptoms a patient complains of and their severity, and is used by doctors to make diagnoses.

[1150] A "generation API" is a program interface for sending data to a generative AI model and generating medical records, explanatory text, etc.

[1151] The "explanation" is a sentence that explains the contents of the generated medical record to the patient in an easy-to-understand manner.

[1152] The "emotion engine" is a system that recognizes emotions in real time from physiological data such as a user's facial expressions, voice, and heart rate.

[1153] "Tone" refers to the emotional expression and tone of the content of an explanation or other text.

[1154] A "terminal" is a device that allows a user to input data and display generated charts and explanations.

[1155] "Emotion data" is information about the user's emotional state as recognized by the emotion engine.

[1156] This invention is a system designed to improve communication between patients and doctors in medical settings. The system inputs a user's symptoms, automatically generates medical records and explanations using a generative AI model, and also includes the ability to recognize and respond to the user's emotions in real time.

[1157] Hardware and software used

[1158] Hardware:

[1159] Terminal: A device (e.g., personal computer, tablet, smartphone, etc.) used to enter user data and display the generated chart and narrative.

[1160] Server: A computer system that processes and calculates the received data and generates medical records and explanatory text using a generative AI model.

[1161] software:

[1162] Generative AI model: For example, OpenAI's GPT-3 is used to analyze data on the server and generate medical records and explanatory text.

[1163] Generative API: A program interface that sends input data to a generative AI model and receives the generated medical records and descriptions.

[1164] Emotion engine: Software that analyzes physiological data such as a user's facial expressions, voice, and heart rate in real time to recognize emotions (e.g., Emotion Recognition API).

[1165] Specific Embodiments of the System

[1166] 1. Symptom input:

[1167] The user inputs their symptoms using the device. For example, the user might input "my stomach hurts" and rate the pain intensity as 8 / 10. This data is then used as an input form on the device using a JavaScript framework such as React or Vue.js.

[1168] 2. Data transmission:

[1169] The device sends the entered symptom and severity data to the server. The data is organized in JSON format and sent in a format such as {"Symptoms": "Stomachache", "Severity": 8}. This process uses HTTP request libraries such as fetch and axios.

[1170] 3. Medical record generation:

[1171] The server analyzes the received data and calls the generative AI model to automatically generate a medical record. The generated medical record will state that "the patient complains of stomach pain, and the pain intensity is 8 / 10." The data is sent using the generation API, and the generated medical record is received.

[1172] 4. Description generation:

[1173] The server uses the same generative AI model to generate explanatory text in patient-friendly language and a character-like tone, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside you?"

[1174] 5. Emotion recognition:

[1175] The device's built-in emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize the user's emotional state. For example, the emotion engine may determine that the user is feeling stressed while typing.

[1176] 6. Emotional Data Transmission:

[1177] The device organizes the recognized emotion data and sends it to the server. The data sent includes information that the user is feeling stressed. The emotion data is also sent in JSON format.

[1178] 7. Description adjustments:

[1179] Based on the emotion data received by the server, the API sends a request to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the API generates a gentler explanation.

[1180] 8. Display:

[1181] The server sends the generated medical record and the adjusted explanation to the terminal, and the terminal displays this information to the user.Specific examples of the information provided include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1182] Specific examples

[1183] Symptom entry example

[1184] A user types in "I have a headache" and sets the pain intensity to 7 / 10.

[1185] Example of medical record generation

[1186] "The patient complains of a headache and the pain intensity is 7 / 10."

[1187] Example of description generation

[1188] "My head is throbbing. Does it feel like ghosts are snapping around in my head?"

[1189] Emotion Recognition Example

[1190] The emotion engine recognizes that the user is nervous.

[1191] Example of adjusting the description

[1192] The user is nervous, so adjust the instructions to make them more relaxed.

[1193] Display example

[1194] The device displays "Medical record: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Does it feel like there's a ghost popping in my head?"

[1195] In this way, this system not only accurately inputs the user's symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides explanations that correspond to the user's emotional state, thereby improving communication in the medical field.

[1196] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1197] Step 1:

[1198] The user accesses the input form on the medical device and enters their symptoms. For example, the user enters "my stomach hurts" and sets the pain intensity to 8 / 10. The input data is saved in text format on the device. This process uses a user interface (e.g., React or Vue.js).

[1199] Input: The user enters the text "My stomach hurts" and sets the pain level to 8.

[1200] Output: JSON data: {"Symptom": "Stomachache", "Pain level": 8}.

[1201] Action: A user accesses a form, enters "My stomach hurts" into the form field, and uses the slider to set the pain intensity to 8.

[1202] Step 2:

[1203] The device sends the user input data to the server using an HTTP POST request, with the data sent in JSON format. Specifically, an HTTP library such as fetch or axios is used.

[1204] Input: JSON data entered by the user: {"Symptom": "Stomachache", "Pain level": 8}

[1205] Output: The data sent to the server.

[1206] Specific operation: The device uses fetch to create an HTTP POST request and send data to the server.

[1207] Step 3:

[1208] The server analyzes the received data and sends it as prompts to a generative AI model, which is used to generate a medical record. The generative AI model uses, for example, GPT-3.

[1209] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[1210] Output: Text data from the medical record: "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[1211] Specific operation: The server executes a script written in Python, uses the requests library to send a prompt to the generation API, and saves the returned text as a medical record.

[1212] Step 4:

[1213] The server uses the same generative AI model to generate a prompt, which includes the symptom and severity information entered by the user.

[1214] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[1215] Output: Description: "Your stomach feels all tingly and painful. It feels like there's a little hedgehog thrashing around inside you."

[1216] Specific operation: The server calls the generation API again, sends the input data as a prompt, and saves the returned explanation.

[1217] Step 5:

[1218] The device's emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[1219] Input: Real-time video and audio data from the user.

[1220] Output: Emotion data "feeling stressed."

[1221] What it does: The device collects data using the user's webcam and microphone, and analyzes emotions using the Emotion Recognition API.

[1222] Step 6:

[1223] The device organizes the recognized emotion data and sends it to the server. The data is sent in JSON format, for example, {"emotion": "stress"}.

[1224] Input: Emotional data of "feeling stressed."

[1225] Output: JSON of emotion data sent to the server.

[1226] Specific operation: The device uses fetch to create an HTTP POST request and send emotion data to the server.

[1227] Step 7:

[1228] The server sends a request to the generative AI model based on the emotional data to adjust the tone and content of the explanation. Specifically, if the user is feeling stressed, it will generate a gentler explanation.

[1229] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8} and {"Emotion": "Stress"}.

[1230] Output: A gentle description: "Your stomach feels all tingly and painful. Does it feel like there's a little hedgehog thrashing around inside you?"

[1231] Specific operation: The server generates a prompt including emotion data, sends a request to the generation API, and saves the adjusted explanation that is returned.

[1232] Step 8:

[1233] The server sends the generated medical record and the adjusted explanation to the terminal, which displays them to the user. The medical record and explanation are formatted in HTML format and displayed in the user interface.

[1234] Input: Text data: "The patient complains of stomach pain, pain intensity is 8 / 10" and "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1235] Output: Medical record and explanation displayed on the terminal screen.

