System

Abstract

A system is provided.SOLUTION: A system including a terminal for inputting information on symptoms, server means for preprocessing symptom information received from the terminal, server means for specifying a disease using a generated AI model based on the preprocessed symptom information, server means for transmitting the specified disease and a prediction probability thereof to the terminal, and means for displaying the specified disease and the prediction probability thereof on the terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Many of the so-called intractable diseases are not generally known, and it can be difficult to diagnose them in small hospitals. This can delay accurate diagnosis, which can have a serious impact on the patient's health and life. It also takes a lot of time and money to identify the disease. There is a need for a system that can solve these problems and identify diseases quickly and accurately. [Means for solving the problem]

[0005] The present invention provides a system including a terminal for inputting symptom information, server means for preprocessing the received symptom information, server means for identifying diseases using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified diseases and their predicted probabilities to the terminal, and means for displaying the identified diseases and their predicted probabilities on the terminal. This enables rapid and accurate diagnosis, which is expected to improve the patient's health and quality of life. Furthermore, the generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification. Furthermore, the terminal and server means transmit and receive information using a secure communication protocol, ensuring the security of the information.

[0006] "Symptom information" is data relating to a specific medical condition or poor physical condition that is input by the user into the input terminal.

[0007] A "terminal" is a device used by a user to input symptom information and send it to a server. Examples include a smartphone or a PC.

[0008] The "server means" is a computer system having a series of functions for receiving symptom information sent from a terminal, preprocessing it, diagnosing it using a generative AI model, and sending the results.

[0009] "Preprocessing" is the process of converting the received symptom information into a format that is easy for the generative AI model to handle by removing noise, filling in missing values, and standardizing the format.

[0010] A "generative AI model" is an algorithm that is trained based on past medical data and diagnostic information and identifies diseases based on input symptom information.

[0011] "Disease identification" is the process of using a generative AI model to calculate possible diseases and their probabilities from input symptom information.

[0012] "Predicted probability" is a number output by a generative AI model for a particular disease that indicates the likelihood of that disease being present.

[0013] A "secure communication protocol" is a protocol for securely transmitting and receiving information between a terminal and a server. A common example is HTTPS.

[0014] The "display means" is an interface that visually shows the identified diseases and their predicted probabilities to the user on the terminal. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

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

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system including a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal.

[0037] System Configuration

[0038] 1. Terminal

[0039] A device where the user inputs information about their condition or symptoms. Typically, a smartphone or PC is used. The device converts the input information into data packets and sends them to a server using a secure communication protocol.

[0040] 2. Server Means

[0041] The server receives symptom information sent from the terminal and performs preprocessing on it, such as removing noise, filling in missing values, and standardizing the format.

[0042] The preprocessed data is then fed into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[0043] As a diagnostic result, a list of identified diseases and their predicted probabilities is generated, formatted, and sent to the terminal.

[0044] 3. Secure Communication Protocols

[0045] This is a protocol used when a device and a server send and receive information, ensuring the security of the information. HTTPS is generally used.

[0046] 4. Display means

[0047] The terminal displays the list of identified diseases and their predicted probabilities sent from the server on the user interface, allowing the user to obtain detailed information about their medical condition.

[0048] Program processing

[0049] 1. Data Entry

[0050] The user inputs information about their symptoms, such as "joint pain" or "fatigue," into the terminal.

[0051] The terminal transmits the input information to the server.

[0052] 2. Data Processing

[0053] The server preprocesses the received data and extracts features. For example, the input information "joint pain" is tokenized as "joint pain."

[0054] 3. Disease Identification Using AI Models

[0055] The server inputs the preprocessed data into a generative AI model to identify diseases. The AI ​​model calculates the predicted probability for each disease, yielding results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[0056] 4. Returning the results

[0057] The server formats the results and sends them to the terminal.

[0058] The terminal displays the results on a user interface, for example, showing identified diseases and their predicted probabilities in graph or list format.

[0059] Specific examples

[0060] The user inputs symptoms into the device, such as "I have joint pain when I wake up in the morning and get tired easily in the evening." The device then sends this input data to the server, which preprocesses the received data and extracts features. The server then uses a generative AI model to identify the disease and calculates probabilities such as "rheumatoid arthritis 60%" and "systemic lupus erythematosus 30%." These results are then formatted and sent to the device. Finally, the device displays the results on a user interface, allowing the user to instantly access detailed information about their condition.

[0061] This system can quickly identify diseases that are difficult to diagnose in hospitals, enabling patients to receive early treatment and receive consultations with appropriate medical institutions, which is expected to improve patients' health and quality of life.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user inputs information about the condition or symptoms into an input terminal. For example, the user selects symptoms from free-form text data such as "joint pain" or "fatigue" or from multiple-choice options.

[0065] Step 2:

[0066] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[0067] Step 3:

[0068] The server receives the data packet sent from the terminal and performs validation to confirm that the data was sent correctly.

[0069] Step 4:

[0070] The server preprocesses the received data, specifically removing noise, filtering spam, imputing missing values, and standardizing data formats. For example, "joint pain" is standardized to "arthritis."

[0071] Step 5:

[0072] The server extracts important features from the preprocessed data, such as keywords and features like "joint pain," "fatigue," "morning," and "evening," and converts them into numerical and categorical data.

[0073] Step 6:

[0074] The server inputs the extracted features into a generative AI model, which is trained on a vast amount of historical medical data and diagnostic information.

[0075] Step 7:

[0076] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[0077] Step 8:

[0078] The server organizes the prediction results obtained from the AI ​​model and formats them into a format that is easy to understand visually (for example, JSON format).

[0079] Step 9:

[0080] The server transmits the formatted prediction result data to the terminal using a secure communication protocol.

[0081] Step 10:

[0082] The device analyzes the received prediction result data and displays the results on the user interface. For example, results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" are displayed in graph and list format.

[0083] Step 11:

[0084] The user checks the displayed results and decides on the next action to take, such as early diagnosis or consulting an appropriate medical institution.

[0085] Example 1

[0086] 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."

[0087] In today's medical environment, rapid and accurate symptom-based disease identification remains a challenge. Delays in diagnosis, especially for diseases that are difficult to diagnose in hospitals, can result in missed opportunities for treatment, leading to a deterioration in health and quality of life. Conventional systems require a cumbersome process from symptom input to disease identification, and lack secure data transmission and highly accurate prediction. There is a need for a support system that can solve these problems and enable patients to receive appropriate medical treatment promptly.

[0088] 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.

[0089] In this invention, the server includes an information terminal means for inputting symptom information, a data processing means for preprocessing the symptom information received from the terminal, an analysis means for identifying a disease using a generative AI model based on the preprocessed symptom information, a communication means for transmitting the identified disease and its predicted probability to the terminal, and a display means for displaying the identified disease and its predicted probability on the terminal. This makes it possible to quickly and accurately analyze the symptom information input by the user, safely transmit the identified disease and its predicted probability, and immediately display it on the terminal.

[0090] The "information terminal means for inputting information about symptoms" refers to a device used by the user to input medical conditions and symptoms, and includes smartphones, personal computers, etc.

[0091] The "data processing means for preprocessing the symptom information received from the terminal" refers to a device or software that analyzes the symptom information sent from the terminal and performs noise removal, missing value complementation, format standardization, etc.

[0092] "Analysis means for identifying diseases using a generative AI model based on preprocessed symptom information" refers to a device or software that inputs preprocessed data into an AI model and identifies diseases based on past medical data and diagnostic information.

[0093] The "communication means for transmitting the identified disease and its predicted probability to the terminal" is a device or software that formats the analysis results and transmits them to the terminal using a secure communication protocol.

[0094] The "display means for displaying the identified disease and its predicted probability on the terminal" refers to a device or software that displays the analysis results received on the terminal on a user interface so that the user can check them.

[0095] A "generative AI model" is an artificial intelligence model that is trained on past medical data and diagnostic information and is capable of predicting disease based on symptom information.

[0096] A "secure communication protocol" is a protocol that encrypts data transmission and reception to ensure safety, and generally includes HTTPS.

[0097] This invention is a system that includes an information terminal means for inputting information about symptoms, a data processing means for performing preprocessing, an analysis means for identifying diseases using a generative AI model, a communication means, and a display means.

[0098] System Configuration

[0099] 1. Information terminal means

[0100] User: Enters symptom information using an information terminal such as a smartphone or PC. For example, a smartphone app or web interface is provided, allowing the user to enter symptoms. An example of a prompt sentence could be, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[0101] 2. Data processing means

[0102] Server: Preprocesses the symptom information received from the device. Preprocessing includes spell checking, noise removal, missing value completion, and format standardization. For example, data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." The information is also tokenized to extract features such as "joint pain" and "fatigue."

[0103] 3. Analysis method

[0104] Server: The preprocessed data is input into a generative AI model to identify diseases. The generative AI model used is trained based on past medical data and diagnostic information. The AI ​​model calculates the predicted probability for each disease based on the user's symptom information. For example, it outputs results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%."

[0105] 4. Means of communication

[0106] Server and terminal: The identified diseases and their predicted probabilities are transmitted to the terminal using a secure communication protocol (e.g., HTTPS) to ensure data integrity and confidentiality.

[0107] 5. Display means

[0108] Terminal: The received analysis results are displayed on a user interface, allowing the user to check the identified diseases and their predicted probabilities. The results are displayed in graph and list format. For example, a list of diseases such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" and their predicted probabilities are visually displayed.

[0109] Specific examples

[0110] The user inputs symptoms such as "I have joint pain when I wake up in the morning, and I get tired easily in the evening" using an information terminal. The terminal converts this information into a data packet and sends it to the server. The server preprocesses the received data and tokenizes the information "I have joint pain when I wake up in the morning, and I get tired easily in the evening" as "joint pain" and "fatigue." The preprocessed data is input into a generative AI model, which calculates predicted probabilities such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%." These results are formatted in JSON and sent to the terminal using a secure communication protocol. Finally, the terminal displays the received results on a user interface, allowing the user to visually confirm the identified diseases and their predicted probabilities.

[0111] This system will enable the rapid and accurate identification of diseases that are difficult to diagnose in hospitals, enabling patients to receive appropriate medical treatment at an early stage, which is expected to improve their health and quality of life.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Program processing flow

[0114] Step 1:

[0115] The user inputs symptom information using the information terminal means.

[0116] Specific actions: The user accesses the application or web interface on their smartphone or computer and inputs specific symptoms according to the prompts. For example, they might input, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[0117] Input: Symptom information ("My joints hurt when I wake up in the morning, and I get tired easily in the evening.")

[0118] Output: Symptom information entered into the terminal

[0119] Step 2:

[0120] The terminal transmits the input symptom information to the server.

[0121] Specific operation: The terminal converts the input symptom information into data packets and sends them to the server using a secure communication protocol (HTTPS).

[0122] Input: Symptom information entered into the terminal

[0123] Output: Symptom information sent to the server

[0124] Step 3:

[0125] The server preprocesses the received symptom information.

[0126] Specific operation: The server cleanses the received symptom information, removing noise and filling in missing values. It also standardizes the format of the information, e.g., data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." It then tokenizes the information as "joint pain" and "fatigue."

[0127] Input: Symptom information sent to the server

[0128] Output: Preprocessed and tokenized data

[0129] Step 4:

[0130] The server inputs the preprocessed symptom information into a generative AI model to identify the disease.

[0131] How it works: The server inputs the preprocessed data into a generative AI model. The AI ​​model is trained based on past medical data and diagnostic information and calculates the predicted probability for each disease. For example, it can produce results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[0132] Input: Preprocessed and tokenized data

[0133] Output: Predicted probability for each disease (rheumatoid arthritis: 60%, systemic lupus erythematosus: 30%)

[0134] Step 5:

[0135] The server formats the diagnostic results and sends them to the terminal.

[0136] Specific operation: The server formats the identified diseases and their predicted probabilities into an easy-to-read format (e.g., JSON format) and sends them to the terminal using a secure communication protocol (HTTPS).

[0137] Input: Predicted probability for each disease

[0138] Output: Formatted data, diagnostic results sent to terminal

[0139] Step 6:

[0140] The terminal displays the diagnostic results on the user interface.

[0141] Specific operation: The terminal application or web interface receives and analyzes the formatted diagnosis results sent from the server. The identified diseases and their predicted probabilities are displayed in the user interface in the form of a graph or list.

[0142] Input: Diagnostic results sent to the terminal

[0143] Output: Identified diseases and their predicted probabilities displayed in a user interface

[0144] Through the above steps, the user can quickly and accurately understand his or her own health condition and receive support to receive necessary medical treatment.

[0145] (Application example 1)

[0146] 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."

[0147] In modern autonomous vehicles, long driving times and driver health management are important issues. However, there is a lack of means to immediately respond when a driver feels unwell, making it difficult to take appropriate measures or respond quickly. In particular, when a health problem occurs while driving, immediate access to appropriate medical support is required, but current systems make it difficult to respond quickly.

[0148] 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.

[0149] In this invention, the server includes an interface means that allows the driver of the autonomous vehicle to input symptom information, a means for processing the symptom information input by the driver in real time and identifying a disease using a generative AI model, and a means for presenting information on the identified disease and its predicted probability to the driver, thereby enabling the driver to manage their own health condition in real time and take necessary measures promptly.

[0150] "Symptom information" is information relating to the specific physical condition or health state that the driver feels.

[0151] A "terminal" is a device through which the driver inputs symptom information, and specifically includes a smartphone or a head-mounted display installed in the vehicle.

[0152] "Server means" refers to a central processing unit that processes the received symptom information and identifies the disease using a generative AI model.

[0153] "Preprocessing" refers to processing the received symptom information by methods such as noise removal, missing value completion, and format standardization.

[0154] A "generative AI model" is a machine learning model trained on past medical data and diagnostic information to identify diseases from symptom information.

[0155] "Disease" refers to a specific illness or disorder that causes physical abnormalities or discomfort.

[0156] "Prediction probability" refers to the probability that a disease will be identified by the generative AI model, and indicates the likelihood that the identified disease applies to the driver.

[0157] The "interface means" is a user interface that allows the driver to easily input symptom information through an input device.

[0158] "Real-time processing" means that the input symptom information is immediately sent to the server, and disease identification and prediction probability calculation are performed quickly based on that information.

[0159] "Presentation means" refers to a display method or audio guidance for immediately visually or audibly informing the driver of the identified disease and its predicted probability.

[0160] The present invention provides a system for enabling a driver of an autonomous vehicle to monitor his or her own health condition in real time. The system includes a driver terminal, a server means, a generative AI model, a secure communication protocol, and an interface means.

[0161] Terminal

[0162] The terminal is a device that the driver uses to input symptom information. This device can be a smartphone or a head-mounted display (HMD) installed in the vehicle. The terminal is responsible for transmitting the symptom information input by the driver to the server.

[0163] Server Means

[0164] The server preprocesses the symptom information received from the device and identifies diseases using a generative AI model. Preprocessing includes noise removal, missing value completion, and format standardization. The preprocessed data is input into the generative AI model, which performs highly accurate disease identification.

[0165] Generative AI Models

[0166] A generative AI model is a machine learning model trained on past medical data and diagnostic information. This model predicts diseases based on input symptom information and calculates the predicted probability.

[0167] Secure Communication Protocol

[0168] Secure communication protocols such as HTTPS are used to send and receive information between the device and the server, ensuring the safety of the information.

[0169] Interface Means

[0170] The interface means is a user interface that allows the driver to easily input symptom information, and specifically supports voice input and text input.

[0171] Specific examples

[0172] If a driver experiences "numbness in the hands" and "nausea," they can input their symptoms into the HMD by voice. The HMD converts the voice input into text and sends it to the server. The server preprocesses the symptom data and identifies the illness using a generative AI model. This produces predictions such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%." These results are displayed on the HMD, allowing the driver to take appropriate action based on their physical condition (e.g., take a break, consult a doctor, etc.).

[0173] Prompt Sentence Examples

[0174] User: Enter symptoms: "numbness in hands," "nausea"

[0175] System: Running diagnostics...

[0176] System:Result - 70% chance of carpal tunnel syndrome, 20% chance of anemia. Showing more information.

[0177] This system allows drivers to monitor their own health status in real time and take necessary measures promptly.

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] The user inputs their symptom information into the terminal.

[0181] Specific symptoms can be entered in voice or text format, such as "numbness in hands" or "nausea." The device converts this symptom information into text data and formats it in JSON format.

[0182] Input: Symptom information in spoken or text form

[0183] Output: Symptom data in JSON format

[0184] Step 2:

[0185] The terminal transmits the input symptom information to the server.

[0186] The HTTPS protocol is used to ensure secure communication, and transmitted data is encrypted end-to-end.

[0187] Input: Symptom data in JSON format

[0188] Output: Symptom data sent to the server

[0189] Step 3:

[0190] The server pre-processes the received symptom information.

[0191] The preprocessing step involves noise removal, missing value imputation, and format standardization. For example, information about "numbness in the hands" and "nausea" is tokenized as "suspected carpal tunnel syndrome."

[0192] Input: Symptom data sent to the server

[0193] Output: Preprocessed data

[0194] Step 4:

[0195] The server inputs the preprocessed data into a generative AI model to identify diseases.

