System

Abstract

A system is provided.SOLUTION: The system includes an inputting means for inputting the health information of the patients, a receiving means for receiving the health information of the patients transmitted from the inputting means, a generation and AI means for selecting the health care providers on the basis of the health information of the patients received by the receiving means, and a notifying means for notifying the patients of the information of the health care providers selected by the generation and AI means.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] There is a problem of unequal access to medical providers depending on the region, with medical resources being overutilized in some areas and underutilized in others. This creates obstacles that prevent patients from receiving the medical care they need quickly and efficiently. There is a need to solve this problem and create an environment where patients can be matched with appropriate medical providers. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: a system including an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient health information received by the receiving means, and a notification means for notifying the patient of the healthcare provider selected by the generating AI means. This system automatically matches the patient with the most appropriate healthcare provider based on the patient's health information, thereby enabling fast and efficient access to healthcare.

[0006] "Patient Health Information" is data that includes a user's name, age, medical history, current symptoms, and other relevant health information.

[0007] "Input means" refers to the interface through which a user provides their health information to the system, and is typically a form or application that runs on a computer or mobile device.

[0008] The "receiving means" refers to the function of the server to receive and process the patient's health information sent from the input means.

[0009] "Generative AI means" refers to a function that utilizes a generative AI model to select the most appropriate healthcare provider based on the patient's health information obtained by the receiving means.

[0010] "Notification means" refers to the function for conveying information about the healthcare provider selected by the generation AI means to the patient, and mainly uses means such as email and push notifications. [Brief explanation of the drawings]

[0011] [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 illustrating 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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] The system of the present invention utilizes generative AI to efficiently match patients with healthcare providers. The system collects and analyzes the patient's health information and selects the most appropriate healthcare provider based on that information.

[0033] System configuration

[0034] Entering patient health information

[0035] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application provided on the device, and then press the submit button.

[0036] Sending and Receiving Health Information

[0037] The device sends the entered health information to the server, which sends the information as an HTTP POST request.

[0038] The server receives the patient's health information sent from the terminal and stores it in a database. After receiving the data, the server verifies that each element of the data is accurate.

[0039] Selection of healthcare provider

[0040] The server retrieves a list of available healthcare providers from a database, generates a prompt to select the most suitable healthcare provider for the patient, sends the generated prompt to the generation AI (OpenAI's GPT-based model), and receives a response from the AI ​​model.

[0041] The generative AI analyzes the prompts and responds with a text recommending the most suitable healthcare provider for the patient, including the provider's name and specialty.

[0042] Healthcare provider notification

[0043] The server analyzes the AI's response, extracts information about the healthcare provider recommended by the AI, and generates a response containing details of the selected healthcare provider based on that information and sends it back to the device.

[0044] The terminal receives the response from the server and displays to the user information about healthcare providers who recommend vaccinations.

[0045] Specific examples

[0046] For example, a user named Tanaka uses a terminal to input his / her health information. Tanaka writes his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and presses the send button. The terminal then sends the health information to the server.

[0047] Based on the received information, the server sends a prompt to the generating AI: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generating AI analyzes the list of available healthcare providers and returns the answer that "Dr. Suzuki (Internal Medicine)" is best.

[0048] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable healthcare provider for Mr. Tanaka, and sends it to the terminal. The terminal receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended."

[0049] This process ensures that Tanaka is quickly and efficiently matched with the appropriate healthcare provider and receives the medical services he needs.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The user enters health information into the terminal. The entered information includes name, age, medical history, symptoms, etc. The user presses the send button.

[0053] Step 2:

[0054] The device sends the health information entered by the user to the server as an HTTP POST request.

[0055] Step 3:

[0056] The server receives the patient's health information from the terminal and stores it in a database. It also verifies that the format of the received data is correct.

[0057] Step 4:

[0058] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[0059] Step 5:

[0060] The server generates a prompt for the AI, which includes the patient's health information and a list of available providers, in the format "Which provider is best?"

[0061] Step 6:

[0062] The server calls the OpenAI API and sends a prompt to the generated AI, authenticating the request with an API key.

[0063] Step 7:

[0064] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[0065] Step 8:

[0066] The server analyzes the AI's response, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[0067] Step 9:

[0068] The server returns the recommended healthcare provider information to the device as an HTTP response.

[0069] Step 10:

[0070] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider.

[0071] Step 11:

[0072] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[0073] Example 1

[0074] 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."

[0075] Conventional patient-healthcare provider matching systems have difficulty efficiently selecting the most appropriate healthcare provider based on the patient's detailed health information. Another problem is that it takes a lot of time and effort for patients to find the appropriate healthcare provider. Furthermore, there is a lack of a way to accurately and quickly convey patient information to healthcare providers.

[0076] 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.

[0077] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for storing the patient health information received by the receiving means in a database and selecting a healthcare provider based on the data, and a notifying means for notifying the patient of the healthcare provider selected by the generating AI means. This makes it possible to efficiently and accurately select the most appropriate healthcare provider based on the patient's health information and quickly notify the information.

[0078] "Patient health information" refers to information that indicates the patient's health condition, such as the patient's name, age, medical history, and symptoms.

[0079] "Input means" refers to the means used by patients to enter their health information, specifically a web form on a computer or smartphone or a mobile application.

[0080] The "receiving means" is a means for receiving the patient's health information transmitted from the input means, and the server is mainly responsible for this role.

[0081] "Database" means an electronic record system for storing patient health information and healthcare provider information.

[0082] "Generative AI method" refers to an artificial intelligence model used to select the most appropriate healthcare provider based on a patient's health information and a list of healthcare providers.

[0083] "Notification means" refers to a means for conveying information about the healthcare provider selected by the generation AI means to the patient, and primarily refers to an electronic message sent from the server to the terminal.

[0084] A "prompt" is text data to be input into the generative AI, and includes questions about the patient's health information and required medical services.

[0085] A "Response" is a reply message from the Generating AI that includes detailed information about a recommended healthcare provider.

[0086] The system of the present invention utilizes generative AI models to efficiently match patients with healthcare providers. The system collects and analyzes patient health information and then selects the most appropriate healthcare provider based on that information.