[1236] Specific operation: The terminal formats the data received from the server in HTML format and displays it on the screen. Specifically, the medical record displayed is, "The patient complains of stomach pain, and the pain intensity is 8 / 10," with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1237] (Application example 2)

[1238] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1239] Conventional food delivery services have had difficulty providing meal menus that correspond to the user's physical and emotional state. This has led to problems such as not being able to suggest appropriate meals when the user is feeling unwell, or not being able to provide services that are sensitive to the user's emotions. In particular, there is a need for services that suggest optimal meals and provide consideration to ease the user's emotions when the user is feeling unwell or stressed.

[1240] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a brief description of symptoms and the severity of the symptoms; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generation API based on the received data; means for generating an explanation of the generated medical record for the user in easy-to-understand words or a character's tone of voice; means having an emotion engine that recognizes the user's emotions in real time; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation based on the emotion data received by the server; and means for transmitting the generated medical record and the explanation adjusted based on the emotion data to the terminal and displaying it. This makes it possible to propose a personalized meal menu based on the user's physical condition and emotions, and to provide a service that takes emotions into consideration.

[1241] "Brief explanation of symptoms" is information in which the user briefly describes their own physical condition or illness.

[1242] "Symptom severity" is information that indicates the strength or degree of the symptoms felt by the user using a numerical value or a scale.

[1243] "Generation API" means an application programming interface for automatically generating information based on input data.

[1244] A "medical record" is a detailed record of a patient's or user's physical condition and symptoms, and is a document containing information useful for providing medical care and services.

[1245] "Character tone" refers to the way a character speaks and expresses themselves, with the aim of conveying information in a user-friendly and engaging format.

[1246] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and other physiological data to recognize their emotional state in real time.

[1247] "Emotion data" is information that indicates the emotional state of the user recognized by the emotion engine.

[1248] "Means to adjust the tone and content of descriptions" refers to a function that changes the way information is expressed and worded based on emotional data.

[1249] A "terminal" is a device that allows a user to use the system and is capable of inputting and displaying data.

[1250] This invention provides a system for suggesting personalized meal menus and providing emotionally sensitive service in a food delivery service. The system includes the following main means.

[1251] 1. How to enter a brief description of your symptoms and their severity:

[1252] It is a means for users to briefly describe their physical condition or discomfort and input numerical values ​​to indicate the strength and degree of the condition. For example, a user can input a symptom such as "my stomach hurts" and the degree of the pain.

[1253] 2. Means of data transmission:

[1254] This is a means to send the entered symptom description and severity to the server. In this example, the information entered by the user is sent to the server in the format "Stomachache, severity: 8 / 10".

[1255] 3. Automatic generation of medical records using the generation API:

[1256] The server calls a generation API based on the received data and automatically generates a medical record. This medical record contains information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." A possible generation API would be the "OpenAI API" using the "GPT-4" model.

[1257] 4. How to generate a description using the generation API:

[1258] The server uses the generation API to generate explanatory text for patients in easy-to-understand language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1259] 5. Emotion recognition using emotion engine:

[1260] The device is equipped with an emotion engine that analyzes physiological data such as the user's facial expressions and voice in real time to recognize the user's emotions. Possible software for emotion recognition includes "OpenFace" and "IBM Watson Emotion Analysis."

[1261] 6. Means of sending emotional data:

[1262] This is a means for transmitting the recognized emotion data to the server. The transmitted data includes, for example, information that "the user is feeling stressed."

[1263] 7. Adjust the tone and content of your description:

[1264] The server sends a request to the generation API based on the received emotional data to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates an explanation in a gentler tone.

[1265] 8. Display of generated medical records and explanations:

[1266] This is a means of sending and displaying a medical record generated by the server and an explanation adjusted based on emotion data to the terminal. Examples of displayed content include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1267] Examples:

[1268] When a user enters the symptom "stomach ache" and rates the pain intensity as 8 / 10 through a food delivery application, this information is sent to the server. The server then uses a generation API to automatically generate a medical record and suggests a meal menu suitable for the user. If the emotion engine recognizes that the user is feeling stressed, it adjusts the tone of the explanation to a gentler one and displays it to the user along with a relaxing menu.

[1269] Example prompt sentence:

[1270] "Please suggest a meal plan for a user who is experiencing stomach pain. The pain level is 8 / 10 and the user is currently feeling stressed. Please suggest a meal that is easy to digest and explain it to them in a gentle tone."

[1271] Such a system would enable the provision of personalized meal menus and appropriate services according to the user's physical condition and emotions.

[1272] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1273] Step 1:

[1274] A user launches a food delivery application and inputs information about their health condition and emotions. Specifically, they input their physical condition and symptoms (e.g., "I have a stomachache") and their severity (on a scale of 1 to 10). This input data is prepared as transmission data in the format "Symptom: stomachache, Severity: 8 / 10."

[1275] Step 2:

[1276] The device sends the data entered by the user to the server. The input data includes information on symptoms and symptom severity, and is received as "Symptoms: stomachache, Severity: 8 / 10" when sent to the server. This data is stored on the server for subsequent processing.

[1277] Step 3:

[1278] The server calls a generation API based on the received data and automatically generates a medical record. At this stage, a generative AI model (for example, an API using GPT-4) is called and generates medical record information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." The generated medical record is saved for use in the next step.

[1279] Step 4:

[1280] The server uses the same generation API to generate explanatory text for the user in easy-to-understand language and a character-like tone. The input data for this is composed of the generated medical record information and existing templates, and an explanatory text such as "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?" is generated. This explanatory text is also used in subsequent processing.

[1281] Step 5:

[1282] The device analyzes physiological data such as the user's facial expressions and voice in real time and recognizes the user's emotions using an emotion engine. For example, an emotion engine (such as OpenFace or IBM Watson Emotion Analysis) can be used to determine whether the user is feeling stressed while performing input operations. This emotion data is collected as "the user is feeling stressed" and sent to the server.

[1283] Step 6:

[1284] The server adjusts the tone and content of the description based on the recognized emotion data. Here, the emotion data is used as input and processing is performed to change the tone of the existing description. Specifically, the generative AI model is given a prompt such as "Generate a gentler description for users who are feeling stressed," and a description with an adjusted tone is obtained.

[1285] Step 7:

[1286] The server sends the generated medical record along with the adjusted explanation to the terminal. This information is sent in the form of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1287] Step 8:

[1288] The terminal displays the medical record sent from the server and the adjusted explanation to the user. On the terminal screen, "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed, and the user confirms them.

[1289] Step 9:

[1290] The user can then review the suggested meal menu based on the displayed content and select the most suitable option, thereby providing a personalized meal menu that is tailored to the user's physical condition and emotions.

[1291] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1292] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1293] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1294] [Fourth embodiment]

[1295] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1296] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1297] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1298] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1299] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1300] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1301] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1302] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1303] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1304] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1305] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1306] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1307] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1308] The proposed system is designed to improve communication between patients and doctors in medical settings and includes the following features:

[1309] Enter a brief description of your symptoms and their severity

[1310] The user uses an input form on the terminal to input a brief description of the symptoms and their severity.

[1311] Example: "User types 'My stomach hurts' and selects pain intensity as 8 / 10"

[1312] Sending data to the server

[1313] The terminal transmits the symptom data collected from the user to the server.

[1314] Example: "The device sends the summarized data, 'Symptom: stomachache, Severity: 8 / 10', to the server."

[1315] Generate medical records using the generation API

[1316] The server calls the generation API based on the data received and automatically generates the medical record.