[0196] The AI ​​model is trained on past medical data and diagnostic information to calculate identified diseases and their predicted probabilities, generating results such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%."

[0197] Input: Preprocessed data

[0198] Output: Identified diseases and their predicted probabilities by the generative AI model

[0199] Step 5:

[0200] The server formats the identified diseases and their predicted probabilities and transmits them to the terminal.

[0201] The results are formatted in lists and graphs to make them easy for drivers to understand, and the data is sent again using the HTTPS protocol.

[0202] Input: Identified diseases and their predicted probabilities by the generative AI model

[0203] Output: Formatted result data sent to the terminal

[0204] Step 6:

[0205] The terminal displays the received identified diseases and their predicted probabilities on a user interface.

[0206] The display format can be, for example, a list format or a graph format, allowing the driver to check the results in real time and take any necessary measures.

[0207] Input: Formatted result data sent to the terminal

[0208] Output: Identified diseases and their predicted probabilities displayed in a user interface

[0209] In this way, the symptom information entered by the user is processed on the server, the disease is identified using a generative AI model, and the results are immediately returned to the driver, enabling a prompt and appropriate response.

[0210] 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.

[0211] The present invention is a system that combines a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal, as well as an emotion engine that recognizes the user's emotions.

[0212] System Configuration

[0213] 1. Terminal

[0214] This is a device into which the user inputs information about their medical condition, symptoms, and emotional state. Specifically, it is a smartphone or PC. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[0215] 2. Server Means

[0216] The server receives symptom information sent from the device and preprocesses it. Preprocessing includes noise removal, standardizing data formats, and filling in missing values. Once preprocessed, the data is input into a generative AI model to identify the disease.

[0217] The generative AI model is trained based on past medical data and diagnostic information to achieve highly accurate disease identification. As a diagnostic result, a list of identified diseases and their predicted probabilities is generated and sent to the device.

[0218] 3. Emotion Engine

[0219] The server also has an emotion engine that recognizes the user's emotional state. This emotion engine analyzes text information and voice data entered by the user and extracts their emotional state. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[0220] 4. Secure Communication Protocols

[0221] The security of information is ensured by the protocol used when sending and receiving information between the device and the server. HTTPS is generally used.

[0222] 5. Display means

[0223] The terminal displays the list of identified diseases and their predicted probabilities, as well as the analysis results of the emotional state, on a user interface. Based on this information, the user can quickly decide on their next course of action.

[0224] Program processing

[0225] 1. Data Entry

[0226] The user inputs their symptoms and emotional state into the device. Symptom information is entered as "joint pain" or "fatigue," and emotional information is entered as "stress" or "anxiety," using free-form text or voice data.

[0227] 2. Data Transmission

[0228] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[0229] 3. Data Reception and Preprocessing

[0230] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing such as noise removal and missing value completion, and standardizes the data format.

[0231] 4. Emotion analysis

[0232] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data.

[0233] 5. Feature Extraction

[0234] The server extracts important features from the preprocessed symptom information and emotion information, such as "joint pain," "fatigue," and "stress."

[0235] 6. Input to the AI ​​model

[0236] The server inputs the extracted feature information into a generative AI model to identify the disease.

[0237] 7. Disease Identification and Outcome Generation

[0238] The server organizes the list of diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually easy-to-understand format (e.g., JSON format).

[0239] 8. Send results

[0240] The server transmits the formatted prediction result data to the terminal.

[0241] 9. Results display

[0242] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[0243] Specific examples

[0244] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, and the user decides on the next action.

[0245] This system can quickly identify diseases that are difficult to diagnose and provide more accurate diagnostic results that take into account the user's emotional state.

[0246] The processing flow will be explained below.

[0247] Step 1:

[0248] The user inputs information about their medical condition and emotions into an input terminal. Specifically, they input free-form text or voice data such as "My joints hurt when I wake up in the morning, and I feel more tired and stressed in the evening."

[0249] Step 2:

[0250] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol such as HTTPS.

[0251] Step 3:

[0252] The server receives data packets sent from the device, and then validates them to ensure they were sent correctly and checks for inaccurate or lost data.

[0253] Step 4:

[0254] The server preprocesses the received data, which may include noise reduction (e.g., removing nonsense text or audio), spam filtering, missing value imputation, and data formatting standardization (e.g., converting all text to lowercase).

[0255] Step 5:

[0256] The server analyzes the preprocessed data and extracts specific keywords and phrases, such as symptoms and emotional characteristics like "joint pain," "fatigue," and "stress."

[0257] Step 6:

[0258] The server passes the extracted feature data to the emotion engine, which analyzes the user's emotional state (e.g., "stress" or "anxiety") from the text and voice data and converts it into a numerical value or categorization.

[0259] Step 7:

[0260] The server combines the emotion information obtained from the emotion engine with the pre-processed symptom information and inputs it into a generative AI model, which is trained on past medical data and diagnostic information.

[0261] Step 8:

[0262] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[0263] Step 9:

[0264] The server formats the generated prediction results and emotion information into a visually easy-to-understand format (e.g., JSON format).

[0265] Step 10:

[0266] The server then transmits the formatted prediction result data to the terminal again using a secure communication protocol such as HTTPS.

[0267] Step 11:

[0268] The device analyzes the received prediction result data and emotion information and displays them on the user interface. For example, the identified disease and its predicted probability, results such as "rheumatoid arthritis: 60%," "systemic lupus erythematosus: 30%," and "stress level: high" are displayed in graph and list format.

[0269] Step 12:

[0270] The user checks the displayed results and, based on the information about their health condition, consults with a medical institution as necessary and makes a treatment plan.

[0271] Example 2

[0272] 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."

[0273] Conventional medical diagnostic systems do not take into account the user's emotional state, making it difficult to identify diseases caused by urgency or psychological factors. Furthermore, preprocessing of input symptom information is insufficient, making it difficult to remove noise and complete missing values, resulting in low diagnostic accuracy. Furthermore, the lack of secure communication protocols means that data security cannot be guaranteed. These issues must be resolved to achieve more accurate and rapid disease identification.

[0274] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0275] In this invention, the server includes a means for preprocessing the received symptom information, a means including an emotion engine for recognizing the user's emotional state, and a means for identifying a disease using a generative AI model based on the preprocessed symptom information, thereby enabling highly accurate disease identification that takes the user's emotional state into consideration.

[0276] "Symptom information" is information about a medical condition or physical condition entered by a user.

[0277] A "terminal" is a device through which a user inputs symptom information, and examples include a smartphone and a personal computer.

[0278] The "server means" refers to a server that processes symptom information received from a terminal and performs various analyses and data transmissions.

[0279] "Preprocessing" refers to processes such as removing noise from received symptom information, filling in missing values, and standardizing data formats.

[0280] A "generative AI model" is an artificial intelligence model trained based on past medical data and diagnostic information, and is a technology that enables highly accurate disease identification.

[0281] "Disease identification" refers to the process of using generative AI models to identify possible diseases based on specific symptoms.

[0282] "Predicted probability" is a numerical value that indicates the probability that the generative AI model estimates for a specified disease.

[0283] An "emotion engine" is a system that includes software functions for analyzing a user's emotional state from text information and voice data.

[0284] A "secure communication protocol" is a communication protocol used by a terminal and a server means to send and receive information securely, and a specific example of this is HTTPS.

[0285] "User interface" refers to an interface for visually displaying information to a user on a terminal.

[0286] This invention is a system that includes a terminal where a user inputs their own symptom information and emotional state, a server means for preprocessing the received symptom information and identifying a disease using a generative AI model, and a means for displaying the identified disease and its predicted probability. The system also includes an emotion engine that recognizes the user's emotional state.

[0287] First, the user inputs their symptom information and emotional state using a device such as a smartphone or PC. Symptom information includes such things as "My joints hurt when I wake up in the morning" and "I get tired easily in the evening," while emotional information includes free-form text and voice data such as "I feel stressed" and "I feel anxious."

[0288] The terminal then converts the input information into data packets and transmits them to the server using a secure communication protocol (e.g., HTTPS).

[0289] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing to remove noise from the data, fill in missing values, and standardize the data format. Preprocessing also includes converting voice data to text and formatting text data for sentiment analysis.

[0290] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it detects "stress" from text data and analyzes "anxiety" from voice data. The results of the emotion analysis are also used as input data for the generative AI model.

[0291] Next, the server extracts key features from the preprocessed symptom and emotion information. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. This feature information is input into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[0292] Once the generative AI model has obtained the list of diseases and their predicted probabilities, the server formats it into a visually understandable format (e.g., JSON), and the formatted result data is sent to the device.

[0293] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid Arthritis: 60%," "Systemic Lupus Erythematosus: 30%," and "Stress Level: High" are displayed. Based on this information, the user can quickly decide on their next course of action.

[0294] Specific examples

[0295] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device converts this information into a data packet and sends it to the server using HTTPS. The server validates the received data and performs preprocessing such as missing value completion and noise removal. The emotion engine analyzes "stress," and the server extracts "joint pain," "fatigue," and "stress" as features. The feature information is input into the generative AI model, which generates the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus." This resulting data is sent to the device, which displays the results on the user interface.

[0296] Prompt Sentence Examples

[0297] "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed. Could you please tell me what illnesses these symptoms could suggest?"

[0298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0299] Step 1: Data entry

[0300] The user inputs their symptoms and emotional state into the device. For example, they can input text or voice data such as "My joints hurt when I wake up in the morning," "I get tired easily in the evening," or "I feel stressed."

[0301] Input: Symptom information and emotion information (text and audio data)

[0302] Output: Data packets

[0303] Step 2: Send data

[0304] The terminal converts the input information into data packets and transmits them to the server using a secure communication protocol (for example, HTTPS).

[0305] Input: Data packet

[0306] Output: Data sent to the server

[0307] Step 3: Data Receipt and Validation

[0308] The server receives the data sent from the terminal and performs validation on the received data, checking the format and content (e.g., checking for missing values, checking the data format, etc.).

[0309] Input: Received data

[0310] Output: Validated data

[0311] Step 4: Data Preprocessing

[0312] The server performs preprocessing on the data that has passed validation, such as removing noise, filling in missing values, and standardizing the data format, to prepare the data in a format suitable for analysis.

[0313] Input: Validated data

[0314] Output: Preprocessed data

[0315] Step 5: Sentiment Analysis

[0316] The server passes a portion of the preprocessed data to the emotion engine, which analyzes the user's emotional state by detecting "stress" from the text data and "anxiety" from the voice data.

[0317] Input: Preprocessed data

[0318] Output: Emotion analysis results

[0319] Step 6: Feature Extraction

[0320] The server extracts key features from the preprocessed symptom and emotion information, such as "joint pain," "fatigue," and "stress."

[0321] Input: Preprocessed data and sentiment analysis results

[0322] Output: Extracted feature data

[0323] Step 7: Input to the AI ​​model

[0324] The server inputs the extracted feature information into a generative AI model, which has been previously trained on past medical data and diagnostic information.

[0325] Input: Extracted feature data

[0326] Output: AI-identified disease data

[0327] Step 8: Disease identification and outcome generation

[0328] The server retrieves the diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually understandable format (e.g., JSON format).

[0329] Input: AI-identified disease data

[0330] Output: Formatted result data

[0331] Step 9: Send results

[0332] The server transmits the formatted prediction result data to the terminal.

[0333] Input: Formatted result data

[0334] Output: Data sent to the terminal

[0335] Step 10: View the results

[0336] The device then displays the received prediction data and emotion analysis results on a user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[0337] Input: Submitted result data

[0338] Output: what is displayed to the user

[0339] (Application example 2)

[0340] 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."

[0341] In modern society, there is a demand for rapid and accurate disease identification based on each individual's health and emotional state. However, many systems perform diagnosis without taking emotional information into account, resulting in low accuracy of diagnostic results. Furthermore, there is a lack of systems that provide advertisements for appropriate products and services based on identified disease information. Therefore, there is a need for a system that analyzes a user's symptom information and emotional information, identifies a disease based on that information, and then displays relevant advertisements based on the identified disease information.

[0342] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal that inputs information about symptoms, server means that preprocesses the symptom information received from the terminal, server means that identifies a disease using a generative AI model based on the preprocessed symptom information, server means that transmits the identified disease and its predicted probability to the terminal, means for displaying advertisements for related products and services based on the disease information displayed on the terminal, an emotion engine that inputs and analyzes emotion information, and means for displaying the identified disease and its predicted probability on the terminal. This enables highly accurate disease identification that takes the user's emotional state into consideration, and further makes it possible to display advertisements for appropriate products and services based on the identified disease.

[0343] A "terminal" is a device that allows a user to input information about symptoms and emotions.

[0344] The "server means" is a server that processes symptom information and emotion information received from the terminal and identifies diseases using a generative AI model.

[0345] A "generative AI model" is an AI algorithm that is trained based on past medical data and diagnostic information and identifies diseases based on the user's symptoms and emotional information.

[0346] An "emotion engine" is an engine that has the function of analyzing text and voice input by the user and extracting their emotional state.

[0347] A "secure communication protocol" is a communication method that ensures the security of information when sending and receiving data between a terminal and a server.

[0348] The "display means" is a function that displays the identified disease, its predicted probability, and related advertisements sent from the server on the user interface.

[0349] The "means for displaying advertisements" is a function for providing users with advertisements for related products and services based on the identified disease information.

[0350] The present invention is a system that includes a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, an emotion engine for recognizing the user's emotions, and a function for displaying the identified disease and its predicted probability, as well as means for displaying advertisements for related products and services.

[0351] System Configuration

[0352] 1. Terminal

[0353] A device into which a user inputs information about their medical condition, symptoms, and emotional state. Specifically, a smartphone, smart glasses, or PC can be used. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[0354] 2. Server Means

[0355] The server receives the symptom information sent from the device and performs preprocessing, which includes noise removal, data format standardization, and missing value completion. After preprocessing is complete, the data is input into a generative AI model to identify diseases. A list of identified diseases and their predicted probabilities is sent to the device.

[0356] The server also has an emotion engine that analyzes the user's emotional state by analyzing the text information and voice data entered by the user. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[0357] 3. Secure Communication Protocols

[0358] A protocol used when a terminal and a server send and receive information. HTTPS is generally used.

[0359] 4. Display means

[0360] The terminal displays a list of identified diseases and their predicted probabilities sent from the server, as well as advertisements for related products and services, on the user interface, allowing the user to quickly decide their next course of action based on this information.

[0361] Specific examples

[0362] The user inputs into the smart glasses, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, along with advertisements for related products and services. The user can then decide on appropriate actions based on this.

[0363] Example prompt sentence:

[0364] "I've had a headache since this morning and I feel really sick."

[0365] "Recently, my joints have been hurting and I've been feeling tired easily."

[0366] This invention realizes a system that comprehensively analyzes a user's symptoms and emotional state and provides the user with optimal information and services.

[0367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0368] Step 1:

[0369] The user inputs their symptoms and emotional state into the device. This input information includes text and voice data. Specifically, the user inputs a prompt sentence such as "I've had a headache since this morning and I feel very unwell" using smart glasses or a smartphone. This input information is converted into a data packet.

[0370] Step 2:

[0371] The device sends the input information to the server using a secure communication protocol (e.g., HTTPS). The input here is symptom information and emotion information entered by the user, and this becomes the output sent to the server.

[0372] Step 3:

[0373] The server preprocesses the received data, including removing noise, standardizing data formats, and filling in missing values. The input is the raw data sent from the device, and the output is clean data that has undergone preprocessing.

[0374] Step 4:

[0375] The server passes the preprocessed data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data. The input is the preprocessed symptom and emotion data, and the output is the analysis result including the emotional state.

[0376] Step 5:

[0377] The server extracts important features from the preprocessed symptom information and the analysis results of the emotion engine. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. The input is the preprocessed data and the emotion analysis results, and the output is the extracted feature information.

[0378] Step 6:

[0379] The server inputs the extracted feature information into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification. The input is feature information, and the output is a list of identified diseases and their predicted probabilities.

[0380] Step 7:

[0381] The server organizes the list of identified diseases and their predicted probabilities and formats them into a visually understandable format (e.g., JSON format). The input is the output of the generative AI model, and the formatted prediction result data is obtained.

[0382] Step 8:

[0383] The server sends the formatted prediction result data to the terminal. The input here is the formatted prediction result data, and the output sent to the terminal.

[0384] Step 9:

[0385] The device displays advertisements for related products and services on the user interface based on the received prediction result data and emotion analysis results. Specifically, based on results such as "Migraine: 70%" and "Mood Depression: Strong," advertisements for supplements effective against migraines or relaxing yoga classes are displayed. The input is the prediction result data and emotion analysis results from the server, and the output is what is displayed on the user interface.

[0386] 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.

[0387] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0388] 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.

[0389] [Second embodiment]

[0390] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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."

[0402] The present invention is a system including a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal.

[0403] System Configuration

[0404] 1. Terminal

[0405] A device where the user inputs information about their condition or symptoms. Typically, a smartphone or PC is used. The device converts the input information into data packets and sends them to a server using a secure communication protocol.