[0087] Entering and submitting health information

[0088] To enter their health information, users use devices such as computers or smartphones. They access a web form or mobile application on their device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses a submit button to send the information to the server. When the submit button is pressed, the device sends the data via an HTTP POST request.

[0089] Receiving and storing health information

[0090] The server receives the HTTP POST request sent from the device, analyzes the request, and stores the submitted patient health information in a database, performing checks to verify the accuracy of the data.

[0091] Selection of healthcare provider

[0092] The server retrieves a list of available healthcare providers from a database. This list includes information such as the provider's name, specialty, and location. Based on the patient's health information and the list of healthcare providers, the server generates a prompt for the generative AI model. For example, the server creates a prompt such as, "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generated prompt is then sent to the generative AI (e.g., OpenAI's GPT-based model).

[0093] Receiving a response from the AI

[0094] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[0095] Notification of recommendation information

[0096] The server analyzes the response from the AI ​​generator and extracts details of the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The device receives this response and displays the information to the user.

[0097] Specific examples

[0098] For example, a user, Mr. Takahashi, uses a terminal to input his health information. Mr. Takahashi writes "Ichiro Takahashi, 70 years old, at risk of high blood pressure" in the input form and presses the send button. The terminal then sends the health information to the server.

[0099] Based on the received information, the server sends the following prompt to the Generative AI: "Ichiro Takahashi, 70 years old, at risk of high blood pressure. Which healthcare provider is best?" The Generative AI analyzes the list of available healthcare providers and returns the answer that "Dr. Sato (cardiologist)" is best.

[0100] Based on this answer, the server generates a response containing information about Dr. Sato, the most suitable medical provider for Mr. Takahashi, and sends it to the terminal. The terminal receives this response and displays it to Mr. Takahashi, saying, "Dr. Sato is recommended."

[0101] This process ensures that Takahashi is quickly and efficiently matched with the appropriate medical provider and receives the medical services he needs.

[0102] Through the above steps, the system of the present invention is able to select the most suitable healthcare provider based on the patient's health information and notify the patient promptly and accurately.

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1: Enter patient health information

[0105] Users use devices such as computers or smartphones to enter their health information. They access a web form or mobile application on the device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses the send button, which prepares the input data for transmission to the device.

[0106] Step 2: Submit your health information

[0107] The device sends the health information entered by the user to the server as an HTTP POST request. The input at this point is the user's health information (name, age, medical history, symptoms), and the output is an HTTP request sent to the server. After sending, the device notifies the user that "Sending has been completed."

[0108] Step 3: Receiving and storing health information

[0109] The server receives the HTTP POST request sent from the device. The server analyzes the request, extracts the submitted patient health information, and stores it in a database. In this process, the input is the HTTP request, and the output is the patient health information stored in the database. The server also performs checks to verify the accuracy of the data.

[0110] Step 4: Get a list of healthcare providers

[0111] The server retrieves a list of available providers from a database, which includes information such as provider name, specialty, location, etc. The input is a query to the database, and the output is a list of providers.

[0112] Step 5: Generate and send the prompt

[0113] The server generates a prompt to send to the generative AI model based on the user's health information and list of healthcare providers. For example, it creates a prompt with the following content: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The input is the patient's health information and list of healthcare providers, and the output is the generated prompt text. The generated prompt is sent to the generative AI (e.g., OpenAI's GPT-based model).

[0114] Step 6: Receive a response from the AI

[0115] The server receives a response from the generation AI. The response includes the name and specialty of the recommended healthcare provider. The input is the response from the generation AI, and the output is information about the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[0116] Step 7: Parse the response and generate recommendations

[0117] The server analyzes the response received from the generation AI and extracts detailed information about the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The input is the response from the generation AI, and the output is a message to notify the patient.

[0118] Step 8: Submit and view your recommendations

[0119] The server sends the generated response to the terminal. The terminal analyzes the received response and displays detailed information about the recommended healthcare provider to the user. The input is the response from the server, and the output is the information displayed to the user (e.g., "Dr. Suzuki is recommended").

[0120] Through this series of processes, users are quickly and efficiently matched with appropriate medical providers, enabling them to receive medical services efficiently.

[0121] (Application example 1)

[0122] 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."

[0123] Conventional healthcare provider and patient matching systems have the problem that patients must manually enter their health information and it takes time to select an appropriate healthcare provider. It can also be difficult for patients to accurately enter their medical conditions and symptoms, which can lead to the wrong healthcare provider being recommended. This system is required to allow patients to easily enter their health information and quickly and accurately recommend the most appropriate healthcare provider.

[0124] 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.

[0125] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information received by the receiving means, a notification means for notifying the patient of the healthcare provider selected by the generating AI means, an input means for inputting the patient's health information in real time using a smart device, and a transmission means for acquiring and transmitting the health information by voice input or code scanning. This allows the patient to easily and quickly input their health information using a smart device, and enables the generating AI to quickly and accurately recommend the most suitable healthcare provider.

[0126] "Patient health information" refers to general information about the patient's health condition, such as the patient's name, age, medical history, current symptoms, allergy information, and medications currently being taken.

[0127] "Input means" refers to devices or interfaces through which patients input their health information, including smartphones, tablets, smart glasses, etc.

[0128] The "receiving means" refers to a server or a communication interface for receiving the patient's health information transmitted from the input means.

[0129] "Generative AI means" refers to the artificial intelligence model used to select healthcare providers based on received patient health information, specifically a generative AI model (e.g., a GPT-based model).

[0130] "Notification means" refers to a communication interface or display device used to notify patients of the information about the healthcare provider selected by the generation AI means.

[0131] "Smart devices" refer to electronic devices that are equipped with voice input, camera functions, displays, etc. and can collect and display patient health information, and specifically include smart glasses, smartphones, tablets, etc.

[0132] The "transmission means" refers to a function for transmitting patient health information acquired from a smart device to a server, specifically a data transmission means via an internet connection.