[1317] Example: "The server uses the generation API to generate a medical record stating, 'The patient complains of abdominal pain, and the pain intensity is 8 / 10.'"

[1318] Generating descriptions using the generation API

[1319] The server also uses the generation API to generate explanatory text for patients using easy-to-understand language and a character-like tone of voice.

[1320] Example: "The server generates the description 'Your stomach feels all fuzzy and painful. Does it feel like a little hedgehog is moving around inside you?'"

[1321] Display on the device

[1322] The server sends the generated medical record and explanation to the terminal.

[1323] The terminal displays the received data to the user.

[1324] Example: "The device displays to the user: 'Patient report: Patient complains of abdominal pain, pain intensity 8 / 10' and 'Explanation: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?'"

[1325] Program processing description

[1326] The program is expected to operate as follows:

[1327] 1. Enter symptoms

[1328] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[1329] 2. Data Transmission

[1330] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[1331] 3. Medical record generation

[1332] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record will state that "the patient complains of abdominal pain, and the pain intensity is 8 / 10."

[1333] 4. Description Generation

[1334] The server uses the same generation API to generate patient-friendly descriptions in language and character-like voice, such as "You're feeling a tingly, painful sensation in your stomach. Does it feel like a little hedgehog is moving around inside you?"

[1335] 5.Display

[1336] The server sends the generated chart and explanation to the terminal, which displays them to the user. "Chart: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed on the terminal.

[1337] Specific examples

[1338] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[1339] User input: "My head hurts," pain intensity "7 / 10"

[1340] Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[1341] Chart generation: "Patient complains of headache, pain intensity 7 / 10"

[1342] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[1343] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[1344] This will enable patients to more accurately describe their symptoms and make it easier for them to understand explanations from doctors, leading to more appropriate diagnoses and treatment.

[1345] The processing flow will be explained below.

[1346] Step 1:

[1347] A user uses a form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user might enter "I have a stomachache" and rate the pain intensity as 8 / 10.

[1348] Step 2:

[1349] The terminal collects data entered by the user, which is organized as "Symptom: stomachache, Severity: 8 / 10."

[1350] Step 3:

[1351] The terminal sends the collected data to the server. Specifically, the organized data is converted into a data structure that can be sent to the server.

[1352] Step 4:

[1353] The server receives the data sent from the device, checks the received data, and verifies its accuracy.

[1354] Step 5:

[1355] Based on the data received by the server, the symptom description and severity data are sent to the generation API, and a request to generate a medical record is sent.

[1356] Step 6:

[1357] The generation API processes the request and automatically generates a medical record based on the input data. Specifically, it generates a medical record with the content, such as, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[1358] Step 7:

[1359] The generation API returns the generated medical record to the server, which includes the text data of the medical record.

[1360] Step 8:

[1361] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[1362] Step 9:

[1363] The generation API receives the request and generates a description using language and a character voice that is easy for the patient to understand, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1364] Step 10:

[1365] The generation API returns the generated description to the server, which includes the text data of the description.

[1366] Step 11:

[1367] The server receives the description returned from the generation API and combines the data with the medical records received previously.

[1368] Step 12:

[1369] The server sends the compiled data to the terminal, which includes the generated medical record and explanation.

[1370] Step 13:

[1371] The terminal displays the data received from the server. Specifically, it displays to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1372] The above steps allow users to accurately input their symptoms, generate a medical record in a format that is easy for doctors to understand, and provide explanations that are easy for patients to understand, facilitating smooth communication in the medical field.

[1373] Example 1

[1374] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1375] In medical settings, it can be difficult for patients to accurately communicate their symptoms to medical staff, and it can also be difficult for medical staff to explain things to patients in an easy-to-understand manner. This can lead to insufficient communication between patients and medical staff, which can affect the appropriateness of diagnosis and treatment.

[1376] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1377] In this invention, the server includes: a means for a user to input a description and severity of symptoms using a medical terminal; a means for transmitting the input description and severity of symptoms in data format to the server; a means for the server to automatically generate a medical record using a generative AI model based on the received data; a means for the server to generate an explanation for the patient using the generative AI model based on the generated medical record; and a means for the server to transmit the generated medical record and explanation to the terminal and for the terminal to display them. This allows patients to accurately input their symptoms and reliably communicate them to medical staff through the generated medical record and explanation. Furthermore, medical staff can provide explanations to patients in an easy-to-understand manner, improving the appropriateness of diagnosis and treatment.

[1378] "User" refers to a person who uses a medical terminal to input their symptoms and their severity.

[1379] "Medical device" refers to an electronic device, such as a smartphone, tablet, or computer, that a user uses to input a description and severity of their symptoms.

[1380] "Symptom description" refers to a verbal description of the physical or mental abnormality or discomfort the user is experiencing.

[1381] "Degree" refers to the strength or severity of symptoms expressed numerically or verbally.

[1382] "Data format" refers to the structured information format (e.g., JSON or XML) used to transmit the symptom description and severity to the server.

[1383] "Server" refers to the central processing unit that receives data sent by users and generates medical records and explanatory text using generative AI models.

[1384] A "generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate medical records and explanatory text based on input data.

[1385] A "medical record" refers to a document that serves as a medical record and is generated based on the symptoms and their severity entered by the user.

[1386] "Explanatory text" refers to a document generated using a generative AI model to explain symptoms in an easy-to-understand manner for patients.

[1387] "Terminal" refers to a medical terminal operated by a user, which displays the products (medical records and explanatory text) sent from the server.

[1388] This invention is a system designed to improve communication between patients and doctors in medical settings. The system consists of a user, a terminal, and a server, and uses a generative AI model to automatically generate medical records and explanations.

[1389] First, the user uses a medical device (smartphone, tablet, PC, etc.) to enter a description of their symptoms and their severity. The user enters detailed symptoms (e.g., "My stomach hurts") into the application's input form and selects the intensity or level of pain (e.g., 8 / 10) using a slider bar or drop-down menu.

[1390] Next, the terminal sends this input data to the server in a data format (e.g., JSON). Specifically, the terminal uses the HTTPS protocol over an Internet connection to send the input data as a POST request to the server's endpoint.

[1391] The server automatically generates a medical record using a generative AI model (e.g., GPT-3) based on the received data. During the generation process, the server sends a prompt to the generative AI model. This prompt is, "Please describe the patient's symptoms and severity in medical record format." Based on this prompt, the generative AI model generates a medical record such as, "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[1392] The server also uses the generative AI model to generate easy-to-understand explanations for patients. The prompt is, "Please explain the patient's symptoms in kind words and in a character-like tone." An example of a generated explanation is, "Your stomach feels all tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1393] The server sends the generated medical record and explanation to the terminal. The terminal receives this and displays it as specific information for the user. The displayed information is in the form of "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1394] Specific examples

[1395] For example, if a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process goes through the following steps:

[1396] 1. User input: "I have a headache," pain intensity "7 / 10"

[1397] A user enters "I have a headache" into an application form and sets the pain intensity to 7 using the slider.

[1398] 2. Terminal transmission: "Symptom: Headache, Severity: 7 / 10"

[1399] The terminal sends the input data to the server in JSON format.

[1400] 3. Medical record generation

[1401] The server sends a prompt to the generating AI model saying, "Please describe the patient's symptoms and severity in a medical record format," and generates a medical record stating, "The patient complains of a headache, and the pain intensity is 7 / 10."