[0406] 2. Server Means

[0407] The server receives symptom information sent from the terminal and performs preprocessing on it, such as removing noise, filling in missing values, and standardizing the format.

[0408] The preprocessed data is then fed into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[0409] As a diagnostic result, a list of identified diseases and their predicted probabilities is generated, formatted, and sent to the terminal.

[0410] 3. Secure Communication Protocols

[0411] This is a protocol used when a device and a server send and receive information, ensuring the security of the information. HTTPS is generally used.

[0412] 4. Display means

[0413] The terminal displays the list of identified diseases and their predicted probabilities sent from the server on the user interface, allowing the user to obtain detailed information about their medical condition.

[0414] Program processing

[0415] 1. Data Entry

[0416] The user inputs information about their symptoms, such as "joint pain" or "fatigue," into the terminal.

[0417] The terminal transmits the input information to the server.

[0418] 2. Data Processing

[0419] The server preprocesses the received data and extracts features. For example, the input information "joint pain" is tokenized as "joint pain."

[0420] 3. Disease Identification Using AI Models

[0421] The server inputs the preprocessed data into a generative AI model to identify diseases. The AI ​​model calculates the predicted probability for each disease, yielding results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[0422] 4. Returning the results

[0423] The server formats the results and sends them to the terminal.

[0424] The terminal displays the results on a user interface, for example, showing identified diseases and their predicted probabilities in graph or list format.

[0425] Specific examples

[0426] The user inputs symptoms into the device, such as "I have joint pain when I wake up in the morning and get tired easily in the evening." The device then sends this input data to the server, which preprocesses the received data and extracts features. The server then uses a generative AI model to identify the disease and calculates probabilities such as "rheumatoid arthritis 60%" and "systemic lupus erythematosus 30%." These results are then formatted and sent to the device. Finally, the device displays the results on a user interface, allowing the user to instantly access detailed information about their condition.

[0427] This system can quickly identify diseases that are difficult to diagnose in hospitals, enabling patients to receive early treatment and receive consultations with appropriate medical institutions, which is expected to improve patients' health and quality of life.

[0428] The processing flow will be explained below.

[0429] Step 1:

[0430] The user inputs information about the condition or symptoms into an input terminal. For example, the user selects symptoms from free-form text data such as "joint pain" or "fatigue" or from multiple-choice options.

[0431] Step 2:

[0432] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[0433] Step 3:

[0434] The server receives the data packet sent from the terminal and performs validation to confirm that the data was sent correctly.

[0435] Step 4:

[0436] The server preprocesses the received data, specifically removing noise, filtering spam, imputing missing values, and standardizing data formats. For example, "joint pain" is standardized to "arthritis."

[0437] Step 5:

[0438] The server extracts important features from the preprocessed data, such as keywords and features like "joint pain," "fatigue," "morning," and "evening," and converts them into numerical and categorical data.

[0439] Step 6:

[0440] The server inputs the extracted features into a generative AI model, which is trained on a vast amount of historical medical data and diagnostic information.

[0441] Step 7:

[0442] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[0443] Step 8:

[0444] The server organizes the prediction results obtained from the AI ​​model and formats them into a format that is easy to understand visually (for example, JSON format).

[0445] Step 9:

[0446] The server transmits the formatted prediction result data to the terminal using a secure communication protocol.

[0447] Step 10:

[0448] The device analyzes the received prediction result data and displays the results on the user interface. For example, results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" are displayed in graph and list format.

[0449] Step 11:

[0450] The user checks the displayed results and decides on the next action to take, such as early diagnosis or consulting an appropriate medical institution.

[0451] Example 1

[0452] 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."

[0453] In today's medical environment, rapid and accurate symptom-based disease identification remains a challenge. Delays in diagnosis, especially for diseases that are difficult to diagnose in hospitals, can result in missed opportunities for treatment, leading to a deterioration in health and quality of life. Conventional systems require a cumbersome process from symptom input to disease identification, and lack secure data transmission and highly accurate prediction. There is a need for a support system that can solve these problems and enable patients to receive appropriate medical treatment promptly.

[0454] 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.

[0455] In this invention, the server includes an information terminal means for inputting symptom information, a data processing means for preprocessing the symptom information received from the terminal, an analysis means for identifying a disease using a generative AI model based on the preprocessed symptom information, a communication means for transmitting the identified disease and its predicted probability to the terminal, and a display means for displaying the identified disease and its predicted probability on the terminal. This makes it possible to quickly and accurately analyze the symptom information input by the user, safely transmit the identified disease and its predicted probability, and immediately display it on the terminal.

[0456] The "information terminal means for inputting information about symptoms" refers to a device used by the user to input medical conditions and symptoms, and includes smartphones, personal computers, etc.

[0457] The "data processing means for preprocessing the symptom information received from the terminal" refers to a device or software that analyzes the symptom information sent from the terminal and performs noise removal, missing value complementation, format standardization, etc.

[0458] "Analysis means for identifying diseases using a generative AI model based on preprocessed symptom information" refers to a device or software that inputs preprocessed data into an AI model and identifies diseases based on past medical data and diagnostic information.

[0459] The "communication means for transmitting the identified disease and its predicted probability to the terminal" is a device or software that formats the analysis results and transmits them to the terminal using a secure communication protocol.

[0460] The "display means for displaying the identified disease and its predicted probability on the terminal" refers to a device or software that displays the analysis results received on the terminal on a user interface so that the user can check them.

[0461] A "generative AI model" is an artificial intelligence model that is trained on past medical data and diagnostic information and is capable of predicting disease based on symptom information.

[0462] A "secure communication protocol" is a protocol that encrypts data transmission and reception to ensure safety, and generally includes HTTPS.

[0463] This invention is a system that includes an information terminal means for inputting information about symptoms, a data processing means for performing preprocessing, an analysis means for identifying diseases using a generative AI model, a communication means, and a display means.

[0464] System Configuration

[0465] 1. Information terminal means

[0466] User: Enters symptom information using an information terminal such as a smartphone or PC. For example, a smartphone app or web interface is provided, allowing the user to enter symptoms. An example of a prompt sentence could be, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[0467] 2. Data processing means

[0468] Server: Preprocesses the symptom information received from the device. Preprocessing includes spell checking, noise removal, missing value completion, and format standardization. For example, data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." The information is also tokenized to extract features such as "joint pain" and "fatigue."

[0469] 3. Analysis method

[0470] Server: The preprocessed data is input into a generative AI model to identify diseases. The generative AI model used is trained based on past medical data and diagnostic information. The AI ​​model calculates the predicted probability for each disease based on the user's symptom information. For example, it outputs results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%."

[0471] 4. Means of communication

[0472] Server and terminal: The identified diseases and their predicted probabilities are transmitted to the terminal using a secure communication protocol (e.g., HTTPS) to ensure data integrity and confidentiality.

[0473] 5. Display means

[0474] Terminal: The received analysis results are displayed on a user interface, allowing the user to check the identified diseases and their predicted probabilities. The results are displayed in graph and list format. For example, a list of diseases such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" and their predicted probabilities are visually displayed.

[0475] Specific examples

[0476] The user inputs symptoms such as "I have joint pain when I wake up in the morning, and I get tired easily in the evening" using an information terminal. The terminal converts this information into a data packet and sends it to the server. The server preprocesses the received data and tokenizes the information "I have joint pain when I wake up in the morning, and I get tired easily in the evening" as "joint pain" and "fatigue." The preprocessed data is input into a generative AI model, which calculates predicted probabilities such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%." These results are formatted in JSON and sent to the terminal using a secure communication protocol. Finally, the terminal displays the received results on a user interface, allowing the user to visually confirm the identified diseases and their predicted probabilities.

[0477] This system will enable the rapid and accurate identification of diseases that are difficult to diagnose in hospitals, enabling patients to receive appropriate medical treatment at an early stage, which is expected to improve their health and quality of life.

[0478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0479] Program processing flow

[0480] Step 1:

[0481] The user inputs symptom information using the information terminal means.

[0482] Specific actions: The user accesses the application or web interface on their smartphone or computer and inputs specific symptoms according to the prompts. For example, they might input, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[0483] Input: Symptom information ("My joints hurt when I wake up in the morning, and I get tired easily in the evening.")

[0484] Output: Symptom information entered into the terminal

[0485] Step 2:

[0486] The terminal transmits the input symptom information to the server.

[0487] Specific operation: The terminal converts the input symptom information into data packets and sends them to the server using a secure communication protocol (HTTPS).

[0488] Input: Symptom information entered into the terminal

[0489] Output: Symptom information sent to the server

[0490] Step 3:

[0491] The server preprocesses the received symptom information.

[0492] Specific operation: The server cleanses the received symptom information, removing noise and filling in missing values. It also standardizes the format of the information, e.g., data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." It then tokenizes the information as "joint pain" and "fatigue."

[0493] Input: Symptom information sent to the server

[0494] Output: Preprocessed and tokenized data

[0495] Step 4:

[0496] The server inputs the preprocessed symptom information into a generative AI model to identify the disease.

[0497] How it works: The server inputs the preprocessed data into a generative AI model. The AI ​​model is trained based on past medical data and diagnostic information and calculates the predicted probability for each disease. For example, it can produce results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[0498] Input: Preprocessed and tokenized data

[0499] Output: Predicted probability for each disease (rheumatoid arthritis: 60%, systemic lupus erythematosus: 30%)

[0500] Step 5:

[0501] The server formats the diagnostic results and sends them to the terminal.

[0502] Specific operation: The server formats the identified diseases and their predicted probabilities into an easy-to-read format (e.g., JSON format) and sends them to the terminal using a secure communication protocol (HTTPS).

[0503] Input: Predicted probability for each disease

[0504] Output: Formatted data, diagnostic results sent to terminal

[0505] Step 6:

[0506] The terminal displays the diagnostic results on the user interface.

[0507] Specific operation: The terminal application or web interface receives and analyzes the formatted diagnosis results sent from the server. The identified diseases and their predicted probabilities are displayed in the user interface in the form of a graph or list.

[0508] Input: Diagnostic results sent to the terminal

[0509] Output: Identified diseases and their predicted probabilities displayed in a user interface

[0510] Through the above steps, the user can quickly and accurately understand his or her own health condition and receive support to receive necessary medical treatment.

[0511] (Application example 1)

[0512] 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."

[0513] In modern autonomous vehicles, long driving times and driver health management are important issues. However, there is a lack of means to immediately respond when a driver feels unwell, making it difficult to take appropriate measures or respond quickly. In particular, when a health problem occurs while driving, immediate access to appropriate medical support is required, but current systems make it difficult to respond quickly.

[0514] 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.

[0515] In this invention, the server includes an interface means that allows the driver of the autonomous vehicle to input symptom information, a means for processing the symptom information input by the driver in real time and identifying a disease using a generative AI model, and a means for presenting information on the identified disease and its predicted probability to the driver, thereby enabling the driver to manage their own health condition in real time and take necessary measures promptly.

[0516] "Symptom information" is information relating to the specific physical condition or health state that the driver feels.

[0517] A "terminal" is a device through which the driver inputs symptom information, and specifically includes a smartphone or a head-mounted display installed in the vehicle.

[0518] "Server means" refers to a central processing unit that processes the received symptom information and identifies the disease using a generative AI model.

[0519] "Preprocessing" refers to processing the received symptom information by methods such as noise removal, missing value completion, and format standardization.

[0520] A "generative AI model" is a machine learning model trained on past medical data and diagnostic information to identify diseases from symptom information.

[0521] "Disease" refers to a specific illness or disorder that causes physical abnormalities or discomfort.

[0522] "Prediction probability" refers to the probability that a disease will be identified by the generative AI model, and indicates the likelihood that the identified disease applies to the driver.

[0523] The "interface means" is a user interface that allows the driver to easily input symptom information through an input device.

[0524] "Real-time processing" means that the input symptom information is immediately sent to the server, and disease identification and prediction probability calculation are performed quickly based on that information.

[0525] "Presentation means" refers to a display method or audio guidance for immediately visually or audibly informing the driver of the identified disease and its predicted probability.

[0526] The present invention provides a system for enabling a driver of an autonomous vehicle to monitor his or her own health condition in real time. The system includes a driver terminal, a server means, a generative AI model, a secure communication protocol, and an interface means.

[0527] Terminal

[0528] The terminal is a device that the driver uses to input symptom information. This device can be a smartphone or a head-mounted display (HMD) installed in the vehicle. The terminal is responsible for transmitting the symptom information input by the driver to the server.

[0529] Server Means

[0530] The server preprocesses the symptom information received from the device and identifies diseases using a generative AI model. Preprocessing includes noise removal, missing value completion, and format standardization. The preprocessed data is input into the generative AI model, which performs highly accurate disease identification.

[0531] Generative AI Models

[0532] A generative AI model is a machine learning model trained on past medical data and diagnostic information. This model predicts diseases based on input symptom information and calculates the predicted probability.

[0533] Secure Communication Protocol

[0534] Secure communication protocols such as HTTPS are used to send and receive information between the device and the server, ensuring the safety of the information.

[0535] Interface Means

[0536] The interface means is a user interface that allows the driver to easily input symptom information, and specifically supports voice input and text input.

[0537] Specific examples

[0538] If a driver experiences "numbness in the hands" and "nausea," they can input their symptoms into the HMD by voice. The HMD converts the voice input into text and sends it to the server. The server preprocesses the symptom data and identifies the illness using a generative AI model. This produces predictions such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%." These results are displayed on the HMD, allowing the driver to take appropriate action based on their physical condition (e.g., take a break, consult a doctor, etc.).

[0539] Prompt Sentence Examples

[0540] User: Enter symptoms: "numbness in hands," "nausea"

[0541] System: Running diagnostics...

[0542] System:Result - 70% chance of carpal tunnel syndrome, 20% chance of anemia. Showing more information.

[0543] This system allows drivers to monitor their own health status in real time and take necessary measures promptly.

[0544] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0545] Step 1:

[0546] The user inputs their symptom information into the terminal.

[0547] Specific symptoms can be entered in voice or text format, such as "numbness in hands" or "nausea." The device converts this symptom information into text data and formats it in JSON format.

[0548] Input: Symptom information in spoken or text form

[0549] Output: Symptom data in JSON format

[0550] Step 2:

[0551] The terminal transmits the input symptom information to the server.

[0552] The HTTPS protocol is used to ensure secure communication, and transmitted data is encrypted end-to-end.

[0553] Input: Symptom data in JSON format

[0554] Output: Symptom data sent to the server

[0555] Step 3:

[0556] The server pre-processes the received symptom information.

[0557] The preprocessing step involves noise removal, missing value imputation, and format standardization. For example, information about "numbness in the hands" and "nausea" is tokenized as "suspected carpal tunnel syndrome."

[0558] Input: Symptom data sent to the server

[0559] Output: Preprocessed data

[0560] Step 4:

[0561] The server inputs the preprocessed data into a generative AI model to identify diseases.

[0562] The AI ​​model is trained on past medical data and diagnostic information to calculate identified diseases and their predicted probabilities, generating results such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%."

[0563] Input: Preprocessed data

[0564] Output: Identified diseases and their predicted probabilities by the generative AI model

[0565] Step 5:

[0566] The server formats the identified diseases and their predicted probabilities and transmits them to the terminal.

[0567] The results are formatted in lists and graphs to make them easy for drivers to understand, and the data is sent again using the HTTPS protocol.

[0568] Input: Identified diseases and their predicted probabilities by the generative AI model

[0569] Output: Formatted result data sent to the terminal

[0570] Step 6:

[0571] The terminal displays the received identified diseases and their predicted probabilities on a user interface.

[0572] The display format can be, for example, a list format or a graph format, allowing the driver to check the results in real time and take any necessary measures.

[0573] Input: Formatted result data sent to the terminal

[0574] Output: Identified diseases and their predicted probabilities displayed in a user interface

[0575] In this way, the symptom information entered by the user is processed on the server, the disease is identified using a generative AI model, and the results are immediately returned to the driver, enabling a prompt and appropriate response.

[0576] 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.

[0577] The present invention is a system that combines a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal, as well as an emotion engine that recognizes the user's emotions.

[0578] System Configuration

[0579] 1. Terminal

[0580] This is a device into which the user inputs information about their medical condition, symptoms, and emotional state. Specifically, it is a smartphone or PC. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[0581] 2. Server Means

[0582] The server receives symptom information sent from the device and preprocesses it. Preprocessing includes noise removal, standardizing data formats, and filling in missing values. Once preprocessed, the data is input into a generative AI model to identify the disease.

[0583] The generative AI model is trained based on past medical data and diagnostic information to achieve highly accurate disease identification. As a diagnostic result, a list of identified diseases and their predicted probabilities is generated and sent to the device.

[0584] 3. Emotion Engine

[0585] The server also has an emotion engine that recognizes the user's emotional state. This emotion engine analyzes text information and voice data entered by the user and extracts their emotional state. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[0586] 4. Secure Communication Protocols

[0587] The security of information is ensured by the protocol used when sending and receiving information between the device and the server. HTTPS is generally used.