[0133] The present invention is a system for efficiently matching patients with healthcare providers, and in particular, it relates to the collection of real-time health information using smart devices and the selection of the most suitable healthcare provider using AI generation. The system is configured as follows:

[0134] Hardware and Software Use

[0135] 1. Hardware:

[0136] Smart devices (e.g., smart glasses, smartphones)

[0137] Voice input function

[0138] Camera features

[0139] Display Features

[0140] server:

[0141] Data Processing Server

[0142] Hospital Information System

[0143] Database server (storing patient and provider information)

[0144] 2. Software:

[0145] Data transmission API (e.g., using an HTTP POST request)

[0146] Server-side systems (e.g. web frameworks such as Flask and Django)

[0147] Generative AI models (e.g., OpenAI's GPT-based models)

[0148] Database management systems (e.g., MySQL, PostgreSQL)

[0149] Detailed System Description

[0150] Entering patient health information

[0151] Users input their health information using their smart devices. When using smart glasses, health information can be obtained using voice input or QR code scanning with the camera, and the information can be sent directly to the system. For example, users can input information such as "I have a headache" or "I have a history of high blood pressure" using voice input.

[0152] Sending and Receiving Health Information

[0153] The device sends the entered health information to the server via a data transmission API. The sent data reaches the server through a protocol (e.g., HTTP POST request) and is stored in a database.

[0154] Selection of healthcare provider

[0155] The server generates prompts based on the received patient health information and sends them to the generative AI model, which then selects the most appropriate healthcare provider based on the prompts shown below.

[0156] For example: "Taro Tanaka, 65 years old, at risk for diabetes. Which healthcare provider is best?"

[0157] The generative AI model analyzes the prompt and selects the most appropriate healthcare provider based on information about multiple healthcare providers retrieved from a database. For example, it may recommend an "internal medicine specialist."

[0158] Healthcare provider notification

[0159] The server analyzes the information on healthcare providers obtained from the generative AI model and notifies the patient of the results. The device receives the response from the server and displays details of the recommended healthcare provider to the patient. For example, the smart glasses display may show information such as "An internal medicine specialist is recommended."

[0160] This system allows patients to easily and quickly enter their health information using smart devices, and uses generative AI to quickly and accurately recommend the most suitable healthcare provider.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] Users use smart devices to input their own health information. Specifically, they may use the voice input function to input information such as "I have a headache" or "I have a history of high blood pressure," or they may use the camera function of smart glasses to scan QR codes to obtain information about medications. These pieces of information are treated as input.

[0164] Step 2:

[0165] The device sends the collected health information to the server using a data transmission API. The data is packaged in JSON format and sent to the server via an HTTP POST request. The server receives this health information and stores it in a database. The input at this stage is the health information, and the output is storing it in the database and confirming receipt on the server side.

[0166] Step 3:

[0167] The server generates a prompt to be sent to the generative AI model based on the patient's health information stored in the database. Specifically, it creates a prompt in the format "Taro Tanaka, 65 years old, at risk of diabetes. Who is the best healthcare provider?" This prompt is sent to the generative AI model. The input is the health information, and the output is the generated prompt.

[0168] Step 4:

[0169] The generative AI model analyzes the sent prompt and selects the most suitable healthcare provider based on information on multiple healthcare providers retrieved from a database. Based on the prompt, the generative AI uses internal learning data and logic to output the name and specialty of the most suitable healthcare provider. The input at this stage is the prompt, and the output is the selection result of the most suitable healthcare provider.

[0170] Step 5:

[0171] The server receives the response from the generative AI model and processes the information of the healthcare provider selected by the generative AI. Specifically, it analyzes the healthcare provider's name, specialty, contact information, etc., and generates a message to notify the patient. The input at this stage is the response from the generative AI model, and the output is the notification message.

[0172] Step 6:

[0173] The terminal receives the notification message from the server and displays the details of the recommended healthcare provider to the patient. In the case of smart glasses, the display will show "An internal medicine specialist is recommended." The patient can check this information through the smart glasses and contact the healthcare provider. The input at this stage is the notification message, and the output is the display to the patient.

[0174] 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.

[0175] The system of the present invention utilizes generative AI and an emotion engine to efficiently match patients and healthcare providers. The system collects and analyzes the patient's health and emotion information, and then selects the most appropriate healthcare provider based on that information.

[0176] System configuration

[0177] Entering patient health information

[0178] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application on the device and press the submit button.

[0179] Recognition of emotional information

[0180] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[0181] Sending and receiving health and emotional information

[0182] The device sends the entered health information and emotion label to the server as an HTTP POST request.

[0183] The server receives the patient's health information and emotion label from the device, stores them in a database, and verifies that the format of the received data is correct.

[0184] Selection of healthcare provider

[0185] The server retrieves a list of available providers from the database, including the provider's name, specialty, availability, etc.

[0186] The server generates a prompt for the generative AI, which includes the patient's health information, an emotional label, and a list of available healthcare providers, in the form of "Which healthcare provider is best?"

[0187] The server calls OpenAI's API and sends a prompt to the generating AI, authenticating the request with an API key.

[0188] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[0189] Healthcare provider notification

[0190] The server analyzes the response of the generation AI, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[0191] The server then returns customized notification content based on the recommended healthcare provider information and emotion label to the device as an HTTP response.

[0192] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[0193] Specific examples

[0194] For example, a user named Tanaka uses a device to input his / her health information. Tanaka enters his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and then presses the send button. The device sends the health information to the server along with an emotional label indicating the level of stress Tanaka felt while entering the information.

[0195] Based on the received information, the server sends the following prompt to the generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional label indicating high stress. Which healthcare provider is best?" The generative AI analyzes the list of available healthcare providers and replies, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[0196] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable medical provider for Mr. Tanaka, and adds a kind message that takes into consideration Mr. Tanaka's stress, and sends this to the device. The device receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended. He is an expert in reducing stress."

[0197] This allows Tanaka to be quickly and efficiently matched with the right medical provider and receive emotionally sensitive medical care.

[0198] The processing flow will be explained below.

[0199] Step 1:

[0200] The user enters health information into the terminal. The information includes name, age, medical history, current symptoms, etc. The user then presses the send button.

[0201] Step 2:

[0202] When the device transmits the user's health information, it collects the user's emotional indicators, including input speed, voice tone, and facial expression data (when using the camera).

[0203] Step 3:

[0204] The device sends the collected health information and emotional indicators to the server as an HTTP POST request.

[0205] Step 4:

[0206] The server receives the patient's health information and emotional indicators sent from the device, temporarily stores the received data, and verifies that the format is correct.