[1402] 4. Description Generation

[1403] The server sends a prompt to the generative AI model, asking it to "describe the symptoms the patient reported in kind words or in a character-like tone," and generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[1404] 5.Display

[1405] The server sends the generated medical record and explanation to the terminal, which displays it on the screen.

[1406] In this way, patients can accurately record their symptoms and communicate them to medical staff in an understandable manner, improving the quality of diagnosis and treatment.

[1407] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1408] Step 1: User symptom input

[1409] The user uses a medical device to input symptoms and their severity. The user enters symptoms such as "my stomach hurts" into the application's input form and sets the pain intensity to, for example, 8 / 10 using a slider bar or drop-down menu. The input data is stored in the device in text format.

[1410] Input: User-entered symptoms and their severity (e.g., "My stomach hurts" with severity "8 / 10").

[1411] Output: Temporarily saved as structured data (e.g. JSON).

[1412] Step 2: Send data

[1413] The device sends the entered data to the server. The device sends the data as a POST request to the server endpoint using the HTTPS protocol via an internet connection.

[1414] Input: JSON data containing symptoms and their severity entered by the user into the device (e.g., "Symptom: stomachache, Severity: 8 / 10").

[1415] Output: JSON formatted data sent to the server.

[1416] Step 3: Create a medical record

[1417] Based on the data received by the server, a medical record is automatically generated using a generative AI model. The server sends a prompt to the generative AI model, saying, "Please describe the patient's symptoms and severity in medical record format," and retrieves the generated medical record.

[1418] Input: Symptom and severity data received by the server (e.g., "Symptom: stomachache, Severity: 8 / 10").

[1419] Data processing: The generative AI model is invoked using a prompt ("Please describe the patient's symptoms and severity in medical record format").

[1420] Output: An automatically generated medical record (e.g., "The patient complains of abdominal pain, pain intensity is 8 / 10").

[1421] Step 4: Description generation

[1422] The server uses the same generative AI model to generate a patient-oriented explanation. The server sends a prompt, "Please explain the patient's symptoms in a gentle and character-like tone," and retrieves the generated explanation.

[1423] Input: The prompt and medical record contents to be sent to the generative AI model (e.g., "Symptoms: stomachache, Severity: 8 / 10").

[1424] Data processing: The generative AI model is invoked using a prompt ("Please explain the symptoms the patient reported in kind words and in a character-like voice").

[1425] Output: An automatically generated description (e.g. "Your stomach feels all fuzzy and painful. Does it feel like there's a little hedgehog thrashing around inside you?").

[1426] Step 5: View the medical record and explanation

[1427] The server sends the generated chart and explanation to the terminal, which receives it and displays it to the user. The terminal application analyzes the received data and displays it on the screen.

[1428] Input: Medical record and description data sent from the server (e.g., "Medical record: Patient complains of abdominal pain, pain intensity 8 / 10"; "Description: You're feeling a tingly, painful feeling in your stomach. Does it feel like there's a little hedgehog moving around inside you?").

[1429] Output: Information displayed on the device screen.

[1430] In this way, users can easily record their own symptoms, and the server can provide automatically generated medical records and explanations based on this information, facilitating smooth communication between medical staff and patients.

[1431] (Application example 1)

[1432] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1433] In today's food delivery services, it is difficult for users to accurately communicate their preferences and allergy information. Existing systems limit the ways in which users can specify their requests in detail, which can lead to ordering errors or inappropriate menu suggestions. Furthermore, explanations to users are often difficult to understand, making it difficult for them to understand complex information. To solve this problem, a system is needed that allows users to easily input their preferences and allergy information, automatically suggests optimal menus based on that information, and provides easy-to-understand explanations.

[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1435] In this invention, the server includes means for inputting a simple explanation of preference information and allergy information, means for transmitting the input preference information and allergy information to the server, means for automatically generating a suggested menu using a generation API based on the received data, means for generating an explanation of the generated suggested menu in easy-to-understand language for the user, and means for transmitting the generated suggested menu and explanation to the terminal and displaying it. This enables users to receive the optimal menu tailored to their preferences and allergies, reduces ordering errors, and provides easy-to-understand explanations.

[1436] The "brief description of preference information" is information about the types of food and seasonings that the user likes.

[1437] "Allergy information" is information about ingredients or substances to which the user is allergic.

[1438] "Input means" refers to a device or software that provides an interface for users to input preference information and allergy information.

[1439] The "means for automatically generating a suggested menu using a generation API" is a method that uses an application programming interface to automatically generate an optimal menu based on the user's preference information and allergy information.

[1440] The "means for generating explanatory text in easy-to-understand language for users" is a method for explaining information about the generated suggested menu in simple language that is easy for users to understand.

[1441] The "means for transmitting to the terminal and displaying" is a method for transmitting the generated suggested menu and explanatory text to the user's terminal and displaying them.

[1442] The embodiments of the present invention will be described below.

[1443] The system for realizing the invention provides a means for users to input a simple description of their preferences and allergy information. This means utilizes a smartphone application. The user inputs their preferences and allergy information using the application. For example, they can input information such as "I like spicy food" or "I'm allergic to nuts."

[1444] The smartphone sends the input preference and allergy information to the server. The server uses a generation API based on the received data to automatically generate a suggested menu that suits the user's preferences and allergies. The generated suggested menu is provided using a generative AI model.

[1445] Next, the server generates an easy-to-understand explanation for the user based on the generated suggested menu. For example, for the menu item "Spicy Tandoori Chicken, Nut-Free," it generates an explanation such as "It's spicy, but it's nut-free, so you can eat it with peace of mind." This explanation is also generated using the generation API.

[1446] Finally, the server sends the generated menu suggestions and explanations to the smartphone, which then displays them to the user, allowing the user to easily check the most suitable menu based on their preferences and allergy information and place their order with confidence.

[1447] The hardware used includes smartphones and servers, and the software used for generation includes a generation API, such as OpenAI's Generative Model API.

[1448] For example, if a user enters "I like spicy food" and specifies "I have a nut allergy," the process will proceed as follows:

[1449] User input: "I like spicy food", allergy information: "nuts"

[1450] Send to device: "Preferences: spicy, Allergies: nuts"

[1451] Generate suggested menu: "Spicy tandoori chicken, nut-free"

[1452] Description generation: "It's spicy, but nut-free so you can eat it with peace of mind."

[1453] Display: "Menu: Spicy Tandoori Chicken, Nut-Free" and "Description: It's spicy, but it's nut-free so you can eat it with peace of mind" will be displayed on your smartphone.

[1454] In this way, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information. This process is achieved by inputting a prompt message to the generation API, such as, "If the user likes spicy food and has a nut allergy, please generate the optimal menu suggestion and corresponding explanation."

[1455] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1456] Step 1:

[1457] A user enters preference information and allergy information using a smartphone application. Specifically, the user enters "I like spicy food" and selects "I'm allergic to nuts" in the application's input form.

[1458] Input: User preference information (e.g., I like spicy food), allergy information (e.g., I'm allergic to nuts)

[1459] Output: The input information is saved in the application

[1460] Step 2:

[1461] The smartphone sends the user's preference and allergy information to the server, which then formats the data appropriately and sends it to the server.

[1462] Input: Saved input information (preference information, allergy information)

[1463] Output: Formatted data is sent to the server

[1464] Step 3:

[1465] The server calls the generation API based on the received data and automatically generates a menu suggestion. Here, a specific generation AI model is used to analyze the user's input data and generate the optimal menu that meets the conditions.