[0588] 5. Display means

[0589] The terminal displays the list of identified diseases and their predicted probabilities, as well as the analysis results of the emotional state, on a user interface. Based on this information, the user can quickly decide on their next course of action.

[0590] Program processing

[0591] 1. Data Entry

[0592] The user inputs their symptoms and emotional state into the device. Symptom information is entered as "joint pain" or "fatigue," and emotional information is entered as "stress" or "anxiety," using free-form text or voice data.

[0593] 2. Data Transmission

[0594] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[0595] 3. Data Reception and Preprocessing

[0596] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing such as noise removal and missing value completion, and standardizes the data format.

[0597] 4. Emotion analysis

[0598] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data.

[0599] 5. Feature Extraction

[0600] The server extracts important features from the preprocessed symptom information and emotion information, such as "joint pain," "fatigue," and "stress."

[0601] 6. Input to the AI ​​model

[0602] The server inputs the extracted feature information into a generative AI model to identify the disease.

[0603] 7. Disease Identification and Outcome Generation

[0604] The server organizes the list of diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually easy-to-understand format (e.g., JSON format).

[0605] 8. Send results

[0606] The server transmits the formatted prediction result data to the terminal.

[0607] 9. Results display

[0608] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[0609] Specific examples

[0610] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, and the user decides on the next action.

[0611] This system can quickly identify diseases that are difficult to diagnose and provide more accurate diagnostic results that take into account the user's emotional state.

[0612] The processing flow will be explained below.

[0613] Step 1:

[0614] The user inputs information about their medical condition and emotions into an input terminal. Specifically, they input free-form text or voice data such as "My joints hurt when I wake up in the morning, and I feel more tired and stressed in the evening."

[0615] Step 2:

[0616] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol such as HTTPS.

[0617] Step 3:

[0618] The server receives data packets sent from the device, and then validates them to ensure they were sent correctly and checks for inaccurate or lost data.

[0619] Step 4:

[0620] The server preprocesses the received data, which may include noise reduction (e.g., removing nonsense text or audio), spam filtering, missing value imputation, and data formatting standardization (e.g., converting all text to lowercase).

[0621] Step 5:

[0622] The server analyzes the preprocessed data and extracts specific keywords and phrases, such as symptoms and emotional characteristics like "joint pain," "fatigue," and "stress."

[0623] Step 6:

[0624] The server passes the extracted feature data to the emotion engine, which analyzes the user's emotional state (e.g., "stress" or "anxiety") from the text and voice data and converts it into a numerical value or categorization.

[0625] Step 7:

[0626] The server combines the emotion information obtained from the emotion engine with the pre-processed symptom information and inputs it into a generative AI model, which is trained on past medical data and diagnostic information.

[0627] Step 8:

[0628] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[0629] Step 9:

[0630] The server formats the generated prediction results and emotion information into a visually easy-to-understand format (e.g., JSON format).

[0631] Step 10:

[0632] The server then transmits the formatted prediction result data to the terminal again using a secure communication protocol such as HTTPS.

[0633] Step 11:

[0634] The device analyzes the received prediction result data and emotion information and displays them on the user interface. For example, the identified disease and its predicted probability, results such as "rheumatoid arthritis: 60%," "systemic lupus erythematosus: 30%," and "stress level: high" are displayed in graph and list format.

[0635] Step 12:

[0636] The user checks the displayed results and, based on the information about their health condition, consults with a medical institution as necessary and makes a treatment plan.

[0637] Example 2

[0638] 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."

[0639] Conventional medical diagnostic systems do not take into account the user's emotional state, making it difficult to identify diseases caused by urgency or psychological factors. Furthermore, preprocessing of input symptom information is insufficient, making it difficult to remove noise and complete missing values, resulting in low diagnostic accuracy. Furthermore, the lack of secure communication protocols means that data security cannot be guaranteed. These issues must be resolved to achieve more accurate and rapid disease identification.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0641] In this invention, the server includes a means for preprocessing the received symptom information, a means including an emotion engine for recognizing the user's emotional state, and a means for identifying a disease using a generative AI model based on the preprocessed symptom information, thereby enabling highly accurate disease identification that takes the user's emotional state into consideration.

[0642] "Symptom information" is information about a medical condition or physical condition entered by a user.

[0643] A "terminal" is a device through which a user inputs symptom information, and examples include a smartphone and a personal computer.

[0644] The "server means" refers to a server that processes symptom information received from a terminal and performs various analyses and data transmissions.

[0645] "Preprocessing" refers to processes such as removing noise from received symptom information, filling in missing values, and standardizing data formats.

[0646] A "generative AI model" is an artificial intelligence model trained based on past medical data and diagnostic information, and is a technology that enables highly accurate disease identification.

[0647] "Disease identification" refers to the process of using generative AI models to identify possible diseases based on specific symptoms.

[0648] "Predicted probability" is a numerical value that indicates the probability that the generative AI model estimates for a specified disease.

[0649] An "emotion engine" is a system that includes software functions for analyzing a user's emotional state from text information and voice data.

[0650] A "secure communication protocol" is a communication protocol used by a terminal and a server means to send and receive information securely, and a specific example of this is HTTPS.

[0651] "User interface" refers to an interface for visually displaying information to a user on a terminal.

[0652] This invention is a system that includes a terminal where a user inputs their own symptom information and emotional state, a server means for preprocessing the received symptom information and identifying a disease using a generative AI model, and a means for displaying the identified disease and its predicted probability. The system also includes an emotion engine that recognizes the user's emotional state.

[0653] First, the user inputs their symptom information and emotional state using a device such as a smartphone or PC. Symptom information includes such things as "My joints hurt when I wake up in the morning" and "I get tired easily in the evening," while emotional information includes free-form text and voice data such as "I feel stressed" and "I feel anxious."

[0654] The terminal then converts the input information into data packets and transmits them to the server using a secure communication protocol (e.g., HTTPS).

[0655] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing to remove noise from the data, fill in missing values, and standardize the data format. Preprocessing also includes converting voice data to text and formatting text data for sentiment analysis.

[0656] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it detects "stress" from text data and analyzes "anxiety" from voice data. The results of the emotion analysis are also used as input data for the generative AI model.

[0657] Next, the server extracts key features from the preprocessed symptom and emotion information. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. This feature information is input into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[0658] Once the generative AI model has obtained the list of diseases and their predicted probabilities, the server formats it into a visually understandable format (e.g., JSON), and the formatted result data is sent to the device.

[0659] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid Arthritis: 60%," "Systemic Lupus Erythematosus: 30%," and "Stress Level: High" are displayed. Based on this information, the user can quickly decide on their next course of action.

[0660] Specific examples

[0661] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device converts this information into a data packet and sends it to the server using HTTPS. The server validates the received data and performs preprocessing such as missing value completion and noise removal. The emotion engine analyzes "stress," and the server extracts "joint pain," "fatigue," and "stress" as features. The feature information is input into the generative AI model, which generates the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus." This resulting data is sent to the device, which displays the results on the user interface.

[0662] Prompt Sentence Examples

[0663] "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed. Could you please tell me what illnesses these symptoms could suggest?"

[0664] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0665] Step 1: Data entry

[0666] The user inputs their symptoms and emotional state into the device. For example, they can input text or voice data such as "My joints hurt when I wake up in the morning," "I get tired easily in the evening," or "I feel stressed."

[0667] Input: Symptom information and emotion information (text and audio data)

[0668] Output: Data packets

[0669] Step 2: Send data

[0670] The terminal converts the input information into data packets and transmits them to the server using a secure communication protocol (for example, HTTPS).

[0671] Input: Data packet

[0672] Output: Data sent to the server

[0673] Step 3: Data Receipt and Validation

[0674] The server receives the data sent from the terminal and performs validation on the received data, checking the format and content (e.g., checking for missing values, checking the data format, etc.).

[0675] Input: Received data

[0676] Output: Validated data

[0677] Step 4: Data Preprocessing

[0678] The server performs preprocessing on the data that has passed validation, such as removing noise, filling in missing values, and standardizing the data format, to prepare the data in a format suitable for analysis.

[0679] Input: Validated data

[0680] Output: Preprocessed data

[0681] Step 5: Sentiment Analysis

[0682] The server passes a portion of the preprocessed data to the emotion engine, which analyzes the user's emotional state by detecting "stress" from the text data and "anxiety" from the voice data.

[0683] Input: Preprocessed data

[0684] Output: Emotion analysis results

[0685] Step 6: Feature Extraction

[0686] The server extracts key features from the preprocessed symptom and emotion information, such as "joint pain," "fatigue," and "stress."

[0687] Input: Preprocessed data and sentiment analysis results

[0688] Output: Extracted feature data

[0689] Step 7: Input to the AI ​​model

[0690] The server inputs the extracted feature information into a generative AI model, which has been previously trained on past medical data and diagnostic information.

[0691] Input: Extracted feature data

[0692] Output: AI-identified disease data

[0693] Step 8: Disease identification and outcome generation

[0694] The server retrieves the diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually understandable format (e.g., JSON format).

[0695] Input: AI-identified disease data

[0696] Output: Formatted result data

[0697] Step 9: Send results

[0698] The server transmits the formatted prediction result data to the terminal.

[0699] Input: Formatted result data

[0700] Output: Data sent to the terminal

[0701] Step 10: View the results

[0702] The device then displays the received prediction data and emotion analysis results on a user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[0703] Input: Submitted result data

[0704] Output: what is displayed to the user

[0705] (Application example 2)

[0706] 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."

[0707] In modern society, there is a demand for rapid and accurate disease identification based on each individual's health and emotional state. However, many systems perform diagnosis without taking emotional information into account, resulting in low accuracy of diagnostic results. Furthermore, there is a lack of systems that provide advertisements for appropriate products and services based on identified disease information. Therefore, there is a need for a system that analyzes a user's symptom information and emotional information, identifies a disease based on that information, and then displays relevant advertisements based on the identified disease information.

[0708] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal that inputs information about symptoms, server means that preprocesses the symptom information received from the terminal, server means that identifies a disease using a generative AI model based on the preprocessed symptom information, server means that transmits the identified disease and its predicted probability to the terminal, means for displaying advertisements for related products and services based on the disease information displayed on the terminal, an emotion engine that inputs and analyzes emotion information, and means for displaying the identified disease and its predicted probability on the terminal. This enables highly accurate disease identification that takes the user's emotional state into consideration, and further makes it possible to display advertisements for appropriate products and services based on the identified disease.

[0709] A "terminal" is a device that allows a user to input information about symptoms and emotions.

[0710] The "server means" is a server that processes symptom information and emotion information received from the terminal and identifies diseases using a generative AI model.

[0711] A "generative AI model" is an AI algorithm that is trained based on past medical data and diagnostic information and identifies diseases based on the user's symptoms and emotional information.

[0712] An "emotion engine" is an engine that has the function of analyzing text and voice input by the user and extracting their emotional state.

[0713] A "secure communication protocol" is a communication method that ensures the security of information when sending and receiving data between a terminal and a server.

[0714] The "display means" is a function that displays the identified disease, its predicted probability, and related advertisements sent from the server on the user interface.

[0715] The "means for displaying advertisements" is a function for providing users with advertisements for related products and services based on the identified disease information.

[0716] The present invention is a system that includes a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, an emotion engine for recognizing the user's emotions, and a function for displaying the identified disease and its predicted probability, as well as means for displaying advertisements for related products and services.

[0717] System Configuration

[0718] 1. Terminal

[0719] A device into which a user inputs information about their medical condition, symptoms, and emotional state. Specifically, a smartphone, smart glasses, or PC can be used. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[0720] 2. Server Means

[0721] The server receives the symptom information sent from the device and performs preprocessing, which includes noise removal, data format standardization, and missing value completion. After preprocessing is complete, the data is input into a generative AI model to identify diseases. A list of identified diseases and their predicted probabilities is sent to the device.

[0722] The server also has an emotion engine that analyzes the user's emotional state by analyzing the text information and voice data entered by the user. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[0723] 3. Secure Communication Protocols

[0724] A protocol used when a terminal and a server send and receive information. HTTPS is generally used.

[0725] 4. Display means

[0726] The terminal displays a list of identified diseases and their predicted probabilities sent from the server, as well as advertisements for related products and services, on the user interface, allowing the user to quickly decide their next course of action based on this information.

[0727] Specific examples

[0728] The user inputs into the smart glasses, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, along with advertisements for related products and services. The user can then decide on appropriate actions based on this.

[0729] Example prompt sentence:

[0730] "I've had a headache since this morning and I feel really sick."

[0731] "Recently, my joints have been hurting and I've been feeling tired easily."

[0732] This invention realizes a system that comprehensively analyzes a user's symptoms and emotional state and provides the user with optimal information and services.

[0733] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0734] Step 1:

[0735] The user inputs their symptoms and emotional state into the device. This input information includes text and voice data. Specifically, the user inputs a prompt sentence such as "I've had a headache since this morning and I feel very unwell" using smart glasses or a smartphone. This input information is converted into a data packet.

[0736] Step 2:

[0737] The device sends the input information to the server using a secure communication protocol (e.g., HTTPS). The input here is symptom information and emotion information entered by the user, and this becomes the output sent to the server.

[0738] Step 3:

[0739] The server preprocesses the received data, including removing noise, standardizing data formats, and filling in missing values. The input is the raw data sent from the device, and the output is clean data that has undergone preprocessing.

[0740] Step 4:

[0741] The server passes the preprocessed data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data. The input is the preprocessed symptom and emotion data, and the output is the analysis result including the emotional state.

[0742] Step 5:

[0743] The server extracts important features from the preprocessed symptom information and the analysis results of the emotion engine. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. The input is the preprocessed data and the emotion analysis results, and the output is the extracted feature information.

[0744] Step 6:

[0745] The server inputs the extracted feature information into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification. The input is feature information, and the output is a list of identified diseases and their predicted probabilities.

[0746] Step 7:

[0747] The server organizes the list of identified diseases and their predicted probabilities and formats them into a visually understandable format (e.g., JSON format). The input is the output of the generative AI model, and the formatted prediction result data is obtained.

[0748] Step 8:

[0749] The server sends the formatted prediction result data to the terminal. The input here is the formatted prediction result data, and the output sent to the terminal.

[0750] Step 9:

[0751] The device displays advertisements for related products and services on the user interface based on the received prediction result data and emotion analysis results. Specifically, based on results such as "Migraine: 70%" and "Mood Depression: Strong," advertisements for supplements effective against migraines or relaxing yoga classes are displayed. The input is the prediction result data and emotion analysis results from the server, and the output is what is displayed on the user interface.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] [Third embodiment]

[0756] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0757] 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.

[0758] 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).

[0759] 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.

[0760] 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.

[0761] 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).

[0762] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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."

[0768] The present invention is a system including a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal.

[0769] System Configuration

[0770] 1. Terminal

[0771] A device where the user inputs information about their condition or symptoms. Typically, a smartphone or PC is used. The device converts the input information into data packets and sends them to a server using a secure communication protocol.

[0772] 2. Server Means

[0773] The server receives symptom information sent from the terminal and performs preprocessing on it, such as removing noise, filling in missing values, and standardizing the format.

[0774] The preprocessed data is then fed into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[0775] As a diagnostic result, a list of identified diseases and their predicted probabilities is generated, formatted, and sent to the terminal.

[0776] 3. Secure Communication Protocols

[0777] This is a protocol used when a device and a server send and receive information, ensuring the security of the information. HTTPS is generally used.

[0778] 4. Display means

[0779] The terminal displays the list of identified diseases and their predicted probabilities sent from the server on the user interface, allowing the user to obtain detailed information about their medical condition.

[0780] Program processing

[0781] 1. Data Entry

[0782] The user inputs information about their symptoms, such as "joint pain" or "fatigue," into the terminal.

[0783] The terminal transmits the input information to the server.

[0784] 2. Data Processing

[0785] The server preprocesses the received data and extracts features. For example, the input information "joint pain" is tokenized as "joint pain."

[0786] 3. Disease Identification Using AI Models

[0787] The server inputs the preprocessed data into a generative AI model to identify diseases. The AI ​​model calculates the predicted probability for each disease, yielding results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[0788] 4. Returning the results

[0789] The server formats the results and sends them to the terminal.

[0790] The terminal displays the results on a user interface, for example, showing identified diseases and their predicted probabilities in graph or list format.

[0791] Specific examples

[0792] The user inputs symptoms into the device, such as "I have joint pain when I wake up in the morning and get tired easily in the evening." The device then sends this input data to the server, which preprocesses the received data and extracts features. The server then uses a generative AI model to identify the disease and calculates probabilities such as "rheumatoid arthritis 60%" and "systemic lupus erythematosus 30%." These results are then formatted and sent to the device. Finally, the device displays the results on a user interface, allowing the user to instantly access detailed information about their condition.

[0793] This system can quickly identify diseases that are difficult to diagnose in hospitals, enabling patients to receive early treatment and receive consultations with appropriate medical institutions, which is expected to improve patients' health and quality of life.

[0794] The processing flow will be explained below.

[0795] Step 1:

[0796] The user inputs information about the condition or symptoms into an input terminal. For example, the user selects symptoms from free-form text data such as "joint pain" or "fatigue" or from multiple-choice options.