[0207] Step 5:

[0208] The server uses an emotion engine to analyze the emotion indicators and generate an emotion label for the user, which may include stress, satisfaction, relief, etc.

[0209] Step 6:

[0210] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[0211] Step 7:

[0212] The server combines the patient's health information with the emotion label and the list of healthcare providers to generate prompts for the generative AI, such as "Please select the most appropriate healthcare provider based on the patient's health information and emotion label."

[0213] Step 8:

[0214] The server calls OpenAI's API to send a prompt to the generating AI, authenticating using the API key.

[0215] Step 9:

[0216] The server receives the response from the generative AI, which includes the name and specialty of the recommended healthcare provider.

[0217] Step 10:

[0218] The server analyzes the generated AI's response and extracts information about the recommended healthcare provider.

[0219] Step 11:

[0220] The server generates customized notification content based on the recommended healthcare provider information and emotion labels, for example adding a message encouraging users to relax if they are feeling highly stressed.

[0221] Step 12:

[0222] The server returns the customized notification content to the device as an HTTP response.

[0223] Step 13:

[0224] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider.

[0225] Step 14:

[0226] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[0227] Example 2

[0228] 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."

[0229] Conventional patient-healthcare provider matching systems selected healthcare providers based solely on the patient's health information, making it difficult to select an appropriate healthcare provider that took the patient's emotional state into consideration. Furthermore, there was no way to collect and analyze emotional information, such as stress or anxiety, when the patient entered their information, making it difficult to select the healthcare provider best suited to the patient. This meant that patients were unable to receive appropriate healthcare services quickly and efficiently.

[0230] 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.

[0231] In this invention, the server includes a means for inputting a patient's health information and emotional information, a means for receiving the patient's health information and emotional information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, and a means for notifying the patient of a customized notification based on the healthcare provider information and emotional information selected by the generating AI means. This enables the selection of a healthcare provider that takes the patient's emotional state into consideration, enabling the patient to receive appropriate healthcare services quickly and efficiently.

[0232] "Patient health information" is data that indicates the patient's condition, including name, age, medical history, symptoms, etc.

[0233] "Emotional information" is data that indicates the emotional state of the patient, and includes information analyzed from voice, facial expression, and input speed.

[0234] The "input means" refers to a means by which a patient inputs health information and emotional information, and is a terminal such as a computer or smartphone.

[0235] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[0236] "Generative AI means" means means including artificial intelligence for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means.

[0237] "Notification means" means a means for notifying a patient of customized notification content based on the healthcare provider information and emotional information selected by the generation AI means.

[0238] "Server" means a central control unit that receives, processes, and stores data, selects healthcare providers using generative AI means, and notifies the results.

[0239] "Database" means a storage device for storing received patient health and emotional information and for maintaining available healthcare provider information.

[0240] "Prompts" are questions or instructions posed to the generative AI, which in this system are used to select a healthcare provider based on the patient's health and emotional information.

[0241] The "emotion engine" includes systems and algorithms for analyzing data such as voice, facial expressions, and input speed from the patient's input behavior and generating emotional information.

[0242] This invention is a system that utilizes generative AI and an emotion engine to efficiently match patients with healthcare providers. The system collects and analyzes patients' health and emotional information, and selects the most suitable healthcare provider based on this information.

[0243] System configuration

[0244] This system is composed of the following hardware and software: The hardware includes devices such as computers and smartphones. The software includes a web browser, mobile application, emotion engine, and generative AI (e.g., OpenAI API).

[0245] Specific processing flow

[0246] Entering patient health information

[0247] A user uses a device to enter their health information, for example, by entering their name, age, medical history, symptoms, etc. into a web form or mobile application, and then pressing a submit button. This entered health information is then sent to the system.

[0248] Recognition of emotional information

[0249] The device collects emotional indicators such as voice, facial expressions, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as "stress" and "anxiety."

[0250] Sending and receiving health and emotional information

[0251] The device sends the collected health information and emotion labels to the server via an HTTP POST request.

[0252] The server receives the data and stores it in a database. It also verifies that the received information is in the correct format.

[0253] Selection of healthcare provider

[0254] The server retrieves a list of available healthcare providers from a database, then generates a prompt containing the patient's health information and emotion label and sends it to a generative AI (e.g., OpenAI's API).

[0255] Acquisition and notification of recommended medical providers

[0256] The server receives the response from the AI ​​generator, extracts information about recommended healthcare providers, and generates customized notification content based on that information and the emotion label, which is then sent to the device as an HTTP response.

[0257] The device receives this response and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[0258] Specific examples

[0259] A 65-year-old user named Tanaka enters his health information using his smartphone. Tanaka enters his name "Taro Tanaka," his age "65," and his medical history of "risk of diabetes" into the input form, then presses the submit button. At this time, the device captures Tanaka's voice, facial expression, and input speed, and the emotion engine generates an emotion label such as "high stress." The device then sends this information to the server as an HTTP POST request.

[0260] The server receives the information and stores it in a database. It then sends the following prompt to the Generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional labels indicate high stress. Which healthcare provider is best?" The Generative AI responds, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[0261] Based on this answer, the server generates a response including information about Dr. Suzuki and a message that takes Mr. Tanaka into consideration, and sends it to the device. The device receives this and displays to Mr. Tanaka, "Dr. Suzuki is recommended. He is an expert in reducing stress." This allows Mr. Tanaka to be quickly and efficiently matched with an appropriate medical provider, and to receive medical services that are also considerate of his emotional state.

[0262] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0263] Step 1:

[0264] Users use the device to enter their health information: they open a web browser or mobile application, enter information such as their name, age, medical history, and symptoms, and then press the submit button.

[0265] Input: Name, age, medical history, symptoms, and other health information

[0266] Output: The entered health information is saved on the device.

[0267] Specific behavior:

[0268] A user opens a web browser or mobile application.

[0269] Enter your health information in the form provided.

[0270] Click the send button to send the information.

[0271] Step 2:

[0272] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as stress or anxiety.

[0273] Input: User voice, facial expressions, and typing speed

[0274] Output: Emotion labels generated by the emotion engine

[0275] Specific behavior:

[0276] The device's microphone and camera capture the user's voice and facial expressions.