[1466] Input: Preference and allergy information received by the server

[1467] Output: Generated menu suggestions (e.g. spicy tandoori chicken, nut-free)

[1468] Step 4:

[1469] The server generates a user-friendly description of the proposed menu based on the generated menu suggestion. It uses the generation API again to create a simple and friendly description of the proposed menu.

[1470] Input: Generated suggestion menu

[1471] Output: Generated description (e.g., "It's spicy, but it's nut-free so you can eat it with peace of mind")

[1472] Step 5:

[1473] The server sends the generated suggestion menu and explanation to the smartphone, which then prepares to display this information to the user.

[1474] Input: Generated suggestion menu and description

[1475] Output: Suggested menu and explanations are sent to your smartphone.

[1476] Step 6:

[1477] The smartphone displays the received suggested menu and description to the user, who can then check the suggested menu and description on the screen and decide whether to order.

[1478] Input: Received suggestion menu and description

[1479] Output: A suggestion menu and explanations are displayed on the smartphone screen.

[1480] Through the above steps, the system of the invention allows users to easily receive optimal menu suggestions based on their preferences and allergy information.

[1481] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1482] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The system includes the following features:

[1483] Enter a brief description of your symptoms and their severity

[1484] A user uses an input form on a medical device to briefly describe their symptoms and select a symptom severity (e.g., a scale of 1 to 10). For example, a user enters "I have a stomachache" and sets the pain intensity as 8 / 10.

[1485] Sending data to the server

[1486] The device sends the data collected from the user to the server, which includes information organized in the format "Symptom: stomachache, Severity: 8 / 10."

[1487] Generate medical records using the generation API

[1488] Based on the data received by the server, the generation API is called and a medical record is automatically generated. The generated medical record includes the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[1489] Generating descriptions using the generation API

[1490] The server also uses the generation API to generate explanations in patient-friendly language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1491] Emotion Recognition Using Emotion Engine

[1492] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize the user's emotions. For example, the emotion engine determines that the user is feeling stressed while typing.

[1493] Emotion data sent to server

[1494] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[1495] Adjusting the tone and content of your descriptions

[1496] Based on the emotion data received by the server, the server sends a request to the generation API to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates a gentler explanation.

[1497] Display on the device

[1498] The server sends the compiled data to the device, which includes the generated medical record and an explanation adjusted based on the user's emotions.

[1499] The device displays this information to the user, specifically, "Medical record: Patient complains of stomach pain, pain intensity 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1500] Specific explanation of program processing

[1501] The program is expected to operate as follows:

[1502] 1. Enter symptoms

[1503] The user uses the medical device to input a description and severity of the symptom. For example, the user may input "my stomach hurts" and set the pain intensity as 8 / 10.

[1504] 2. Data Transmission

[1505] The device sends this data to the server in the format "Symptom: stomachache, Severity: 8 / 10".

[1506] 3. Medical record generation

[1507] Based on the data received by the server, the generation API is called and a medical record is automatically generated. For example, it might state, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[1508] 4. Description Generation

[1509] The server uses the same generation API to generate patient-friendly descriptions in a character-like voice, such as, "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside you?"

[1510] 5. Emotion recognition

[1511] The device's emotion engine recognizes the user's emotions in real time. For example, the emotion engine recognizes when the user is feeling stressed.

[1512] 6. Emotional Data Transmission

[1513] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[1514] 7. Adjustments to the description

[1515] The server sends a request to the generation API based on the emotion data and adjusts the tone and content of the explanation. For example, if the user is feeling stressed, the explanation will be generated in a gentler tone.

[1516] 8. Display

[1517] The server sends the compiled data to the terminal, which displays it to the user. The medical record reads, "Patient complains of stomach pain, pain intensity 8 / 10," along with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1518] Specific examples

[1519] Symptom input: The user enters "I have a headache" and sets the pain intensity as 7 / 10.

[1520] Chart generation: "Patient complains of headache, pain intensity 7 / 10"

[1521] Description generation: "My head is throbbing. Does it feel like there's a ghost popping in my head?"

[1522] Emotion recognition: The emotion engine recognizes when a user is nervous.

[1523] Adjust the instructions: The user is nervous, so adjust the instructions to make them more relaxed.

[1524] Display: "Patient report: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Feels like a ghost is popping in my head?" will be displayed on the device.

[1525] In this way, this system, which combines an emotion engine, allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides easy-to-understand explanations that correspond to the patient's emotional state, further improving communication in medical settings.

[1526] The processing flow will be explained below.

[1527] The present invention is a system designed to improve communication between patients and doctors in medical settings, and includes an emotion engine that recognizes the user's emotions, enabling more personalized communication. The specific processing flow of this system is described below.

[1528] Step 1:

[1529] The user uses the input form on the medical device to briefly describe their symptoms and select the severity of the symptoms. For example, the user enters "My stomach hurts" and sets the pain intensity as 8 / 10.

[1530] Step 2:

[1531] The device sends the collected symptom data to the server, which organizes the data in the format "Symptom: stomachache, Severity: 8 / 10."

[1532] Step 3:

[1533] The server receives the data sent from the device, verifies its accuracy, and then calls the generation API to automatically generate the medical record.

[1534] Step 4:

[1535] The generation API generates a medical record based on the input data and sends it back to the server. The medical record contains the content, "The patient complains of stomach pain, and the pain intensity is 8 / 10."

[1536] Step 5:

[1537] The server receives the medical record returned from the generation API and then sends a request to the generation API to generate an explanation for the patient.

[1538] Step 6:

[1539] The generation API generates a description using words and a character tone that the patient can easily understand, and sends it back to the server. For example, a description such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1540] Step 7:

[1541] The device's built-in emotion engine analyzes the user's facial expressions, voice, and other physiological data in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[1542] Step 8:

[1543] The device sends the recognized emotion data to the server, which includes information that the user is feeling stressed.

[1544] Step 9:

[1545] The server sends a request to the generation API to adjust the tone and content of the generated description based on the received emotional data. For example, if the user is feeling stressed, the description will be generated in a gentler tone.

[1546] Step 10:

[1547] The generation API generates the adjusted description and sends it back to the server.

[1548] Step 11:

[1549] The server compiles the adjusted explanation and the previously generated medical record and sends it to the terminal.

[1550] Step 12:

[1551] The terminal displays the data received from the server to the user in the format of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1552] Specific examples

[1553] If a user types "I have a headache" into a medical device and sets the pain intensity to 7 / 10, the process will proceed as follows:

[1554] Step 1: User types "I have a headache" and sets pain intensity to 7 / 10.

[1555] Step 2: The device sends the organized data, "Symptom: headache, Severity: 7 / 10", to the server.

[1556] Step 3: The server receives the data and sends it to the generation API.

[1557] Step 4: The generation API generates a medical record stating that "the patient complains of a headache and the pain intensity is 7 / 10" and sends it back to the server.

[1558] Step 5: The server receives the medical record and sends a request to the generation API to generate a description.

[1559] Step 6: The generation API generates a description such as "My head is throbbing. Does it feel like there's a ghost popping in my head?" and sends it back to the server.

[1560] Step 7: The emotion engine recognizes the user's tension.

[1561] Step 8: Send the emotion data "user is nervous" to the server.