[0797] Step 2:

[0798] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[0799] Step 3:

[0800] The server receives the data packet sent from the terminal and performs validation to confirm that the data was sent correctly.

[0801] Step 4:

[0802] The server preprocesses the received data, specifically removing noise, filtering spam, imputing missing values, and standardizing data formats. For example, "joint pain" is standardized to "arthritis."

[0803] Step 5:

[0804] The server extracts important features from the preprocessed data, such as keywords and features like "joint pain," "fatigue," "morning," and "evening," and converts them into numerical and categorical data.

[0805] Step 6:

[0806] The server inputs the extracted features into a generative AI model, which is trained on a vast amount of historical medical data and diagnostic information.

[0807] Step 7:

[0808] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[0809] Step 8:

[0810] The server organizes the prediction results obtained from the AI ​​model and formats them into a format that is easy to understand visually (for example, JSON format).

[0811] Step 9:

[0812] The server transmits the formatted prediction result data to the terminal using a secure communication protocol.

[0813] Step 10:

[0814] The device analyzes the received prediction result data and displays the results on the user interface. For example, results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" are displayed in graph and list format.

[0815] Step 11:

[0816] The user checks the displayed results and decides on the next action to take, such as early diagnosis or consulting an appropriate medical institution.

[0817] Example 1

[0818] 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."

[0819] In today's medical environment, rapid and accurate symptom-based disease identification remains a challenge. Delays in diagnosis, especially for diseases that are difficult to diagnose in hospitals, can result in missed opportunities for treatment, leading to a deterioration in health and quality of life. Conventional systems require a cumbersome process from symptom input to disease identification, and lack secure data transmission and highly accurate prediction. There is a need for a support system that can solve these problems and enable patients to receive appropriate medical treatment promptly.

[0820] 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.

[0821] In this invention, the server includes an information terminal means for inputting symptom information, a data processing means for preprocessing the symptom information received from the terminal, an analysis means for identifying a disease using a generative AI model based on the preprocessed symptom information, a communication means for transmitting the identified disease and its predicted probability to the terminal, and a display means for displaying the identified disease and its predicted probability on the terminal. This makes it possible to quickly and accurately analyze the symptom information input by the user, safely transmit the identified disease and its predicted probability, and immediately display it on the terminal.

[0822] The "information terminal means for inputting information about symptoms" refers to a device used by the user to input medical conditions and symptoms, and includes smartphones, personal computers, etc.

[0823] The "data processing means for preprocessing the symptom information received from the terminal" refers to a device or software that analyzes the symptom information sent from the terminal and performs noise removal, missing value complementation, format standardization, etc.

[0824] "Analysis means for identifying diseases using a generative AI model based on preprocessed symptom information" refers to a device or software that inputs preprocessed data into an AI model and identifies diseases based on past medical data and diagnostic information.

[0825] The "communication means for transmitting the identified disease and its predicted probability to the terminal" is a device or software that formats the analysis results and transmits them to the terminal using a secure communication protocol.

[0826] The "display means for displaying the identified disease and its predicted probability on the terminal" refers to a device or software that displays the analysis results received on the terminal on a user interface so that the user can check them.

[0827] A "generative AI model" is an artificial intelligence model that is trained on past medical data and diagnostic information and is capable of predicting disease based on symptom information.

[0828] A "secure communication protocol" is a protocol that encrypts data transmission and reception to ensure safety, and generally includes HTTPS.

[0829] This invention is a system that includes an information terminal means for inputting information about symptoms, a data processing means for performing preprocessing, an analysis means for identifying diseases using a generative AI model, a communication means, and a display means.

[0830] System Configuration

[0831] 1. Information terminal means

[0832] User: Enters symptom information using an information terminal such as a smartphone or PC. For example, a smartphone app or web interface is provided, allowing the user to enter symptoms. An example of a prompt sentence could be, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[0833] 2. Data processing means

[0834] Server: Preprocesses the symptom information received from the device. Preprocessing includes spell checking, noise removal, missing value completion, and format standardization. For example, data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." The information is also tokenized to extract features such as "joint pain" and "fatigue."

[0835] 3. Analysis method

[0836] Server: The preprocessed data is input into a generative AI model to identify diseases. The generative AI model used is trained based on past medical data and diagnostic information. The AI ​​model calculates the predicted probability for each disease based on the user's symptom information. For example, it outputs results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%."

[0837] 4. Means of communication

[0838] Server and terminal: The identified diseases and their predicted probabilities are transmitted to the terminal using a secure communication protocol (e.g., HTTPS) to ensure data integrity and confidentiality.

[0839] 5. Display means

[0840] Terminal: The received analysis results are displayed on a user interface, allowing the user to check the identified diseases and their predicted probabilities. The results are displayed in graph and list format. For example, a list of diseases such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" and their predicted probabilities are visually displayed.

[0841] Specific examples

[0842] The user inputs symptoms such as "I have joint pain when I wake up in the morning, and I get tired easily in the evening" using an information terminal. The terminal converts this information into a data packet and sends it to the server. The server preprocesses the received data and tokenizes the information "I have joint pain when I wake up in the morning, and I get tired easily in the evening" as "joint pain" and "fatigue." The preprocessed data is input into a generative AI model, which calculates predicted probabilities such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%." These results are formatted in JSON and sent to the terminal using a secure communication protocol. Finally, the terminal displays the received results on a user interface, allowing the user to visually confirm the identified diseases and their predicted probabilities.

[0843] This system will enable the rapid and accurate identification of diseases that are difficult to diagnose in hospitals, enabling patients to receive appropriate medical treatment at an early stage, which is expected to improve their health and quality of life.

[0844] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0845] Program processing flow

[0846] Step 1:

[0847] The user inputs symptom information using the information terminal means.

[0848] Specific actions: The user accesses the application or web interface on their smartphone or computer and inputs specific symptoms according to the prompts. For example, they might input, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[0849] Input: Symptom information ("My joints hurt when I wake up in the morning, and I get tired easily in the evening.")

[0850] Output: Symptom information entered into the terminal

[0851] Step 2:

[0852] The terminal transmits the input symptom information to the server.

[0853] Specific operation: The terminal converts the input symptom information into data packets and sends them to the server using a secure communication protocol (HTTPS).

[0854] Input: Symptom information entered into the terminal

[0855] Output: Symptom information sent to the server

[0856] Step 3:

[0857] The server preprocesses the received symptom information.

[0858] Specific operation: The server cleanses the received symptom information, removing noise and filling in missing values. It also standardizes the format of the information, e.g., data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." It then tokenizes the information as "joint pain" and "fatigue."

[0859] Input: Symptom information sent to the server

[0860] Output: Preprocessed and tokenized data

[0861] Step 4:

[0862] The server inputs the preprocessed symptom information into a generative AI model to identify the disease.

[0863] How it works: The server inputs the preprocessed data into a generative AI model. The AI ​​model is trained based on past medical data and diagnostic information and calculates the predicted probability for each disease. For example, it can produce results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[0864] Input: Preprocessed and tokenized data

[0865] Output: Predicted probability for each disease (rheumatoid arthritis: 60%, systemic lupus erythematosus: 30%)

[0866] Step 5:

[0867] The server formats the diagnostic results and sends them to the terminal.

[0868] Specific operation: The server formats the identified diseases and their predicted probabilities into an easy-to-read format (e.g., JSON format) and sends them to the terminal using a secure communication protocol (HTTPS).

[0869] Input: Predicted probability for each disease

[0870] Output: Formatted data, diagnostic results sent to terminal

[0871] Step 6:

[0872] The terminal displays the diagnostic results on the user interface.

[0873] Specific operation: The terminal application or web interface receives and analyzes the formatted diagnosis results sent from the server. The identified diseases and their predicted probabilities are displayed in the user interface in the form of a graph or list.

[0874] Input: Diagnostic results sent to the terminal

[0875] Output: Identified diseases and their predicted probabilities displayed in a user interface

[0876] Through the above steps, the user can quickly and accurately understand his or her own health condition and receive support to receive necessary medical treatment.

[0877] (Application example 1)

[0878] 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."

[0879] In modern autonomous vehicles, long driving times and driver health management are important issues. However, there is a lack of means to immediately respond when a driver feels unwell, making it difficult to take appropriate measures or respond quickly. In particular, when a health problem occurs while driving, immediate access to appropriate medical support is required, but current systems make it difficult to respond quickly.

[0880] 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.

[0881] In this invention, the server includes an interface means that allows the driver of the autonomous vehicle to input symptom information, a means for processing the symptom information input by the driver in real time and identifying a disease using a generative AI model, and a means for presenting information on the identified disease and its predicted probability to the driver, thereby enabling the driver to manage their own health condition in real time and take necessary measures promptly.

[0882] "Symptom information" is information relating to the specific physical condition or health state that the driver feels.

[0883] A "terminal" is a device through which the driver inputs symptom information, and specifically includes a smartphone or a head-mounted display installed in the vehicle.

[0884] "Server means" refers to a central processing unit that processes the received symptom information and identifies the disease using a generative AI model.

[0885] "Preprocessing" refers to processing the received symptom information by methods such as noise removal, missing value completion, and format standardization.

[0886] A "generative AI model" is a machine learning model trained on past medical data and diagnostic information to identify diseases from symptom information.

[0887] "Disease" refers to a specific illness or disorder that causes physical abnormalities or discomfort.

[0888] "Prediction probability" refers to the probability that a disease will be identified by the generative AI model, and indicates the likelihood that the identified disease applies to the driver.

[0889] The "interface means" is a user interface that allows the driver to easily input symptom information through an input device.

[0890] "Real-time processing" means that the input symptom information is immediately sent to the server, and disease identification and prediction probability calculation are performed quickly based on that information.

[0891] "Presentation means" refers to a display method or audio guidance for immediately visually or audibly informing the driver of the identified disease and its predicted probability.

[0892] The present invention provides a system for enabling a driver of an autonomous vehicle to monitor his or her own health condition in real time. The system includes a driver terminal, a server means, a generative AI model, a secure communication protocol, and an interface means.

[0893] Terminal

[0894] The terminal is a device that the driver uses to input symptom information. This device can be a smartphone or a head-mounted display (HMD) installed in the vehicle. The terminal is responsible for transmitting the symptom information input by the driver to the server.

[0895] Server Means

[0896] The server preprocesses the symptom information received from the device and identifies diseases using a generative AI model. Preprocessing includes noise removal, missing value completion, and format standardization. The preprocessed data is input into the generative AI model, which performs highly accurate disease identification.

[0897] Generative AI Models

[0898] A generative AI model is a machine learning model trained on past medical data and diagnostic information. This model predicts diseases based on input symptom information and calculates the predicted probability.

[0899] Secure Communication Protocol

[0900] Secure communication protocols such as HTTPS are used to send and receive information between the device and the server, ensuring the safety of the information.

[0901] Interface Means

[0902] The interface means is a user interface that allows the driver to easily input symptom information, and specifically supports voice input and text input.

[0903] Specific examples

[0904] If a driver experiences "numbness in the hands" and "nausea," they can input their symptoms into the HMD by voice. The HMD converts the voice input into text and sends it to the server. The server preprocesses the symptom data and identifies the illness using a generative AI model. This produces predictions such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%." These results are displayed on the HMD, allowing the driver to take appropriate action based on their physical condition (e.g., take a break, consult a doctor, etc.).

[0905] Prompt Sentence Examples

[0906] User: Enter symptoms: "numbness in hands," "nausea"

[0907] System: Running diagnostics...

[0908] System:Result - 70% chance of carpal tunnel syndrome, 20% chance of anemia. Showing more information.

[0909] This system allows drivers to monitor their own health status in real time and take necessary measures promptly.

[0910] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0911] Step 1:

[0912] The user inputs their symptom information into the terminal.

[0913] Specific symptoms can be entered in voice or text format, such as "numbness in hands" or "nausea." The device converts this symptom information into text data and formats it in JSON format.

[0914] Input: Symptom information in spoken or text form

[0915] Output: Symptom data in JSON format

[0916] Step 2:

[0917] The terminal transmits the input symptom information to the server.

[0918] The HTTPS protocol is used to ensure secure communication, and transmitted data is encrypted end-to-end.

[0919] Input: Symptom data in JSON format

[0920] Output: Symptom data sent to the server

[0921] Step 3:

[0922] The server pre-processes the received symptom information.

[0923] The preprocessing step involves noise removal, missing value imputation, and format standardization. For example, information about "numbness in the hands" and "nausea" is tokenized as "suspected carpal tunnel syndrome."

[0924] Input: Symptom data sent to the server

[0925] Output: Preprocessed data

[0926] Step 4:

[0927] The server inputs the preprocessed data into a generative AI model to identify diseases.

[0928] The AI ​​model is trained on past medical data and diagnostic information to calculate identified diseases and their predicted probabilities, generating results such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%."

[0929] Input: Preprocessed data

[0930] Output: Identified diseases and their predicted probabilities by the generative AI model

[0931] Step 5:

[0932] The server formats the identified diseases and their predicted probabilities and transmits them to the terminal.

[0933] The results are formatted in lists and graphs to make them easy for drivers to understand, and the data is sent again using the HTTPS protocol.

[0934] Input: Identified diseases and their predicted probabilities by the generative AI model

[0935] Output: Formatted result data sent to the terminal

[0936] Step 6:

[0937] The terminal displays the received identified diseases and their predicted probabilities on a user interface.

[0938] The display format can be, for example, a list format or a graph format, allowing the driver to check the results in real time and take any necessary measures.

[0939] Input: Formatted result data sent to the terminal

[0940] Output: Identified diseases and their predicted probabilities displayed in a user interface

[0941] In this way, the symptom information entered by the user is processed on the server, the disease is identified using a generative AI model, and the results are immediately returned to the driver, enabling a prompt and appropriate response.

[0942] 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.

[0943] The present invention is a system that combines a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal, as well as an emotion engine that recognizes the user's emotions.

[0944] System Configuration

[0945] 1. Terminal

[0946] This is a device into which the user inputs information about their medical condition, symptoms, and emotional state. Specifically, it is a smartphone or PC. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[0947] 2. Server Means

[0948] The server receives symptom information sent from the device and preprocesses it. Preprocessing includes noise removal, standardizing data formats, and filling in missing values. Once preprocessed, the data is input into a generative AI model to identify the disease.

[0949] The generative AI model is trained based on past medical data and diagnostic information to achieve highly accurate disease identification. As a diagnostic result, a list of identified diseases and their predicted probabilities is generated and sent to the device.

[0950] 3. Emotion Engine

[0951] The server also has an emotion engine that recognizes the user's emotional state. This emotion engine analyzes text information and voice data entered by the user and extracts their emotional state. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[0952] 4. Secure Communication Protocols

[0953] The security of information is ensured by the protocol used when sending and receiving information between the device and the server. HTTPS is generally used.

[0954] 5. Display means

[0955] The terminal displays the list of identified diseases and their predicted probabilities, as well as the analysis results of the emotional state, on a user interface. Based on this information, the user can quickly decide on their next course of action.

[0956] Program processing

[0957] 1. Data Entry

[0958] The user inputs their symptoms and emotional state into the device. Symptom information is entered as "joint pain" or "fatigue," and emotional information is entered as "stress" or "anxiety," using free-form text or voice data.

[0959] 2. Data Transmission

[0960] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[0961] 3. Data Reception and Preprocessing

[0962] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing such as noise removal and missing value completion, and standardizes the data format.

[0963] 4. Emotion analysis

[0964] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data.

[0965] 5. Feature Extraction

[0966] The server extracts important features from the preprocessed symptom information and emotion information, such as "joint pain," "fatigue," and "stress."

[0967] 6. Input to the AI ​​model

[0968] The server inputs the extracted feature information into a generative AI model to identify the disease.

[0969] 7. Disease Identification and Outcome Generation

[0970] The server organizes the list of diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually easy-to-understand format (e.g., JSON format).

[0971] 8. Send results

[0972] The server transmits the formatted prediction result data to the terminal.

[0973] 9. Results display

[0974] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[0975] Specific examples

[0976] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, and the user decides on the next action.

[0977] This system can quickly identify diseases that are difficult to diagnose and provide more accurate diagnostic results that take into account the user's emotional state.

[0978] The processing flow will be explained below.

[0979] Step 1:

[0980] The user inputs information about their medical condition and emotions into an input terminal. Specifically, they input free-form text or voice data such as "My joints hurt when I wake up in the morning, and I feel more tired and stressed in the evening."

[0981] Step 2:

[0982] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol such as HTTPS.

[0983] Step 3:

[0984] The server receives data packets sent from the device, and then validates them to ensure they were sent correctly and checks for inaccurate or lost data.

[0985] Step 4:

[0986] The server preprocesses the received data, which may include noise reduction (e.g., removing nonsense text or audio), spam filtering, missing value imputation, and data formatting standardization (e.g., converting all text to lowercase).

[0987] Step 5:

[0988] The server analyzes the preprocessed data and extracts specific keywords and phrases, such as symptoms and emotional characteristics like "joint pain," "fatigue," and "stress."