[0277] Collect behavioral data such as typing speed.

[0278] The collected data is sent to the emotion engine for analysis.

[0279] The emotion engine generates emotion labels.

[0280] Step 3:

[0281] The device sends the collected health information and emotion labels to the server using an HTTP POST request.

[0282] Input: Health information, emotion labels

[0283] Output: Data sent to the server

[0284] Specific behavior:

[0285] The device makes an HTTP POST request containing the health information and emotion label.

[0286] Send this request to the server.

[0287] Step 4:

[0288] The server validates the received data and stores it in the database. It checks whether the received data is in the correct format.

[0289] Input: Health information sent from the device, emotion label

[0290] Output: Validated data stored in a database

[0291] Specific behavior:

[0292] The server receives an HTTP POST request.

[0293] Validate that the data is in the correct format.

[0294] The validated data is stored in the database.

[0295] Step 5:

[0296] The server retrieves a list of available healthcare providers from the database and generates a prompt to the generative AI means, which includes the patient's health information and an emotion label.

[0297] Input: Patient health information stored in a database, emotion labels

[0298] Output: Generated prompt

[0299] Specific behavior:

[0300] The server retrieves a list of available healthcare providers from a database.

[0301] Prompts are generated based on provider information, patient health information, and emotion labels.

[0302] Step 6:

[0303] The server sends a prompt to a generative AI tool (e.g., OpenAI's API), which contains the patient's health information and an emotion label.

[0304] Input: Generated prompt

[0305] Output: Recommendation results from the generative AI

[0306] Specific behavior:

[0307] The server sends the prompt to the API, which generates the AI.

[0308] Receive the generative AI means' response to the prompt.

[0309] Step 7:

[0310] The server analyzes the response from the generation AI and extracts information on recommended healthcare providers, which is then used to generate notifications for patients.

[0311] Input: Response from the generation AI

[0312] Output: Information and emotionally sensitive message for the notified healthcare provider

[0313] Specific behavior:

[0314] The server analyzes the response from the generated AI.

[0315] Extract recommended healthcare provider information.

[0316] Create notifications that are patient-friendly.

[0317] Step 8:

[0318] The server sends the customized notification content to the terminal as an HTTP response.

[0319] Input: Notification content

[0320] Output: Notification content sent to device

[0321] Specific behavior:

[0322] The server embeds the customized notification content in the HTTP response.

[0323] This HTTP response is sent to the terminal.

[0324] Step 9:

[0325] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[0326] Input: Notification content received from the server

[0327] Output: The notification that is displayed to the user

[0328] Specific behavior:

[0329] The device receives the HTTP response.

[0330] Display notification content in a user-friendly format.

[0331] (Application example 2)

[0332] 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."

[0333] In today's healthcare delivery environment, it remains difficult to quickly and effectively select the most appropriate healthcare provider for a patient. This can result in patients not receiving the medical care they need in a timely manner, leading to treatment delays and inappropriate medical responses. Furthermore, while providing emotionally sensitive healthcare has a significant impact on patient satisfaction and treatment outcomes, the current system does not adequately consider this important aspect. Furthermore, healthcare service scheduling and electronic payments are not centralized, resulting in increased hassle.

[0334] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0335] In this invention, the server includes an input means for inputting the patient's health information, an emotion engine means for the receiving means to collect and analyze emotional information along with the health information, a generation AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, a notification means, and a payment means. This allows the selection of the most appropriate healthcare provider based on the patient's health information and emotional information, and enables recommendation of healthcare services, reservations, and electronic payment that take emotions into consideration.

[0336] "Patient Health Information" refers to a set of data related to a patient's health status, such as the patient's name, age, medical history, and current symptoms.

[0337] "Input means" refers to the means by which patients input their health information, and includes devices such as computers and smartphones, web forms, and mobile applications.

[0338] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[0339] The "emotion engine means" is a means for analyzing emotion indicators such as voice, facial expression, and input speed collected together with the received health information of the patient, and generating emotion labels.

[0340] "Generative AI methods" refer to artificial intelligence models and algorithms that select the most appropriate healthcare provider based on a patient's health and emotional information.

[0341] "Notification means and payment means" refers to means for notifying patients of the information about the healthcare provider selected by the generating AI means, and for making reservations for healthcare services and making electronic payments.

[0342] "Database" refers to a digital storage system for storing patient health and emotional information and available healthcare provider information.

[0343] "Healthcare provider" refers to a doctor, nurse, specialist, or other health care professional who provides medical services, treatment, or diagnosis to a patient.

[0344] The system of the present invention has the function of collecting and analyzing a patient's health information and emotional information to efficiently match patients with healthcare providers, and recommending the most suitable healthcare provider. It also enables medical service reservations and electronic payments. The system includes an input means, a receiving means, an emotion engine means, a generation AI means, a notification means, and a payment means.

[0345] System configuration

[0346] Entering patient health information

[0347] Users enter their own health information using a device such as a smartphone, entering the patient's name, age, medical history, symptoms, and other health information into a mobile application on the device, and then pressing the send button.

[0348] Collecting and analyzing emotional information

[0349] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[0350] Sending and receiving health and emotional information

[0351] The device sends the entered health information and emotion label to the server as an HTTP POST request. The server receives the patient's health information and emotion label from the device and stores them in a database.

[0352] Selection of healthcare provider

[0353] The server retrieves a list of available healthcare providers from the database. The retrieved list includes the provider's name, specialty, availability, etc. The server generates a prompt for the generative AI model mentioned above. The prompt includes a question about the most suitable healthcare provider based on the patient's health information and emotion label and the list of available healthcare providers. An example of a specific prompt is, "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is the most suitable?"

[0354] Notification of recommendation information

[0355] The server receives the response from the generation AI and extracts information about the recommended healthcare provider. The server then generates a response based on the extracted information and sends it back to the device with a message that takes emotional information into consideration. For example, the message might read, "Dr. Suzuki is recommended. He is an expert in stress reduction."

[0356] Medical appointment booking and electronic payment

[0357] Users can select medical services based on recommendations from the server and make electronic payments directly within the application, making the system an efficient and emotionally sensitive way to book and pay for medical services easily and quickly.