[1562] Step 9: The server requests the generation API to generate a description of the relaxing content.

[1563] Step 10: The generation API generates the adjusted description and sends it back to the server.

[1564] Step 11: The server sends the adjusted explanation and medical record together to the terminal.

[1565] Step 12: The terminal displays "Chart: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Do I feel like there are ghosts popping in my head?"

[1566] In this way, this system allows patients to accurately input their symptoms, generates medical records in a format that is easy for doctors to understand, and provides explanations that reflect the patient's emotional state, facilitating smooth communication in medical settings.

[1567] Example 2

[1568] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1569] In modern medical settings, it is often pointed out that communication between patients and doctors is not smooth. In particular, it is often difficult for patients to accurately communicate their symptoms, and the patient's emotional state is often not taken into consideration. As a result, doctors are unable to make appropriate diagnoses or provide appropriate treatment, leading to a decline in patient satisfaction.

[1570] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a brief description of symptoms and the severity of the symptoms using an input form; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generative AI model based on the received data; means for generating an explanation for the generated medical record using a generation API in easy-to-understand words and a character's tone of voice for the patient; means for recognizing the user's emotions in real time using an emotion engine built into the terminal; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation using the generative AI model based on the emotion data; and means for transmitting the generated medical record and the adjusted explanation to the terminal and displaying them. This not only allows patients to accurately input their symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides easy-to-understand explanations that correspond to the patient's emotional state, thereby improving communication in medical settings.

[1571] The "input form" is an interface that allows the user to input a description and severity of the symptoms.

[1572] The "server" is a computer system that receives data entered by the user, generates medical records and explanatory text using a generative AI model, and sends them to the terminal.

[1573] A "generative AI model" is an artificial intelligence model that automatically generates medical records and explanatory text based on the data it receives.

[1574] A medical record is a document that organizes information such as the symptoms a patient complains of and their severity, and is used by doctors to make diagnoses.

[1575] A "generation API" is a program interface for sending data to a generative AI model and generating medical records, explanatory text, etc.

[1576] The "explanation" is a sentence that explains the contents of the generated medical record to the patient in an easy-to-understand manner.

[1577] The "emotion engine" is a system that recognizes emotions in real time from physiological data such as a user's facial expressions, voice, and heart rate.

[1578] "Tone" refers to the emotional expression and tone of the content of an explanation or other text.

[1579] A "terminal" is a device that allows a user to input data and display generated charts and explanations.

[1580] "Emotion data" is information about the user's emotional state as recognized by the emotion engine.

[1581] This invention is a system designed to improve communication between patients and doctors in medical settings. The system inputs a user's symptoms, automatically generates medical records and explanations using a generative AI model, and also includes the ability to recognize and respond to the user's emotions in real time.

[1582] Hardware and software used

[1583] Hardware:

[1584] Terminal: A device (e.g., personal computer, tablet, smartphone, etc.) used to enter user data and display the generated chart and narrative.

[1585] Server: A computer system that processes and calculates the received data and generates medical records and explanatory text using a generative AI model.

[1586] software:

[1587] Generative AI model: For example, OpenAI's GPT-3 is used to analyze data on the server and generate medical records and explanatory text.

[1588] Generative API: A program interface that sends input data to a generative AI model and receives the generated medical records and descriptions.

[1589] Emotion engine: Software that analyzes physiological data such as a user's facial expressions, voice, and heart rate in real time to recognize emotions (e.g., Emotion Recognition API).

[1590] Specific Embodiments of the System

[1591] 1. Symptom input:

[1592] The user inputs their symptoms using the device. For example, the user might input "my stomach hurts" and rate the pain intensity as 8 / 10. This data is then used as an input form on the device using a JavaScript framework such as React or Vue.js.

[1593] 2. Data transmission:

[1594] The device sends the entered symptom and severity data to the server. The data is organized in JSON format and sent in a format such as {"Symptoms": "Stomachache", "Severity": 8}. This process uses HTTP request libraries such as fetch and axios.

[1595] 3. Medical record generation:

[1596] The server analyzes the received data and calls the generative AI model to automatically generate a medical record. The generated medical record will state that "the patient complains of stomach pain, and the pain intensity is 8 / 10." The data is sent using the generation API, and the generated medical record is received.

[1597] 4. Description generation:

[1598] The server uses the same generative AI model to generate explanatory text in patient-friendly language and a character-like tone, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside you?"

[1599] 5. Emotion recognition:

[1600] The device's built-in emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize the user's emotional state. For example, the emotion engine may determine that the user is feeling stressed while typing.

[1601] 6. Emotional Data Transmission:

[1602] The device organizes the recognized emotion data and sends it to the server. The data sent includes information that the user is feeling stressed. The emotion data is also sent in JSON format.

[1603] 7. Description adjustments:

[1604] Based on the emotion data received by the server, the API sends a request to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the API generates a gentler explanation.

[1605] 8. Display:

[1606] The server sends the generated medical record and the adjusted explanation to the terminal, and the terminal displays this information to the user.Specific examples of the information provided include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1607] Specific examples

[1608] Symptom entry example

[1609] A user types in "I have a headache" and sets the pain intensity to 7 / 10.

[1610] Example of medical record generation

[1611] "The patient complains of a headache and the pain intensity is 7 / 10."

[1612] Example of description generation

[1613] "My head is throbbing. Does it feel like ghosts are snapping around in my head?"

[1614] Emotion Recognition Example

[1615] The emotion engine recognizes that the user is nervous.

[1616] Example of adjusting the description

[1617] The user is nervous, so adjust the instructions to make them more relaxed.

[1618] Display example

[1619] The device displays "Medical record: Patient complains of headache, pain intensity 7 / 10" and "Description: My head is throbbing. Does it feel like there's a ghost popping in my head?"

[1620] In this way, this system not only accurately inputs the user's symptoms and generates a medical record in a format that is easy for doctors to understand, but also provides explanations that correspond to the user's emotional state, thereby improving communication in the medical field.

[1621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1622] Step 1:

[1623] The user accesses the input form on the medical device and enters their symptoms. For example, the user enters "my stomach hurts" and sets the pain intensity to 8 / 10. The input data is saved in text format on the device. This process uses a user interface (e.g., React or Vue.js).

[1624] Input: The user enters the text "My stomach hurts" and sets the pain level to 8.

[1625] Output: JSON data: {"Symptom": "Stomachache", "Pain level": 8}.

[1626] Action: A user accesses a form, enters "My stomach hurts" into the form field, and uses the slider to set the pain intensity to 8.

[1627] Step 2:

[1628] The device sends the user input data to the server using an HTTP POST request, with the data sent in JSON format. Specifically, an HTTP library such as fetch or axios is used.

[1629] Input: JSON data entered by the user: {"Symptom": "Stomachache", "Pain level": 8}

[1630] Output: The data sent to the server.

[1631] Specific operation: The device uses fetch to create an HTTP POST request and send data to the server.

[1632] Step 3:

[1633] The server analyzes the received data and sends it as prompts to a generative AI model, which is used to generate a medical record. The generative AI model uses, for example, GPT-3.

[1634] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[1635] Output: Text data from the medical record: "The patient complains of abdominal pain, and the pain intensity is 8 / 10."

[1636] Specific operation: The server executes a script written in Python, uses the requests library to send a prompt to the generation API, and saves the returned text as a medical record.