[0989] Step 6:

[0990] The server passes the extracted feature data to the emotion engine, which analyzes the user's emotional state (e.g., "stress" or "anxiety") from the text and voice data and converts it into a numerical value or categorization.

[0991] Step 7:

[0992] The server combines the emotion information obtained from the emotion engine with the pre-processed symptom information and inputs it into a generative AI model, which is trained on past medical data and diagnostic information.

[0993] Step 8:

[0994] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[0995] Step 9:

[0996] The server formats the generated prediction results and emotion information into a visually easy-to-understand format (e.g., JSON format).

[0997] Step 10:

[0998] The server then transmits the formatted prediction result data to the terminal again using a secure communication protocol such as HTTPS.

[0999] Step 11:

[1000] The device analyzes the received prediction result data and emotion information and displays them on the user interface. For example, the identified disease and its predicted probability, results such as "rheumatoid arthritis: 60%," "systemic lupus erythematosus: 30%," and "stress level: high" are displayed in graph and list format.

[1001] Step 12:

[1002] The user checks the displayed results and, based on the information about their health condition, consults with a medical institution as necessary and makes a treatment plan.

[1003] Example 2

[1004] 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."

[1005] Conventional medical diagnostic systems do not take into account the user's emotional state, making it difficult to identify diseases caused by urgency or psychological factors. Furthermore, preprocessing of input symptom information is insufficient, making it difficult to remove noise and complete missing values, resulting in low diagnostic accuracy. Furthermore, the lack of secure communication protocols means that data security cannot be guaranteed. These issues must be resolved to achieve more accurate and rapid disease identification.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1007] In this invention, the server includes a means for preprocessing the received symptom information, a means including an emotion engine for recognizing the user's emotional state, and a means for identifying a disease using a generative AI model based on the preprocessed symptom information, thereby enabling highly accurate disease identification that takes the user's emotional state into consideration.

[1008] "Symptom information" is information about a medical condition or physical condition entered by a user.

[1009] A "terminal" is a device through which a user inputs symptom information, and examples include a smartphone and a personal computer.

[1010] The "server means" refers to a server that processes symptom information received from a terminal and performs various analyses and data transmissions.

[1011] "Preprocessing" refers to processes such as removing noise from received symptom information, filling in missing values, and standardizing data formats.

[1012] A "generative AI model" is an artificial intelligence model trained based on past medical data and diagnostic information, and is a technology that enables highly accurate disease identification.

[1013] "Disease identification" refers to the process of using generative AI models to identify possible diseases based on specific symptoms.

[1014] "Predicted probability" is a numerical value that indicates the probability that the generative AI model estimates for a specified disease.

[1015] An "emotion engine" is a system that includes software functions for analyzing a user's emotional state from text information and voice data.

[1016] A "secure communication protocol" is a communication protocol used by a terminal and a server means to send and receive information securely, and a specific example of this is HTTPS.

[1017] "User interface" refers to an interface for visually displaying information to a user on a terminal.

[1018] This invention is a system that includes a terminal where a user inputs their own symptom information and emotional state, a server means for preprocessing the received symptom information and identifying a disease using a generative AI model, and a means for displaying the identified disease and its predicted probability. The system also includes an emotion engine that recognizes the user's emotional state.

[1019] First, the user inputs their symptom information and emotional state using a device such as a smartphone or PC. Symptom information includes such things as "My joints hurt when I wake up in the morning" and "I get tired easily in the evening," while emotional information includes free-form text and voice data such as "I feel stressed" and "I feel anxious."

[1020] The terminal then converts the input information into data packets and transmits them to the server using a secure communication protocol (e.g., HTTPS).

[1021] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing to remove noise from the data, fill in missing values, and standardize the data format. Preprocessing also includes converting voice data to text and formatting text data for sentiment analysis.

[1022] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it detects "stress" from text data and analyzes "anxiety" from voice data. The results of the emotion analysis are also used as input data for the generative AI model.

[1023] Next, the server extracts key features from the preprocessed symptom and emotion information. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. This feature information is input into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[1024] Once the generative AI model has obtained the list of diseases and their predicted probabilities, the server formats it into a visually understandable format (e.g., JSON), and the formatted result data is sent to the device.

[1025] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid Arthritis: 60%," "Systemic Lupus Erythematosus: 30%," and "Stress Level: High" are displayed. Based on this information, the user can quickly decide on their next course of action.

[1026] Specific examples

[1027] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device converts this information into a data packet and sends it to the server using HTTPS. The server validates the received data and performs preprocessing such as missing value completion and noise removal. The emotion engine analyzes "stress," and the server extracts "joint pain," "fatigue," and "stress" as features. The feature information is input into the generative AI model, which generates the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus." This resulting data is sent to the device, which displays the results on the user interface.

[1028] Prompt Sentence Examples

[1029] "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed. Could you please tell me what illnesses these symptoms could suggest?"

[1030] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1031] Step 1: Data entry

[1032] The user inputs their symptoms and emotional state into the device. For example, they can input text or voice data such as "My joints hurt when I wake up in the morning," "I get tired easily in the evening," or "I feel stressed."

[1033] Input: Symptom information and emotion information (text and audio data)

[1034] Output: Data packets

[1035] Step 2: Send data

[1036] The terminal converts the input information into data packets and transmits them to the server using a secure communication protocol (for example, HTTPS).

[1037] Input: Data packet

[1038] Output: Data sent to the server

[1039] Step 3: Data Receipt and Validation

[1040] The server receives the data sent from the terminal and performs validation on the received data, checking the format and content (e.g., checking for missing values, checking the data format, etc.).

[1041] Input: Received data

[1042] Output: Validated data

[1043] Step 4: Data Preprocessing

[1044] The server performs preprocessing on the data that has passed validation, such as removing noise, filling in missing values, and standardizing the data format, to prepare the data in a format suitable for analysis.

[1045] Input: Validated data

[1046] Output: Preprocessed data

[1047] Step 5: Sentiment Analysis

[1048] The server passes a portion of the preprocessed data to the emotion engine, which analyzes the user's emotional state by detecting "stress" from the text data and "anxiety" from the voice data.

[1049] Input: Preprocessed data

[1050] Output: Emotion analysis results

[1051] Step 6: Feature Extraction

[1052] The server extracts key features from the preprocessed symptom and emotion information, such as "joint pain," "fatigue," and "stress."

[1053] Input: Preprocessed data and sentiment analysis results

[1054] Output: Extracted feature data

[1055] Step 7: Input to the AI ​​model

[1056] The server inputs the extracted feature information into a generative AI model, which has been previously trained on past medical data and diagnostic information.

[1057] Input: Extracted feature data

[1058] Output: AI-identified disease data

[1059] Step 8: Disease identification and outcome generation

[1060] The server retrieves the diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually understandable format (e.g., JSON format).

[1061] Input: AI-identified disease data

[1062] Output: Formatted result data

[1063] Step 9: Send results

[1064] The server transmits the formatted prediction result data to the terminal.

[1065] Input: Formatted result data

[1066] Output: Data sent to the terminal

[1067] Step 10: View the results

[1068] The device then displays the received prediction data and emotion analysis results on a user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[1069] Input: Submitted result data

[1070] Output: what is displayed to the user

[1071] (Application example 2)

[1072] 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."

[1073] In modern society, there is a demand for rapid and accurate disease identification based on each individual's health and emotional state. However, many systems perform diagnosis without taking emotional information into account, resulting in low accuracy of diagnostic results. Furthermore, there is a lack of systems that provide advertisements for appropriate products and services based on identified disease information. Therefore, there is a need for a system that analyzes a user's symptom information and emotional information, identifies a disease based on that information, and then displays relevant advertisements based on the identified disease information.

[1074] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal that inputs information about symptoms, server means that preprocesses the symptom information received from the terminal, server means that identifies a disease using a generative AI model based on the preprocessed symptom information, server means that transmits the identified disease and its predicted probability to the terminal, means for displaying advertisements for related products and services based on the disease information displayed on the terminal, an emotion engine that inputs and analyzes emotion information, and means for displaying the identified disease and its predicted probability on the terminal. This enables highly accurate disease identification that takes the user's emotional state into consideration, and further makes it possible to display advertisements for appropriate products and services based on the identified disease.

[1075] A "terminal" is a device that allows a user to input information about symptoms and emotions.

[1076] The "server means" is a server that processes symptom information and emotion information received from the terminal and identifies diseases using a generative AI model.

[1077] A "generative AI model" is an AI algorithm that is trained based on past medical data and diagnostic information and identifies diseases based on the user's symptoms and emotional information.

[1078] An "emotion engine" is an engine that has the function of analyzing text and voice input by the user and extracting their emotional state.

[1079] A "secure communication protocol" is a communication method that ensures the security of information when sending and receiving data between a terminal and a server.

[1080] The "display means" is a function that displays the identified disease, its predicted probability, and related advertisements sent from the server on the user interface.

[1081] The "means for displaying advertisements" is a function for providing users with advertisements for related products and services based on the identified disease information.

[1082] The present invention is a system that includes a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, an emotion engine for recognizing the user's emotions, and a function for displaying the identified disease and its predicted probability, as well as means for displaying advertisements for related products and services.

[1083] System Configuration

[1084] 1. Terminal

[1085] A device into which a user inputs information about their medical condition, symptoms, and emotional state. Specifically, a smartphone, smart glasses, or PC can be used. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[1086] 2. Server Means

[1087] The server receives the symptom information sent from the device and performs preprocessing, which includes noise removal, data format standardization, and missing value completion. After preprocessing is complete, the data is input into a generative AI model to identify diseases. A list of identified diseases and their predicted probabilities is sent to the device.

[1088] The server also has an emotion engine that analyzes the user's emotional state by analyzing the text information and voice data entered by the user. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[1089] 3. Secure Communication Protocols

[1090] A protocol used when a terminal and a server send and receive information. HTTPS is generally used.

[1091] 4. Display means

[1092] The terminal displays a list of identified diseases and their predicted probabilities sent from the server, as well as advertisements for related products and services, on the user interface, allowing the user to quickly decide their next course of action based on this information.

[1093] Specific examples

[1094] The user inputs into the smart glasses, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, along with advertisements for related products and services. The user can then decide on appropriate actions based on this.

[1095] Example prompt sentence:

[1096] "I've had a headache since this morning and I feel really sick."

[1097] "Recently, my joints have been hurting and I've been feeling tired easily."

[1098] This invention realizes a system that comprehensively analyzes a user's symptoms and emotional state and provides the user with optimal information and services.

[1099] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1100] Step 1:

[1101] The user inputs their symptoms and emotional state into the device. This input information includes text and voice data. Specifically, the user inputs a prompt sentence such as "I've had a headache since this morning and I feel very unwell" using smart glasses or a smartphone. This input information is converted into a data packet.

[1102] Step 2:

[1103] The device sends the input information to the server using a secure communication protocol (e.g., HTTPS). The input here is symptom information and emotion information entered by the user, and this becomes the output sent to the server.

[1104] Step 3:

[1105] The server preprocesses the received data, including removing noise, standardizing data formats, and filling in missing values. The input is the raw data sent from the device, and the output is clean data that has undergone preprocessing.

[1106] Step 4:

[1107] The server passes the preprocessed data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data. The input is the preprocessed symptom and emotion data, and the output is the analysis result including the emotional state.

[1108] Step 5:

[1109] The server extracts important features from the preprocessed symptom information and the analysis results of the emotion engine. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. The input is the preprocessed data and the emotion analysis results, and the output is the extracted feature information.

[1110] Step 6:

[1111] The server inputs the extracted feature information into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification. The input is feature information, and the output is a list of identified diseases and their predicted probabilities.

[1112] Step 7:

[1113] The server organizes the list of identified diseases and their predicted probabilities and formats them into a visually understandable format (e.g., JSON format). The input is the output of the generative AI model, and the formatted prediction result data is obtained.

[1114] Step 8:

[1115] The server sends the formatted prediction result data to the terminal. The input here is the formatted prediction result data, and the output sent to the terminal.

[1116] Step 9:

[1117] The device displays advertisements for related products and services on the user interface based on the received prediction result data and emotion analysis results. Specifically, based on results such as "Migraine: 70%" and "Mood Depression: Strong," advertisements for supplements effective against migraines or relaxing yoga classes are displayed. The input is the prediction result data and emotion analysis results from the server, and the output is what is displayed on the user interface.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] [Fourth embodiment]

[1122] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1123] 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.

[1124] 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).

[1125] 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.

[1126] 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.

[1127] 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).

[1128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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."

[1135] The present invention is a system including a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal.

[1136] System Configuration

[1137] 1. Terminal

[1138] A device where the user inputs information about their condition or symptoms. Typically, a smartphone or PC is used. The device converts the input information into data packets and sends them to a server using a secure communication protocol.

[1139] 2. Server Means

[1140] The server receives symptom information sent from the terminal and performs preprocessing on it, such as removing noise, filling in missing values, and standardizing the format.

[1141] The preprocessed data is then fed into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[1142] As a diagnostic result, a list of identified diseases and their predicted probabilities is generated, formatted, and sent to the terminal.

[1143] 3. Secure Communication Protocols

[1144] This is a protocol used when a device and a server send and receive information, ensuring the security of the information. HTTPS is generally used.

[1145] 4. Display means

[1146] The terminal displays the list of identified diseases and their predicted probabilities sent from the server on the user interface, allowing the user to obtain detailed information about their medical condition.

[1147] Program processing

[1148] 1. Data Entry

[1149] The user inputs information about their symptoms, such as "joint pain" or "fatigue," into the terminal.

[1150] The terminal transmits the input information to the server.

[1151] 2. Data Processing

[1152] The server preprocesses the received data and extracts features. For example, the input information "joint pain" is tokenized as "joint pain."

[1153] 3. Disease Identification Using AI Models

[1154] The server inputs the preprocessed data into a generative AI model to identify diseases. The AI ​​model calculates the predicted probability for each disease, yielding results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[1155] 4. Returning the results

[1156] The server formats the results and sends them to the terminal.

[1157] The terminal displays the results on a user interface, for example, showing identified diseases and their predicted probabilities in graph or list format.

[1158] Specific examples

[1159] The user inputs symptoms into the device, such as "I have joint pain when I wake up in the morning and get tired easily in the evening." The device then sends this input data to the server, which preprocesses the received data and extracts features. The server then uses a generative AI model to identify the disease and calculates probabilities such as "rheumatoid arthritis 60%" and "systemic lupus erythematosus 30%." These results are then formatted and sent to the device. Finally, the device displays the results on a user interface, allowing the user to instantly access detailed information about their condition.

[1160] This system can quickly identify diseases that are difficult to diagnose in hospitals, enabling patients to receive early treatment and receive consultations with appropriate medical institutions, which is expected to improve patients' health and quality of life.

[1161] The processing flow will be explained below.

[1162] Step 1:

[1163] The user inputs information about the condition or symptoms into an input terminal. For example, the user selects symptoms from free-form text data such as "joint pain" or "fatigue" or from multiple-choice options.

[1164] Step 2:

[1165] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[1166] Step 3:

[1167] The server receives the data packet sent from the terminal and performs validation to confirm that the data was sent correctly.

[1168] Step 4:

[1169] The server preprocesses the received data, specifically removing noise, filtering spam, imputing missing values, and standardizing data formats. For example, "joint pain" is standardized to "arthritis."

[1170] Step 5:

[1171] The server extracts important features from the preprocessed data, such as keywords and features like "joint pain," "fatigue," "morning," and "evening," and converts them into numerical and categorical data.

[1172] Step 6:

[1173] The server inputs the extracted features into a generative AI model, which is trained on a vast amount of historical medical data and diagnostic information.

[1174] Step 7:

[1175] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[1176] Step 8:

[1177] The server organizes the prediction results obtained from the AI ​​model and formats them into a format that is easy to understand visually (for example, JSON format).

[1178] Step 9:

[1179] The server transmits the formatted prediction result data to the terminal using a secure communication protocol.

[1180] Step 10:

[1181] The device analyzes the received prediction result data and displays the results on the user interface. For example, results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" are displayed in graph and list format.

[1182] Step 11:

[1183] The user checks the displayed results and decides on the next action to take, such as early diagnosis or consulting an appropriate medical institution.

[1184] Example 1

[1185] 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."

[1186] In today's medical environment, rapid and accurate symptom-based disease identification remains a challenge. Delays in diagnosis, especially for diseases that are difficult to diagnose in hospitals, can result in missed opportunities for treatment, leading to a deterioration in health and quality of life. Conventional systems require a cumbersome process from symptom input to disease identification, and lack secure data transmission and highly accurate prediction. There is a need for a support system that can solve these problems and enable patients to receive appropriate medical treatment promptly.

[1187] 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.

[1188] In this invention, the server includes an information terminal means for inputting symptom information, a data processing means for preprocessing the symptom information received from the terminal, an analysis means for identifying a disease using a generative AI model based on the preprocessed symptom information, a communication means for transmitting the identified disease and its predicted probability to the terminal, and a display means for displaying the identified disease and its predicted probability on the terminal. This makes it possible to quickly and accurately analyze the symptom information input by the user, safely transmit the identified disease and its predicted probability, and immediately display it on the terminal.