[0358] Technology used

[0359] The hardware used is a computer terminal such as a smartphone or server, and the software used is a mobile application, Python, OpenAI's GPT-3 API, etc. Data is sent and received via HTTP and stored in a database.

[0360] As a concrete example of the entire system, when Tanaka uses the "MedPay" app to make a medical appointment, the prompt that appears is as follows:

[0361] "Taro Tanaka, 65, at risk for diabetes. Emotional label indicating high stress. Which healthcare provider is best?"

[0362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0363] Step 1:

[0364] The user launches the mobile application on their smartphone and enters their health information. Here, the user enters their name, age, medical history, symptoms, etc. into the input form and presses the submit button. The input data is packaged in JSON format. The entered data is temporarily stored on the device and prepared for transmission.

[0365] Step 2:

[0366] The device collects emotional information at the same time as the health information is entered. Emotional information is an indicator of the stress or anxiety the user felt while entering data, and is acquired using the device's camera and microphone. Input speed and touch patterns are also analyzed. This data is analyzed by the emotion engine and generated as an emotional label. The analyzed emotional label is then generated in JSON format.

[0367] Step 3:

[0368] The device sends the health information and analyzed emotion label to the server using an HTTP POST request, with the data sent in JSON format. The data includes the following items: "Name," "Age," "Symptoms," and "Emotion Label."

[0369] Step 4:

[0370] The server receives the health information and emotion labels received from the device and stores them in a database that also contains a list of existing healthcare providers and their availability information, and verifies the received data for correct formatting.

[0371] Step 5:

[0372] The server retrieves a list of available providers from a database, including the provider's name, specialty, available hours, etc. The retrieved data is stored in an internal memory.

[0373] Step 6:

[0374] The server generates a prompt for the generative AI model. The prompt includes the patient's health information and emotion label received, as well as the list of healthcare providers obtained. A specific prompt sentence might be generated like this: "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is best?" The prompt sentence is in text format.

[0375] Step 7:

[0376] The server sends a prompt to a generative AI model (e.g., OpenAI's GPT-3) using an API request, with the data sent in plain text format. The API key is used to authenticate the request.

[0377] Step 8:

[0378] The server receives a response from the generative AI model, including the name and specialty of the healthcare provider that the generative AI model finds most suitable. This data is also returned in text format.

[0379] Step 9:

[0380] The server analyzes the response from the generative AI model and extracts information about the recommended healthcare provider. The extracted information is then converted back to JSON format and a response message is generated to be displayed to the user. The message also includes emotionally sensitive content.

[0381] Step 10:

[0382] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider. The user can then select the recommended healthcare provider based on this information.

[0383] Step 11:

[0384] The user selects a recommended medical provider and makes a medical appointment. Once the appointment details are confirmed, the appointment information is sent back to the server from the terminal.

[0385] Step 12:

[0386] The server processes the electronic payment based on the received reservation information. A payment gateway service is used to process the payment, and payment is made using credit card information or an online payment account. The payment success or failure status is returned to the terminal and displayed to the user.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Second embodiment]

[0391] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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."

[0403] The system of the present invention utilizes generative AI to efficiently match patients with healthcare providers. The system collects and analyzes the patient's health information and selects the most appropriate healthcare provider based on that information.

[0404] System configuration

[0405] Entering patient health information

[0406] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application provided on the device, and then press the submit button.

[0407] Sending and Receiving Health Information

[0408] The device sends the entered health information to the server, which sends the information as an HTTP POST request.

[0409] The server receives the patient's health information sent from the terminal and stores it in a database. After receiving the data, the server verifies that each element of the data is accurate.

[0410] Selection of healthcare provider

[0411] The server retrieves a list of available healthcare providers from a database, generates a prompt to select the most suitable healthcare provider for the patient, sends the generated prompt to the generation AI (OpenAI's GPT-based model), and receives a response from the AI ​​model.

[0412] The generative AI analyzes the prompts and responds with a text recommending the most suitable healthcare provider for the patient, including the provider's name and specialty.

[0413] Healthcare provider notification

[0414] The server analyzes the AI's response, extracts information about the healthcare provider recommended by the AI, and generates a response containing details of the selected healthcare provider based on that information and sends it back to the device.

[0415] The terminal receives the response from the server and displays to the user information about healthcare providers who recommend vaccinations.

[0416] Specific examples

[0417] For example, a user named Tanaka uses a terminal to input his / her health information. Tanaka writes his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and presses the send button. The terminal then sends the health information to the server.

[0418] Based on the received information, the server sends a prompt to the generating AI: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generating AI analyzes the list of available healthcare providers and returns the answer that "Dr. Suzuki (Internal Medicine)" is best.

[0419] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable healthcare provider for Mr. Tanaka, and sends it to the terminal. The terminal receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended."

[0420] This process ensures that Tanaka is quickly and efficiently matched with the appropriate healthcare provider and receives the medical services he needs.

[0421] The processing flow will be explained below.

[0422] Step 1:

[0423] The user enters health information into the terminal. The entered information includes name, age, medical history, symptoms, etc. The user presses the send button.

[0424] Step 2:

[0425] The device sends the health information entered by the user to the server as an HTTP POST request.

[0426] Step 3:

[0427] The server receives the patient's health information from the terminal and stores it in a database. It also verifies that the format of the received data is correct.

[0428] Step 4:

[0429] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[0430] Step 5:

[0431] The server generates a prompt for the AI, which includes the patient's health information and a list of available providers, in the format "Which provider is best?"

[0432] Step 6:

[0433] The server calls the OpenAI API and sends a prompt to the generated AI, authenticating the request with an API key.

[0434] Step 7:

[0435] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[0436] Step 8:

[0437] The server analyzes the AI's response, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[0438] Step 9:

[0439] The server returns the recommended healthcare provider information to the device as an HTTP response.

[0440] Step 10:

[0441] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider.

[0442] Step 11:

[0443] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[0444] Example 1

[0445] 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."

[0446] Conventional patient-healthcare provider matching systems have difficulty efficiently selecting the most appropriate healthcare provider based on the patient's detailed health information. Another problem is that it takes a lot of time and effort for patients to find the appropriate healthcare provider. Furthermore, there is a lack of a way to accurately and quickly convey patient information to healthcare providers.