[1637] Step 4:

[1638] The server uses the same generative AI model to generate a prompt, which includes the symptom and severity information entered by the user.

[1639] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8}

[1640] Output: Description: "Your stomach feels all tingly and painful. It feels like there's a little hedgehog thrashing around inside you."

[1641] Specific operation: The server calls the generation API again, sends the input data as a prompt, and saves the returned explanation.

[1642] Step 5:

[1643] The device's emotion engine analyzes the user's facial expressions, voice, heart rate, etc. in real time to recognize their emotions. For example, the emotion engine can determine that the user is feeling stressed while typing.

[1644] Input: Real-time video and audio data from the user.

[1645] Output: Emotion data "feeling stressed."

[1646] What it does: The device collects data using the user's webcam and microphone, and analyzes emotions using the Emotion Recognition API.

[1647] Step 6:

[1648] The device organizes the recognized emotion data and sends it to the server. The data is sent in JSON format, for example, {"emotion": "stress"}.

[1649] Input: Emotional data of "feeling stressed."

[1650] Output: JSON of emotion data sent to the server.

[1651] Specific operation: The device uses fetch to create an HTTP POST request and send emotion data to the server.

[1652] Step 7:

[1653] The server sends a request to the generative AI model based on the emotional data to adjust the tone and content of the explanation. Specifically, if the user is feeling stressed, it will generate a gentler explanation.

[1654] Input: JSON data: {"Symptom": "Stomachache", "Pain level": 8} and {"Emotion": "Stress"}.

[1655] Output: A gentle description: "Your stomach feels all tingly and painful. Does it feel like there's a little hedgehog thrashing around inside you?"

[1656] Specific operation: The server generates a prompt including emotion data, sends a request to the generation API, and saves the adjusted explanation that is returned.

[1657] Step 8:

[1658] The server sends the generated medical record and the adjusted explanation to the terminal, which displays them to the user. The medical record and explanation are formatted in HTML format and displayed in the user interface.

[1659] Input: Text data: "The patient complains of stomach pain, pain intensity is 8 / 10" and "Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1660] Output: Medical record and explanation displayed on the terminal screen.

[1661] Specific operation: The terminal formats the data received from the server in HTML format and displays it on the screen. Specifically, the medical record displayed is, "The patient complains of stomach pain, and the pain intensity is 8 / 10," with the explanation, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1662] (Application example 2)

[1663] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1664] Conventional food delivery services have had difficulty providing meal menus that correspond to the user's physical and emotional state. This has led to problems such as not being able to suggest appropriate meals when the user is feeling unwell, or not being able to provide services that are sensitive to the user's emotions. In particular, there is a need for services that suggest optimal meals and provide consideration to ease the user's emotions when the user is feeling unwell or stressed.

[1665] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a brief description of symptoms and the severity of the symptoms; means for transmitting the input description and severity of the symptoms to the server; means for automatically generating a medical record using a generation API based on the received data; means for generating an explanation of the generated medical record for the user in easy-to-understand words or a character's tone of voice; means having an emotion engine that recognizes the user's emotions in real time; means for transmitting the recognized emotion data to the server; means for adjusting the tone and content of the explanation based on the emotion data received by the server; and means for transmitting the generated medical record and the explanation adjusted based on the emotion data to the terminal and displaying it. This makes it possible to propose a personalized meal menu based on the user's physical condition and emotions, and to provide a service that takes emotions into consideration.

[1666] "Brief explanation of symptoms" is information in which the user briefly describes their own physical condition or illness.

[1667] "Symptom severity" is information that indicates the strength or degree of the symptoms felt by the user using a numerical value or a scale.

[1668] "Generation API" means an application programming interface for automatically generating information based on input data.

[1669] A "medical record" is a detailed record of a patient's or user's physical condition and symptoms, and is a document containing information useful for providing medical care and services.

[1670] "Character tone" refers to the way a character speaks and expresses themselves, with the aim of conveying information in a user-friendly and engaging format.

[1671] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and other physiological data to recognize their emotional state in real time.

[1672] "Emotion data" is information that indicates the emotional state of the user recognized by the emotion engine.

[1673] "Means to adjust the tone and content of descriptions" refers to a function that changes the way information is expressed and worded based on emotional data.

[1674] A "terminal" is a device that allows a user to use the system and is capable of inputting and displaying data.

[1675] This invention provides a system for suggesting personalized meal menus and providing emotionally sensitive service in a food delivery service. The system includes the following main means.

[1676] 1. How to enter a brief description of your symptoms and their severity:

[1677] It is a means for users to briefly describe their physical condition or discomfort and input numerical values ​​to indicate the strength and degree of the condition. For example, a user can input a symptom such as "my stomach hurts" and the degree of the pain.

[1678] 2. Means of data transmission:

[1679] This is a means to send the entered symptom description and severity to the server. In this example, the information entered by the user is sent to the server in the format "Stomachache, severity: 8 / 10".

[1680] 3. Automatic generation of medical records using the generation API:

[1681] The server calls a generation API based on the received data and automatically generates a medical record. This medical record contains information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." A possible generation API would be the "OpenAI API" using the "GPT-4" model.

[1682] 4. How to generate a description using the generation API:

[1683] The server uses the generation API to generate explanatory text for patients in easy-to-understand language and character-like voice, such as, "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?"

[1684] 5. Emotion recognition using emotion engine:

[1685] The device is equipped with an emotion engine that analyzes physiological data such as the user's facial expressions and voice in real time to recognize the user's emotions. Possible software for emotion recognition includes "OpenFace" and "IBM Watson Emotion Analysis."

[1686] 6. Means of sending emotional data:

[1687] This is a means for transmitting the recognized emotion data to the server. The transmitted data includes, for example, information that "the user is feeling stressed."

[1688] 7. Adjust the tone and content of your description:

[1689] The server sends a request to the generation API based on the received emotional data to adjust the tone and content of the explanation. For example, if the user is feeling stressed, the server generates an explanation in a gentler tone.

[1690] 8. Display of generated medical records and explanations:

[1691] This is a means of sending and displaying a medical record generated by the server and an explanation adjusted based on emotion data to the terminal. Examples of displayed content include "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1692] Examples:

[1693] When a user enters the symptom "stomach ache" and rates the pain intensity as 8 / 10 through a food delivery application, this information is sent to the server. The server then uses a generation API to automatically generate a medical record and suggests a meal menu suitable for the user. If the emotion engine recognizes that the user is feeling stressed, it adjusts the tone of the explanation to a gentler one and displays it to the user along with a relaxing menu.

[1694] Example prompt sentence:

[1695] "Please suggest a meal plan for a user who is experiencing stomach pain. The pain level is 8 / 10 and the user is currently feeling stressed. Please suggest a meal that is easy to digest and explain it to them in a gentle tone."

[1696] Such a system would enable the provision of personalized meal menus and appropriate services according to the user's physical condition and emotions.

[1697] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1698] Step 1:

[1699] A user launches a food delivery application and inputs information about their health condition and emotions. Specifically, they input their physical condition and symptoms (e.g., "I have a stomachache") and their severity (on a scale of 1 to 10). This input data is prepared as transmission data in the format "Symptom: stomachache, Severity: 8 / 10."

[1700] Step 2:

[1701] The device sends the data entered by the user to the server. The input data includes information on symptoms and symptom severity, and is received as "Symptoms: stomachache, Severity: 8 / 10" when sent to the server. This data is stored on the server for subsequent processing.