[1189] The "information terminal means for inputting information about symptoms" refers to a device used by the user to input medical conditions and symptoms, and includes smartphones, personal computers, etc.

[1190] The "data processing means for preprocessing the symptom information received from the terminal" refers to a device or software that analyzes the symptom information sent from the terminal and performs noise removal, missing value complementation, format standardization, etc.

[1191] "Analysis means for identifying diseases using a generative AI model based on preprocessed symptom information" refers to a device or software that inputs preprocessed data into an AI model and identifies diseases based on past medical data and diagnostic information.

[1192] The "communication means for transmitting the identified disease and its predicted probability to the terminal" is a device or software that formats the analysis results and transmits them to the terminal using a secure communication protocol.

[1193] The "display means for displaying the identified disease and its predicted probability on the terminal" refers to a device or software that displays the analysis results received on the terminal on a user interface so that the user can check them.

[1194] A "generative AI model" is an artificial intelligence model that is trained on past medical data and diagnostic information and is capable of predicting disease based on symptom information.

[1195] A "secure communication protocol" is a protocol that encrypts data transmission and reception to ensure safety, and generally includes HTTPS.

[1196] This invention is a system that includes an information terminal means for inputting information about symptoms, a data processing means for performing preprocessing, an analysis means for identifying diseases using a generative AI model, a communication means, and a display means.

[1197] System Configuration

[1198] 1. Information terminal means

[1199] User: Enters symptom information using an information terminal such as a smartphone or PC. For example, a smartphone app or web interface is provided, allowing the user to enter symptoms. An example of a prompt sentence could be, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[1200] 2. Data processing means

[1201] Server: Preprocesses the symptom information received from the device. Preprocessing includes spell checking, noise removal, missing value completion, and format standardization. For example, data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." The information is also tokenized to extract features such as "joint pain" and "fatigue."

[1202] 3. Analysis method

[1203] Server: The preprocessed data is input into a generative AI model to identify diseases. The generative AI model used is trained based on past medical data and diagnostic information. The AI ​​model calculates the predicted probability for each disease based on the user's symptom information. For example, it outputs results such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%."

[1204] 4. Means of communication

[1205] Server and terminal: The identified diseases and their predicted probabilities are transmitted to the terminal using a secure communication protocol (e.g., HTTPS) to ensure data integrity and confidentiality.

[1206] 5. Display means

[1207] Terminal: The received analysis results are displayed on a user interface, allowing the user to check the identified diseases and their predicted probabilities. The results are displayed in graph and list format. For example, a list of diseases such as "Rheumatoid arthritis: 60%" and "Systemic lupus erythematosus: 30%" and their predicted probabilities are visually displayed.

[1208] Specific examples

[1209] The user inputs symptoms such as "I have joint pain when I wake up in the morning, and I get tired easily in the evening" using an information terminal. The terminal converts this information into a data packet and sends it to the server. The server preprocesses the received data and tokenizes the information "I have joint pain when I wake up in the morning, and I get tired easily in the evening" as "joint pain" and "fatigue." The preprocessed data is input into a generative AI model, which calculates predicted probabilities such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%." These results are formatted in JSON and sent to the terminal using a secure communication protocol. Finally, the terminal displays the received results on a user interface, allowing the user to visually confirm the identified diseases and their predicted probabilities.

[1210] This system will enable the rapid and accurate identification of diseases that are difficult to diagnose in hospitals, enabling patients to receive appropriate medical treatment at an early stage, which is expected to improve their health and quality of life.

[1211] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1212] Program processing flow

[1213] Step 1:

[1214] The user inputs symptom information using the information terminal means.

[1215] Specific actions: The user accesses the application or web interface on their smartphone or computer and inputs specific symptoms according to the prompts. For example, they might input, "My joints hurt when I wake up in the morning, and I get tired easily in the evening."

[1216] Input: Symptom information ("My joints hurt when I wake up in the morning, and I get tired easily in the evening.")

[1217] Output: Symptom information entered into the terminal

[1218] Step 2:

[1219] The terminal transmits the input symptom information to the server.

[1220] Specific operation: The terminal converts the input symptom information into data packets and sends them to the server using a secure communication protocol (HTTPS).

[1221] Input: Symptom information entered into the terminal

[1222] Output: Symptom information sent to the server

[1223] Step 3:

[1224] The server preprocesses the received symptom information.

[1225] Specific operation: The server cleanses the received symptom information, removing noise and filling in missing values. It also standardizes the format of the information, e.g., data such as "When I wake up in the morning, my joints hurt, and I get tired easily in the evening" is corrected to "When I wake up in the morning, my joints hurt, and I get tired easily in the evening." It then tokenizes the information as "joint pain" and "fatigue."

[1226] Input: Symptom information sent to the server

[1227] Output: Preprocessed and tokenized data

[1228] Step 4:

[1229] The server inputs the preprocessed symptom information into a generative AI model to identify the disease.

[1230] How it works: The server inputs the preprocessed data into a generative AI model. The AI ​​model is trained based on past medical data and diagnostic information and calculates the predicted probability for each disease. For example, it can produce results such as "rheumatoid arthritis: 60%" and "systemic lupus erythematosus: 30%."

[1231] Input: Preprocessed and tokenized data

[1232] Output: Predicted probability for each disease (rheumatoid arthritis: 60%, systemic lupus erythematosus: 30%)

[1233] Step 5:

[1234] The server formats the diagnostic results and sends them to the terminal.

[1235] Specific operation: The server formats the identified diseases and their predicted probabilities into an easy-to-read format (e.g., JSON format) and sends them to the terminal using a secure communication protocol (HTTPS).

[1236] Input: Predicted probability for each disease

[1237] Output: Formatted data, diagnostic results sent to terminal

[1238] Step 6:

[1239] The terminal displays the diagnostic results on the user interface.

[1240] Specific operation: The terminal application or web interface receives and analyzes the formatted diagnosis results sent from the server. The identified diseases and their predicted probabilities are displayed in the user interface in the form of a graph or list.

[1241] Input: Diagnostic results sent to the terminal

[1242] Output: Identified diseases and their predicted probabilities displayed in a user interface

[1243] Through the above steps, the user can quickly and accurately understand his or her own health condition and receive support to receive necessary medical treatment.

[1244] (Application example 1)

[1245] 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."

[1246] In modern autonomous vehicles, long driving times and driver health management are important issues. However, there is a lack of means to immediately respond when a driver feels unwell, making it difficult to take appropriate measures or respond quickly. In particular, when a health problem occurs while driving, immediate access to appropriate medical support is required, but current systems make it difficult to respond quickly.

[1247] 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.

[1248] In this invention, the server includes an interface means that allows the driver of the autonomous vehicle to input symptom information, a means for processing the symptom information input by the driver in real time and identifying a disease using a generative AI model, and a means for presenting information on the identified disease and its predicted probability to the driver, thereby enabling the driver to manage their own health condition in real time and take necessary measures promptly.

[1249] "Symptom information" is information relating to the specific physical condition or health state that the driver feels.

[1250] A "terminal" is a device through which the driver inputs symptom information, and specifically includes a smartphone or a head-mounted display installed in the vehicle.

[1251] "Server means" refers to a central processing unit that processes the received symptom information and identifies the disease using a generative AI model.

[1252] "Preprocessing" refers to processing the received symptom information by methods such as noise removal, missing value completion, and format standardization.

[1253] A "generative AI model" is a machine learning model trained on past medical data and diagnostic information to identify diseases from symptom information.

[1254] "Disease" refers to a specific illness or disorder that causes physical abnormalities or discomfort.

[1255] "Prediction probability" refers to the probability that a disease will be identified by the generative AI model, and indicates the likelihood that the identified disease applies to the driver.

[1256] The "interface means" is a user interface that allows the driver to easily input symptom information through an input device.

[1257] "Real-time processing" means that the input symptom information is immediately sent to the server, and disease identification and prediction probability calculation are performed quickly based on that information.

[1258] "Presentation means" refers to a display method or audio guidance for immediately visually or audibly informing the driver of the identified disease and its predicted probability.

[1259] The present invention provides a system for enabling a driver of an autonomous vehicle to monitor his or her own health condition in real time. The system includes a driver terminal, a server means, a generative AI model, a secure communication protocol, and an interface means.

[1260] Terminal

[1261] The terminal is a device that the driver uses to input symptom information. This device can be a smartphone or a head-mounted display (HMD) installed in the vehicle. The terminal is responsible for transmitting the symptom information input by the driver to the server.

[1262] Server Means

[1263] The server preprocesses the symptom information received from the device and identifies diseases using a generative AI model. Preprocessing includes noise removal, missing value completion, and format standardization. The preprocessed data is input into the generative AI model, which performs highly accurate disease identification.

[1264] Generative AI Models

[1265] A generative AI model is a machine learning model trained on past medical data and diagnostic information. This model predicts diseases based on input symptom information and calculates the predicted probability.

[1266] Secure Communication Protocol

[1267] Secure communication protocols such as HTTPS are used to send and receive information between the device and the server, ensuring the safety of the information.

[1268] Interface Means

[1269] The interface means is a user interface that allows the driver to easily input symptom information, and specifically supports voice input and text input.

[1270] Specific examples

[1271] If a driver experiences "numbness in the hands" and "nausea," they can input their symptoms into the HMD by voice. The HMD converts the voice input into text and sends it to the server. The server preprocesses the symptom data and identifies the illness using a generative AI model. This produces predictions such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%." These results are displayed on the HMD, allowing the driver to take appropriate action based on their physical condition (e.g., take a break, consult a doctor, etc.).

[1272] Prompt Sentence Examples

[1273] User: Enter symptoms: "numbness in hands," "nausea"

[1274] System: Running diagnostics...

[1275] System:Result - 70% chance of carpal tunnel syndrome, 20% chance of anemia. Showing more information.

[1276] This system allows drivers to monitor their own health status in real time and take necessary measures promptly.

[1277] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1278] Step 1:

[1279] The user inputs their symptom information into the terminal.

[1280] Specific symptoms can be entered in voice or text format, such as "numbness in hands" or "nausea." The device converts this symptom information into text data and formats it in JSON format.

[1281] Input: Symptom information in spoken or text form

[1282] Output: Symptom data in JSON format

[1283] Step 2:

[1284] The terminal transmits the input symptom information to the server.

[1285] The HTTPS protocol is used to ensure secure communication, and transmitted data is encrypted end-to-end.

[1286] Input: Symptom data in JSON format

[1287] Output: Symptom data sent to the server

[1288] Step 3:

[1289] The server pre-processes the received symptom information.

[1290] The preprocessing step involves noise removal, missing value imputation, and format standardization. For example, information about "numbness in the hands" and "nausea" is tokenized as "suspected carpal tunnel syndrome."

[1291] Input: Symptom data sent to the server

[1292] Output: Preprocessed data

[1293] Step 4:

[1294] The server inputs the preprocessed data into a generative AI model to identify diseases.

[1295] The AI ​​model is trained on past medical data and diagnostic information to calculate identified diseases and their predicted probabilities, generating results such as "Carpal tunnel syndrome: 70%" and "Anemia: 20%."

[1296] Input: Preprocessed data

[1297] Output: Identified diseases and their predicted probabilities by the generative AI model

[1298] Step 5:

[1299] The server formats the identified diseases and their predicted probabilities and transmits them to the terminal.

[1300] The results are formatted in lists and graphs to make them easy for drivers to understand, and the data is sent again using the HTTPS protocol.

[1301] Input: Identified diseases and their predicted probabilities by the generative AI model

[1302] Output: Formatted result data sent to the terminal

[1303] Step 6:

[1304] The terminal displays the received identified diseases and their predicted probabilities on a user interface.

[1305] The display format can be, for example, a list format or a graph format, allowing the driver to check the results in real time and take any necessary measures.

[1306] Input: Formatted result data sent to the terminal

[1307] Output: Identified diseases and their predicted probabilities displayed in a user interface

[1308] In this way, the symptom information entered by the user is processed on the server, the disease is identified using a generative AI model, and the results are immediately returned to the driver, enabling a prompt and appropriate response.

[1309] 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.

[1310] The present invention is a system that combines a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, and means for displaying the identified disease and its predicted probability on the terminal, as well as an emotion engine that recognizes the user's emotions.

[1311] System Configuration

[1312] 1. Terminal

[1313] This is a device into which the user inputs information about their medical condition, symptoms, and emotional state. Specifically, it is a smartphone or PC. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[1314] 2. Server Means

[1315] The server receives symptom information sent from the device and preprocesses it. Preprocessing includes noise removal, standardizing data formats, and filling in missing values. Once preprocessed, the data is input into a generative AI model to identify the disease.

[1316] The generative AI model is trained based on past medical data and diagnostic information to achieve highly accurate disease identification. As a diagnostic result, a list of identified diseases and their predicted probabilities is generated and sent to the device.

[1317] 3. Emotion Engine

[1318] The server also has an emotion engine that recognizes the user's emotional state. This emotion engine analyzes text information and voice data entered by the user and extracts their emotional state. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[1319] 4. Secure Communication Protocols

[1320] The security of information is ensured by the protocol used when sending and receiving information between the device and the server. HTTPS is generally used.

[1321] 5. Display means

[1322] The terminal displays the list of identified diseases and their predicted probabilities, as well as the analysis results of the emotional state, on a user interface. Based on this information, the user can quickly decide on their next course of action.

[1323] Program processing

[1324] 1. Data Entry

[1325] The user inputs their symptoms and emotional state into the device. Symptom information is entered as "joint pain" or "fatigue," and emotional information is entered as "stress" or "anxiety," using free-form text or voice data.

[1326] 2. Data Transmission

[1327] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol (e.g., HTTPS).

[1328] 3. Data Reception and Preprocessing

[1329] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing such as noise removal and missing value completion, and standardizes the data format.

[1330] 4. Emotion analysis

[1331] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data.

[1332] 5. Feature Extraction

[1333] The server extracts important features from the preprocessed symptom information and emotion information, such as "joint pain," "fatigue," and "stress."

[1334] 6. Input to the AI ​​model

[1335] The server inputs the extracted feature information into a generative AI model to identify the disease.

[1336] 7. Disease Identification and Outcome Generation

[1337] The server organizes the list of diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually easy-to-understand format (e.g., JSON format).

[1338] 8. Send results

[1339] The server transmits the formatted prediction result data to the terminal.

[1340] 9. Results display

[1341] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[1342] Specific examples

[1343] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, and the user decides on the next action.

[1344] This system can quickly identify diseases that are difficult to diagnose and provide more accurate diagnostic results that take into account the user's emotional state.

[1345] The processing flow will be explained below.

[1346] Step 1:

[1347] The user inputs information about their medical condition and emotions into an input terminal. Specifically, they input free-form text or voice data such as "My joints hurt when I wake up in the morning, and I feel more tired and stressed in the evening."

[1348] Step 2:

[1349] The terminal converts the input information into data packets and sends them to the server using a secure communication protocol such as HTTPS.

[1350] Step 3:

[1351] The server receives data packets sent from the device, and then validates them to ensure they were sent correctly and checks for inaccurate or lost data.

[1352] Step 4:

[1353] The server preprocesses the received data, which may include noise reduction (e.g., removing nonsense text or audio), spam filtering, missing value imputation, and data formatting standardization (e.g., converting all text to lowercase).

[1354] Step 5:

[1355] The server analyzes the preprocessed data and extracts specific keywords and phrases, such as symptoms and emotional characteristics like "joint pain," "fatigue," and "stress."

[1356] Step 6:

[1357] The server passes the extracted feature data to the emotion engine, which analyzes the user's emotional state (e.g., "stress" or "anxiety") from the text and voice data and converts it into a numerical value or categorization.

[1358] Step 7:

[1359] The server combines the emotion information obtained from the emotion engine with the pre-processed symptom information and inputs it into a generative AI model, which is trained on past medical data and diagnostic information.

[1360] Step 8:

[1361] The server uses a generative AI model to analyze the input data and identify possible diseases. Specifically, it uses a multi-class classification algorithm to calculate the predicted probability for each disease. For example, it can produce results such as "60% for rheumatoid arthritis" or "30% for systemic lupus erythematosus."

[1362] Step 9:

[1363] The server formats the generated prediction results and emotion information into a visually easy-to-understand format (e.g., JSON format).

[1364] Step 10:

[1365] The server then transmits the formatted prediction result data to the terminal again using a secure communication protocol such as HTTPS.

[1366] Step 11:

[1367] The device analyzes the received prediction result data and emotion information and displays them on the user interface. For example, the identified disease and its predicted probability, results such as "rheumatoid arthritis: 60%," "systemic lupus erythematosus: 30%," and "stress level: high" are displayed in graph and list format.

[1368] Step 12:

[1369] The user checks the displayed results and, based on the information about their health condition, consults with a medical institution as necessary and makes a treatment plan.

[1370] Example 2

[1371] 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."

[1372] Conventional medical diagnostic systems do not take into account the user's emotional state, making it difficult to identify diseases caused by urgency or psychological factors. Furthermore, preprocessing of input symptom information is insufficient, making it difficult to remove noise and complete missing values, resulting in low diagnostic accuracy. Furthermore, the lack of secure communication protocols means that data security cannot be guaranteed. These issues must be resolved to achieve more accurate and rapid disease identification.