[0447] 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.

[0448] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for storing the patient health information received by the receiving means in a database and selecting a healthcare provider based on the data, and a notifying means for notifying the patient of the healthcare provider selected by the generating AI means. This makes it possible to efficiently and accurately select the most appropriate healthcare provider based on the patient's health information and quickly notify the information.

[0449] "Patient health information" refers to information that indicates the patient's health condition, such as the patient's name, age, medical history, and symptoms.

[0450] "Input means" refers to the means used by patients to enter their health information, specifically a web form on a computer or smartphone or a mobile application.

[0451] The "receiving means" is a means for receiving the patient's health information transmitted from the input means, and the server is mainly responsible for this role.

[0452] "Database" means an electronic record system for storing patient health information and healthcare provider information.

[0453] "Generative AI method" refers to an artificial intelligence model used to select the most appropriate healthcare provider based on a patient's health information and a list of healthcare providers.

[0454] "Notification means" refers to a means for conveying information about the healthcare provider selected by the generation AI means to the patient, and primarily refers to an electronic message sent from the server to the terminal.

[0455] A "prompt" is text data to be input into the generative AI, and includes questions about the patient's health information and required medical services.

[0456] A "Response" is a reply message from the Generating AI that includes detailed information about a recommended healthcare provider.

[0457] The system of the present invention utilizes generative AI models to efficiently match patients with healthcare providers. The system collects and analyzes patient health information and then selects the most appropriate healthcare provider based on that information.

[0458] Entering and submitting health information

[0459] To enter their health information, users use devices such as computers or smartphones. They access a web form or mobile application on their device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses a submit button to send the information to the server. When the submit button is pressed, the device sends the data via an HTTP POST request.

[0460] Receiving and storing health information

[0461] The server receives the HTTP POST request sent from the device, analyzes the request, and stores the submitted patient health information in a database, performing checks to verify the accuracy of the data.

[0462] Selection of healthcare provider

[0463] The server retrieves a list of available healthcare providers from a database. This list includes information such as the provider's name, specialty, and location. Based on the patient's health information and the list of healthcare providers, the server generates a prompt for the generative AI model. For example, the server creates a prompt such as, "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generated prompt is then sent to the generative AI (e.g., OpenAI's GPT-based model).

[0464] Receiving a response from the AI

[0465] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[0466] Notification of recommendation information

[0467] The server analyzes the response from the AI ​​generator and extracts details of the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The device receives this response and displays the information to the user.

[0468] Specific examples

[0469] For example, a user, Mr. Takahashi, uses a terminal to input his health information. Mr. Takahashi writes "Ichiro Takahashi, 70 years old, at risk of high blood pressure" in the input form and presses the send button. The terminal then sends the health information to the server.

[0470] Based on the received information, the server sends the following prompt to the Generative AI: "Ichiro Takahashi, 70 years old, at risk of high blood pressure. Which healthcare provider is best?" The Generative AI analyzes the list of available healthcare providers and returns the answer that "Dr. Sato (cardiologist)" is best.

[0471] Based on this answer, the server generates a response containing information about Dr. Sato, the most suitable medical provider for Mr. Takahashi, and sends it to the terminal. The terminal receives this response and displays it to Mr. Takahashi, saying, "Dr. Sato is recommended."

[0472] This process ensures that Takahashi is quickly and efficiently matched with the appropriate medical provider and receives the medical services he needs.

[0473] Through the above steps, the system of the present invention is able to select the most suitable healthcare provider based on the patient's health information and notify the patient promptly and accurately.

[0474] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0475] Step 1: Enter patient health information

[0476] Users use devices such as computers or smartphones to enter their health information. They access a web form or mobile application on the device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses the send button, which prepares the input data for transmission to the device.

[0477] Step 2: Submit your health information

[0478] The device sends the health information entered by the user to the server as an HTTP POST request. The input at this point is the user's health information (name, age, medical history, symptoms), and the output is an HTTP request sent to the server. After sending, the device notifies the user that "Sending has been completed."

[0479] Step 3: Receiving and storing health information

[0480] The server receives the HTTP POST request sent from the device. The server analyzes the request, extracts the submitted patient health information, and stores it in a database. In this process, the input is the HTTP request, and the output is the patient health information stored in the database. The server also performs checks to verify the accuracy of the data.

[0481] Step 4: Get a list of healthcare providers

[0482] The server retrieves a list of available providers from a database, which includes information such as provider name, specialty, location, etc. The input is a query to the database, and the output is a list of providers.

[0483] Step 5: Generate and send the prompt

[0484] The server generates a prompt to send to the generative AI model based on the user's health information and list of healthcare providers. For example, it creates a prompt with the following content: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The input is the patient's health information and list of healthcare providers, and the output is the generated prompt text. The generated prompt is sent to the generative AI (e.g., OpenAI's GPT-based model).

[0485] Step 6: Receive a response from the AI

[0486] The server receives a response from the generation AI. The response includes the name and specialty of the recommended healthcare provider. The input is the response from the generation AI, and the output is information about the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[0487] Step 7: Parse the response and generate recommendations

[0488] The server analyzes the response received from the generation AI and extracts detailed information about the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The input is the response from the generation AI, and the output is a message to notify the patient.

[0489] Step 8: Submit and view your recommendations

[0490] The server sends the generated response to the terminal. The terminal analyzes the received response and displays detailed information about the recommended healthcare provider to the user. The input is the response from the server, and the output is the information displayed to the user (e.g., "Dr. Suzuki is recommended").

[0491] Through this series of processes, users are quickly and efficiently matched with appropriate medical providers, enabling them to receive medical services efficiently.

[0492] (Application example 1)

[0493] 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."

[0494] Conventional healthcare provider and patient matching systems have the problem that patients must manually enter their health information and it takes time to select an appropriate healthcare provider. It can also be difficult for patients to accurately enter their medical conditions and symptoms, which can lead to the wrong healthcare provider being recommended. This system is required to allow patients to easily enter their health information and quickly and accurately recommend the most appropriate healthcare provider.

[0495] 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.