[1702] Step 3:

[1703] The server calls a generation API based on the received data and automatically generates a medical record. At this stage, a generative AI model (for example, an API using GPT-4) is called and generates medical record information such as "The patient complains of stomach pain, and the pain intensity is 8 / 10." The generated medical record is saved for use in the next step.

[1704] Step 4:

[1705] The server uses the same generation API to generate explanatory text for the user in easy-to-understand language and a character-like tone. The input data for this is composed of the generated medical record information and existing templates, and an explanatory text such as "Your stomach feels tingly and painful, doesn't it? Does it feel like a little hedgehog is moving around inside your stomach?" is generated. This explanatory text is also used in subsequent processing.

[1706] Step 5:

[1707] The device analyzes physiological data such as the user's facial expressions and voice in real time and recognizes the user's emotions using an emotion engine. For example, an emotion engine (such as OpenFace or IBM Watson Emotion Analysis) can be used to determine whether the user is feeling stressed while performing input operations. This emotion data is collected as "the user is feeling stressed" and sent to the server.

[1708] Step 6:

[1709] The server adjusts the tone and content of the description based on the recognized emotion data. Here, the emotion data is used as input and processing is performed to change the tone of the existing description. Specifically, the generative AI model is given a prompt such as "Generate a gentler description for users who are feeling stressed," and a description with an adjusted tone is obtained.

[1710] Step 7:

[1711] The server sends the generated medical record along with the adjusted explanation to the terminal. This information is sent in the form of "Medical record: Patient complains of stomach pain, pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?"

[1712] Step 8:

[1713] The terminal displays the medical record sent from the server and the adjusted explanation to the user. On the terminal screen, "Medical record: The patient complains of stomach pain, and the pain intensity is 8 / 10" and "Explanation: Your stomach feels tingly and painful. Does it feel like a little hedgehog is moving around inside your stomach?" are displayed, and the user confirms them.

[1714] Step 9:

[1715] The user can then review the suggested meal menu based on the displayed content and select the most suitable option, thereby providing a personalized meal menu that is tailored to the user's physical condition and emotions.

[1716] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1717] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1718] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1719] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1720] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1721] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1722] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1723] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1724] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1725] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1726] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1727] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1728] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1729] 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.

[1730] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1731] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1732] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1733] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1734] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1735] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1736] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1737] The following is further disclosed regarding the above embodiment.

[1738] (Claim 1)

[1739] A means to input a brief description of the symptoms and the severity of the symptoms;

[1740] means for transmitting the input symptom description and severity to a server;

[1741] A means to automatically generate medical records using a generation API based on the received data,

[1742] A means to generate explanatory text for patients in easy-to-understand language and character-style voice for the generated medical records,

[1743] A means for transmitting the generated medical record and explanation to a terminal and displaying them;

[1744] A system including:

[1745] (Claim 2)

[1746] The system according to claim 1, wherein the generated medical record and explanatory text are displayed together on a terminal.

[1747] (Claim 3)

[1748] The system according to claim 1, wherein the character's tone of voice can be selected and an optimal explanation is generated for each patient.

[1749] "Example 1"

[1750] (Claim 1)

[1751] A means for a user to input a description and severity of symptoms using a medical terminal;

[1752] means for transmitting the inputted symptom description and severity in data form to a server;

[1753] A means for the server to automatically generate medical records using a generation AI model based on the received data;

[1754] A means for generating explanatory text for patients using a generative AI model based on the generated medical record;

[1755] A means for transmitting the generated medical record and explanation to the terminal and for the terminal to display them;

[1756] A system including:

[1757] (Claim 2)

[1758] The system according to claim 1, wherein the generated medical record and explanatory text are displayed on a terminal.

[1759] (Claim 3)

[1760] The system according to claim 1, which allows selection of the character's tone of voice and style of expression, and generates the most appropriate explanation for each patient.

[1761] "Application Example 1"

[1762] (Claim 1)

[1763] A means for inputting a brief description of preferences and allergy information;

[1764] means for transmitting the input preference information and allergy information to a server;

[1765] A means to automatically generate a proposal menu using a generation API based on the received data,

[1766] A means for generating an explanation of the generated proposal menu in easy-to-understand language for users;

[1767] a means for transmitting the generated suggested menu and explanation to a terminal and displaying the menu and explanation;

[1768] A system including:

[1769] (Claim 2)

[1770] The system according to claim 1, wherein the generated suggested menu and explanatory text are displayed together on the terminal.

[1771] (Claim 3)

[1772] The system according to claim 1, wherein the explanatory text is expressed in an optimal manner according to the user.

[1773] "Example 2: Combining Emotion Engines"

[1774] (Claim 1)

[1775] A means for a user to input a brief description of the symptom and the severity of the symptom using an input form;

[1776] means for transmitting the input symptom description and severity to a server;

[1777] A means for automatically generating medical records using a generative AI model based on the received data;

[1778] A means to generate explanatory text for patients in easy-to-understand language and character-style voice for the medical records generated using the generation API, and

[1779] A means for recognizing a user's emotions in real time using an emotion engine built into the device;

[1780] means for transmitting the recognized emotion data to a server;

[1781] A means to adjust the tone and content of descriptions using generative AI models based on emotional data; and

[1782] a means for transmitting the generated medical record and the adjusted explanation to a terminal and displaying the same;

[1783] A system including:

[1784] (Claim 2)

[1785] The system according to claim 1, wherein the generated medical record and explanatory text are displayed together on a terminal.

[1786] (Claim 3)

[1787] The system of claim 1 uses an emotion engine to recognize a user's emotion data, and uses a generative AI model to generate explanatory text in a gentle tone or appropriate tone according to the emotion.

[1788] "Application example 2 when combining emotion engines"

[1789] (Claim 1)

[1790] A means to input a brief description of the symptoms and the severity of the symptoms;

[1791] means for transmitting the input symptom description and severity to a server;

[1792] A means to automatically generate medical records using a generation API based on the received data,

[1793] A means to generate explanatory text for patients in easy-to-understand language and character-style voice for the generated medical records,

[1794] means for detecting user emotions in real time, the means including an emotion engine for detecting user emotions in real time;

[1795] means for transmitting the recognized emotion data to a server;

[1796] means for adjusting the tone and content of the description based on the emotion data received by the server;

[1797] a means for transmitting to a terminal an explanation text adjusted based on the generated medical record and emotion data and displaying the explanation text;

[1798] A system including:

[1799] (Claim 2)

[1800] The system according to claim 1, wherein the generated medical record and explanatory text are combined and displayed on the terminal together with the explanatory text adjusted based on the emotion data.

[1801] (Claim 3)

[1802] 2. The system according to claim 1, wherein the character's tone of voice can be selected and an optimal explanatory text is generated according to the user's emotional data. [Explanation of symbols]

[1803] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to input a brief description of the symptoms and the severity of the symptoms; means for transmitting the input symptom description and severity to a server; A means to automatically generate medical records using a generation API based on the received data, A means to generate explanatory text for patients in easy-to-understand language and character-style voice for the generated medical records, A means for transmitting the generated medical record and explanation to a terminal and displaying them; A system including:

2. The system according to claim 1, wherein the generated medical record and explanatory text are displayed together on a terminal.

3. The system according to claim 1, wherein the character's tone of voice can be selected to generate an optimal explanation for each patient.

Images