[1373] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1374] In this invention, the server includes a means for preprocessing the received symptom information, a means including an emotion engine for recognizing the user's emotional state, and a means for identifying a disease using a generative AI model based on the preprocessed symptom information, thereby enabling highly accurate disease identification that takes the user's emotional state into consideration.

[1375] "Symptom information" is information about a medical condition or physical condition entered by a user.

[1376] A "terminal" is a device through which a user inputs symptom information, and examples include a smartphone and a personal computer.

[1377] The "server means" refers to a server that processes symptom information received from a terminal and performs various analyses and data transmissions.

[1378] "Preprocessing" refers to processes such as removing noise from received symptom information, filling in missing values, and standardizing data formats.

[1379] A "generative AI model" is an artificial intelligence model trained based on past medical data and diagnostic information, and is a technology that enables highly accurate disease identification.

[1380] "Disease identification" refers to the process of using generative AI models to identify possible diseases based on specific symptoms.

[1381] "Predicted probability" is a numerical value that indicates the probability that the generative AI model estimates for a specified disease.

[1382] An "emotion engine" is a system that includes software functions for analyzing a user's emotional state from text information and voice data.

[1383] A "secure communication protocol" is a communication protocol used by a terminal and a server means to send and receive information securely, and a specific example of this is HTTPS.

[1384] "User interface" refers to an interface for visually displaying information to a user on a terminal.

[1385] This invention is a system that includes a terminal where a user inputs their own symptom information and emotional state, a server means for preprocessing the received symptom information and identifying a disease using a generative AI model, and a means for displaying the identified disease and its predicted probability. The system also includes an emotion engine that recognizes the user's emotional state.

[1386] First, the user inputs their symptom information and emotional state using a device such as a smartphone or PC. Symptom information includes such things as "My joints hurt when I wake up in the morning" and "I get tired easily in the evening," while emotional information includes free-form text and voice data such as "I feel stressed" and "I feel anxious."

[1387] The terminal then converts the input information into data packets and transmits them to the server using a secure communication protocol (e.g., HTTPS).

[1388] The server receives and validates the data sent from the device. After receiving the data, it performs preprocessing to remove noise from the data, fill in missing values, and standardize the data format. Preprocessing also includes converting voice data to text and formatting text data for sentiment analysis.

[1389] The server passes part of the received data to an emotion engine to analyze the user's emotional state. For example, it detects "stress" from text data and analyzes "anxiety" from voice data. The results of the emotion analysis are also used as input data for the generative AI model.

[1390] Next, the server extracts key features from the preprocessed symptom and emotion information. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. This feature information is input into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification.

[1391] Once the generative AI model has obtained the list of diseases and their predicted probabilities, the server formats it into a visually understandable format (e.g., JSON), and the formatted result data is sent to the device.

[1392] The device displays the received prediction data and emotion analysis results on the user interface. For example, results such as "Rheumatoid Arthritis: 60%," "Systemic Lupus Erythematosus: 30%," and "Stress Level: High" are displayed. Based on this information, the user can quickly decide on their next course of action.

[1393] Specific examples

[1394] The user inputs, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device converts this information into a data packet and sends it to the server using HTTPS. The server validates the received data and performs preprocessing such as missing value completion and noise removal. The emotion engine analyzes "stress," and the server extracts "joint pain," "fatigue," and "stress" as features. The feature information is input into the generative AI model, which generates the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus." This resulting data is sent to the device, which displays the results on the user interface.

[1395] Prompt Sentence Examples

[1396] "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed. Could you please tell me what illnesses these symptoms could suggest?"

[1397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1398] Step 1: Data entry

[1399] The user inputs their symptoms and emotional state into the device. For example, they can input text or voice data such as "My joints hurt when I wake up in the morning," "I get tired easily in the evening," or "I feel stressed."

[1400] Input: Symptom information and emotion information (text and audio data)

[1401] Output: Data packets

[1402] Step 2: Send data

[1403] The terminal converts the input information into data packets and transmits them to the server using a secure communication protocol (for example, HTTPS).

[1404] Input: Data packet

[1405] Output: Data sent to the server

[1406] Step 3: Data Receipt and Validation

[1407] The server receives the data sent from the terminal and performs validation on the received data, checking the format and content (e.g., checking for missing values, checking the data format, etc.).

[1408] Input: Received data

[1409] Output: Validated data

[1410] Step 4: Data Preprocessing

[1411] The server performs preprocessing on the data that has passed validation, such as removing noise, filling in missing values, and standardizing the data format, to prepare the data in a format suitable for analysis.

[1412] Input: Validated data

[1413] Output: Preprocessed data

[1414] Step 5: Sentiment Analysis

[1415] The server passes a portion of the preprocessed data to the emotion engine, which analyzes the user's emotional state by detecting "stress" from the text data and "anxiety" from the voice data.

[1416] Input: Preprocessed data

[1417] Output: Emotion analysis results

[1418] Step 6: Feature Extraction

[1419] The server extracts key features from the preprocessed symptom and emotion information, such as "joint pain," "fatigue," and "stress."

[1420] Input: Preprocessed data and sentiment analysis results

[1421] Output: Extracted feature data

[1422] Step 7: Input to the AI ​​model

[1423] The server inputs the extracted feature information into a generative AI model, which has been previously trained on past medical data and diagnostic information.

[1424] Input: Extracted feature data

[1425] Output: AI-identified disease data

[1426] Step 8: Disease identification and outcome generation

[1427] The server retrieves the diseases identified by the generative AI model and their predicted probabilities, and formats them into a visually understandable format (e.g., JSON format).

[1428] Input: AI-identified disease data

[1429] Output: Formatted result data

[1430] Step 9: Send results

[1431] The server transmits the formatted prediction result data to the terminal.

[1432] Input: Formatted result data

[1433] Output: Data sent to the terminal

[1434] Step 10: View the results

[1435] The device then displays the received prediction data and emotion analysis results on a user interface. For example, results such as "Rheumatoid arthritis: 60%," "Systemic lupus erythematosus: 30%," and "Stress level: High" are displayed.

[1436] Input: Submitted result data

[1437] Output: what is displayed to the user

[1438] (Application example 2)

[1439] 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."

[1440] In modern society, there is a demand for rapid and accurate disease identification based on each individual's health and emotional state. However, many systems perform diagnosis without taking emotional information into account, resulting in low accuracy of diagnostic results. Furthermore, there is a lack of systems that provide advertisements for appropriate products and services based on identified disease information. Therefore, there is a need for a system that analyzes a user's symptom information and emotional information, identifies a disease based on that information, and then displays relevant advertisements based on the identified disease information.

[1441] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal that inputs information about symptoms, server means that preprocesses the symptom information received from the terminal, server means that identifies a disease using a generative AI model based on the preprocessed symptom information, server means that transmits the identified disease and its predicted probability to the terminal, means for displaying advertisements for related products and services based on the disease information displayed on the terminal, an emotion engine that inputs and analyzes emotion information, and means for displaying the identified disease and its predicted probability on the terminal. This enables highly accurate disease identification that takes the user's emotional state into consideration, and further makes it possible to display advertisements for appropriate products and services based on the identified disease.

[1442] A "terminal" is a device that allows a user to input information about symptoms and emotions.

[1443] The "server means" is a server that processes symptom information and emotion information received from the terminal and identifies diseases using a generative AI model.

[1444] A "generative AI model" is an AI algorithm that is trained based on past medical data and diagnostic information and identifies diseases based on the user's symptoms and emotional information.

[1445] An "emotion engine" is an engine that has the function of analyzing text and voice input by the user and extracting their emotional state.

[1446] A "secure communication protocol" is a communication method that ensures the security of information when sending and receiving data between a terminal and a server.

[1447] The "display means" is a function that displays the identified disease, its predicted probability, and related advertisements sent from the server on the user interface.

[1448] The "means for displaying advertisements" is a function for providing users with advertisements for related products and services based on the identified disease information.

[1449] The present invention is a system that includes a terminal for inputting information about symptoms, server means for preprocessing the received symptom information, server means for identifying a disease using a generative AI model based on the preprocessed symptom information, server means for transmitting the identified disease and its predicted probability to the terminal, an emotion engine for recognizing the user's emotions, and a function for displaying the identified disease and its predicted probability, as well as means for displaying advertisements for related products and services.

[1450] System Configuration

[1451] 1. Terminal

[1452] A device into which a user inputs information about their medical condition, symptoms, and emotional state. Specifically, a smartphone, smart glasses, or PC can be used. The device converts the input information into data packets and transmits them to a server using a secure communication protocol.

[1453] 2. Server Means

[1454] The server receives the symptom information sent from the device and performs preprocessing, which includes noise removal, data format standardization, and missing value completion. After preprocessing is complete, the data is input into a generative AI model to identify diseases. A list of identified diseases and their predicted probabilities is sent to the device.

[1455] The server also has an emotion engine that analyzes the user's emotional state by analyzing the text information and voice data entered by the user. The analysis results are also used as input data for the generative AI model, enabling more accurate disease identification.

[1456] 3. Secure Communication Protocols

[1457] A protocol used when a terminal and a server send and receive information. HTTPS is generally used.

[1458] 4. Display means

[1459] The terminal displays a list of identified diseases and their predicted probabilities sent from the server, as well as advertisements for related products and services, on the user interface, allowing the user to quickly decide their next course of action based on this information.

[1460] Specific examples

[1461] The user inputs into the smart glasses, "When I wake up in the morning, my joints hurt, and in the evening I get tired easily and feel stressed." The device sends this information to the server. The server preprocesses the received data and extracts "joint pain," "fatigue," and "stress." The emotion engine analyzes "stress" and inputs the information into the generative AI model. The model produces the results "60% rheumatoid arthritis" and "30% systemic lupus erythematosus," which are sent to the device. The device displays the results, along with advertisements for related products and services. The user can then decide on appropriate actions based on this.

[1462] Example prompt sentence:

[1463] "I've had a headache since this morning and I feel really sick."

[1464] "Recently, my joints have been hurting and I've been feeling tired easily."

[1465] This invention realizes a system that comprehensively analyzes a user's symptoms and emotional state and provides the user with optimal information and services.

[1466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1467] Step 1:

[1468] The user inputs their symptoms and emotional state into the device. This input information includes text and voice data. Specifically, the user inputs a prompt sentence such as "I've had a headache since this morning and I feel very unwell" using smart glasses or a smartphone. This input information is converted into a data packet.

[1469] Step 2:

[1470] The device sends the input information to the server using a secure communication protocol (e.g., HTTPS). The input here is symptom information and emotion information entered by the user, and this becomes the output sent to the server.

[1471] Step 3:

[1472] The server preprocesses the received data, including removing noise, standardizing data formats, and filling in missing values. The input is the raw data sent from the device, and the output is clean data that has undergone preprocessing.

[1473] Step 4:

[1474] The server passes the preprocessed data to an emotion engine to analyze the user's emotional state. For example, it can detect "stress" from text data or "anxiety" from voice data. The input is the preprocessed symptom and emotion data, and the output is the analysis result including the emotional state.

[1475] Step 5:

[1476] The server extracts important features from the preprocessed symptom information and the analysis results of the emotion engine. Specifically, features such as "joint pain," "fatigue," and "stress" are extracted. The input is the preprocessed data and the emotion analysis results, and the output is the extracted feature information.

[1477] Step 6:

[1478] The server inputs the extracted feature information into a generative AI model to identify diseases. The generative AI model is trained based on past medical data and diagnostic information, enabling highly accurate disease identification. The input is feature information, and the output is a list of identified diseases and their predicted probabilities.

[1479] Step 7:

[1480] The server organizes the list of identified diseases and their predicted probabilities and formats them into a visually understandable format (e.g., JSON format). The input is the output of the generative AI model, and the formatted prediction result data is obtained.

[1481] Step 8:

[1482] The server sends the formatted prediction result data to the terminal. The input here is the formatted prediction result data, and the output sent to the terminal.

[1483] Step 9:

[1484] The device displays advertisements for related products and services on the user interface based on the received prediction result data and emotion analysis results. Specifically, based on results such as "Migraine: 70%" and "Mood Depression: Strong," advertisements for supplements effective against migraines or relaxing yoga classes are displayed. The input is the prediction result data and emotion analysis results from the server, and the output is what is displayed on the user interface.

[1485] 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.

[1486] 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.

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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).

[1492] 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.

[1493] 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."

[1494] 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.

[1495] 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).

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] The following is further disclosed regarding the above embodiment.

[1507] (Claim 1)

[1508] a terminal for inputting information about symptoms;

[1509] a server means for preprocessing symptom information received from the terminal;

[1510] a server means for identifying a disease using a generative AI model based on preprocessed symptom information;

[1511] a server means for transmitting the identified disease and its predicted probability to the terminal;

[1512] a means for displaying the identified disease and its predicted probability on the terminal;

[1513] A system including:

[1514] (Claim 2)

[1515] 10. The system of claim 1, wherein the generative AI model is trained based on historical medical data and diagnostic information.

[1516] (Claim 3)

[1517] 2. The system according to claim 1, wherein the terminal and the server means transmit and receive information using a secure communication protocol.

[1518] "Example 1"

[1519] (Claim 1)

[1520] an information terminal means for inputting information about symptoms;

[1521] a data processing means for preprocessing the symptom information received from the terminal;

[1522] An analytical method for identifying diseases using a generative AI model based on preprocessed symptom information; and

[1523] a communication means for transmitting the identified disease and its predicted probability to the terminal;

[1524] a display means for displaying the identified disease and its predicted probability on the terminal;

[1525] A system including:

[1526] (Claim 2)

[1527] 10. The system of claim 1, wherein the generative AI model is trained based on historical medical data and diagnostic information.

[1528] (Claim 3)

[1529] 2. The system according to claim 1, wherein the terminal and the server means transmit and receive information using a secure communication protocol.

[1530] "Application Example 1"

[1531] (Claim 1)

[1532] a terminal for inputting information about symptoms;

[1533] a server means for preprocessing symptom information received from the terminal;

[1534] a server means for identifying a disease using a generative AI model based on preprocessed symptom information;

[1535] a server means for transmitting the identified disease and its predicted probability to the terminal;

[1536] a means for displaying the identified disease and its predicted probability on the terminal;

[1537] an interface means for allowing a driver of the autonomous vehicle to input symptom information;

[1538] A means to process symptom information entered by the driver in real time and identify diseases using a generative AI model;

[1539] A means for presenting information about the identified disease and its predicted probability to the driver;

[1540] A system including:

[1541] (Claim 2)

[1542] 10. The system of claim 1, wherein the generative AI model is trained based on historical medical data and diagnostic information.

[1543] (Claim 3)

[1544] 2. The system according to claim 1, wherein the terminal and the server means transmit and receive information using a secure communication protocol.

[1545] "Example 2: Combining Emotion Engines"

[1546] (Claim 1)

[1547] a terminal for inputting information about symptoms;

[1548] a server means for preprocessing symptom information received from the terminal;

[1549] a server means for identifying a disease using a generative AI model based on preprocessed symptom information;

[1550] a server means for transmitting the identified disease and its predicted probability to the terminal;

[1551] a means for displaying the identified disease, its predicted probability, and emotion recognition results on the terminal;

[1552] server means including an emotion engine for recognizing an emotional state of a user;

[1553] A system including:

[1554] (Claim 2)

[1555] 10. The system of claim 1, wherein the generative AI model is trained based on historical medical data and diagnostic information.

[1556] (Claim 3)

[1557] 2. The system according to claim 1, wherein the terminal and the server means transmit and receive information using a secure communication protocol.

[1558] "Application example 2 when combining emotion engines"

[1559] (Claim 1)

[1560] a terminal for inputting information about symptoms;

[1561] a server means for preprocessing symptom information received from the terminal;

[1562] a server means for identifying a disease using a generative AI model based on preprocessed symptom information;

[1563] a server means for transmitting the identified disease and its predicted probability to the terminal;

[1564] A means for displaying advertisements for related products and services based on the disease information displayed on the terminal;

[1565] An emotion engine that inputs and analyzes emotion information;

[1566] a means for displaying the identified disease and its predicted probability on the terminal;

[1567] A system including:

[1568] (Claim 2)

[1569] 10. The system of claim 1, wherein the generative AI model is trained based on historical medical data and diagnostic information.

[1570] (Claim 3)

[1571] 2. The system according to claim 1, wherein the terminal and the server means transmit and receive information using a secure communication protocol. [Explanation of symbols]

[1572] 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 terminal for inputting information about symptoms; a server means for preprocessing symptom information received from the terminal; a server means for identifying a disease using a generative AI model based on preprocessed symptom information; a server means for transmitting the identified disease and its predicted probability to the terminal; a means for displaying the identified disease and its predicted probability on the terminal; A system including:

2. 10. The system of claim 1, wherein the generative AI model is trained based on historical medical data and diagnostic information.

3. 2. The system according to claim 1, wherein said terminal and said server means transmit and receive information using a secure communication protocol.

Images