[0496] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information received by the receiving means, a notification means for notifying the patient of the healthcare provider selected by the generating AI means, an input means for inputting the patient's health information in real time using a smart device, and a transmission means for acquiring and transmitting the health information by voice input or code scanning. This allows the patient to easily and quickly input their health information using a smart device, and enables the generating AI to quickly and accurately recommend the most suitable healthcare provider.

[0497] "Patient health information" refers to general information about the patient's health condition, such as the patient's name, age, medical history, current symptoms, allergy information, and medications currently being taken.

[0498] "Input means" refers to devices or interfaces through which patients input their health information, including smartphones, tablets, smart glasses, etc.

[0499] The "receiving means" refers to a server or a communication interface for receiving the patient's health information transmitted from the input means.

[0500] "Generative AI means" refers to the artificial intelligence model used to select healthcare providers based on received patient health information, specifically a generative AI model (e.g., a GPT-based model).

[0501] "Notification means" refers to a communication interface or display device used to notify patients of the information about the healthcare provider selected by the generation AI means.

[0502] "Smart devices" refer to electronic devices that are equipped with voice input, camera functions, displays, etc. and can collect and display patient health information, and specifically include smart glasses, smartphones, tablets, etc.

[0503] The "transmission means" refers to a function for transmitting patient health information acquired from a smart device to a server, specifically a data transmission means via an internet connection.

[0504] The present invention is a system for efficiently matching patients with healthcare providers, and in particular, it relates to the collection of real-time health information using smart devices and the selection of the most suitable healthcare provider using AI generation. The system is configured as follows:

[0505] Hardware and Software Use

[0506] 1. Hardware:

[0507] Smart devices (e.g., smart glasses, smartphones)

[0508] Voice input function

[0509] Camera features

[0510] Display Features

[0511] server:

[0512] Data Processing Server

[0513] Hospital Information System

[0514] Database server (storing patient and provider information)

[0515] 2. Software:

[0516] Data transmission API (e.g., using an HTTP POST request)

[0517] Server-side systems (e.g. web frameworks such as Flask and Django)

[0518] Generative AI models (e.g., OpenAI's GPT-based models)

[0519] Database management systems (e.g., MySQL, PostgreSQL)

[0520] Detailed System Description

[0521] Entering patient health information

[0522] Users input their health information using their smart devices. When using smart glasses, health information can be obtained using voice input or QR code scanning with the camera, and the information can be sent directly to the system. For example, users can input information such as "I have a headache" or "I have a history of high blood pressure" using voice input.

[0523] Sending and Receiving Health Information

[0524] The device sends the entered health information to the server via a data transmission API. The sent data reaches the server through a protocol (e.g., HTTP POST request) and is stored in a database.

[0525] Selection of healthcare provider

[0526] The server generates prompts based on the received patient health information and sends them to the generative AI model, which then selects the most appropriate healthcare provider based on the prompts shown below.

[0527] For example: "Taro Tanaka, 65 years old, at risk for diabetes. Which healthcare provider is best?"

[0528] The generative AI model analyzes the prompt and selects the most appropriate healthcare provider based on information about multiple healthcare providers retrieved from a database. For example, it may recommend an "internal medicine specialist."

[0529] Healthcare provider notification

[0530] The server analyzes the information on healthcare providers obtained from the generative AI model and notifies the patient of the results. The device receives the response from the server and displays details of the recommended healthcare provider to the patient. For example, the smart glasses display may show information such as "An internal medicine specialist is recommended."

[0531] This system allows patients to easily and quickly enter their health information using smart devices, and uses generative AI to quickly and accurately recommend the most suitable healthcare provider.

[0532] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0533] Step 1:

[0534] Users use smart devices to input their own health information. Specifically, they may use the voice input function to input information such as "I have a headache" or "I have a history of high blood pressure," or they may use the camera function of smart glasses to scan QR codes to obtain information about medications. These pieces of information are treated as input.

[0535] Step 2:

[0536] The device sends the collected health information to the server using a data transmission API. The data is packaged in JSON format and sent to the server via an HTTP POST request. The server receives this health information and stores it in a database. The input at this stage is the health information, and the output is storing it in the database and confirming receipt on the server side.

[0537] Step 3:

[0538] The server generates a prompt to be sent to the generative AI model based on the patient's health information stored in the database. Specifically, it creates a prompt in the format "Taro Tanaka, 65 years old, at risk of diabetes. Who is the best healthcare provider?" This prompt is sent to the generative AI model. The input is the health information, and the output is the generated prompt.

[0539] Step 4:

[0540] The generative AI model analyzes the sent prompt and selects the most suitable healthcare provider based on information on multiple healthcare providers retrieved from a database. Based on the prompt, the generative AI uses internal learning data and logic to output the name and specialty of the most suitable healthcare provider. The input at this stage is the prompt, and the output is the selection result of the most suitable healthcare provider.

[0541] Step 5:

[0542] The server receives the response from the generative AI model and processes the information of the healthcare provider selected by the generative AI. Specifically, it analyzes the healthcare provider's name, specialty, contact information, etc., and generates a message to notify the patient. The input at this stage is the response from the generative AI model, and the output is the notification message.

[0543] Step 6:

[0544] The terminal receives the notification message from the server and displays the details of the recommended healthcare provider to the patient. In the case of smart glasses, the display will show "An internal medicine specialist is recommended." The patient can check this information through the smart glasses and contact the healthcare provider. The input at this stage is the notification message, and the output is the display to the patient.

[0545] 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.

[0546] The system of the present invention utilizes generative AI and an emotion engine to efficiently match patients and healthcare providers. The system collects and analyzes the patient's health and emotion information, and then selects the most appropriate healthcare provider based on that information.

[0547] System configuration

[0548] Entering patient health information

[0549] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application on the device and press the submit button.

[0550] Recognition of emotional information

[0551] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[0552] Sending and receiving health and emotional information

[0553] The device sends the entered health information and emotion label to the server as an HTTP POST request.

[0554] The server receives the patient's health information and emotion label from the device, stores them in a database, and verifies that the format of the received data is correct.

[0555] Selection of healthcare provider

[0556] The server retrieves a list of available providers from the database, including the provider's name, specialty, availability, etc.

[0557] The server generates a prompt for the generative AI, which includes the patient's health information, an emotional label, and a list of available healthcare providers, in the form of "Which healthcare provider is best?"

[0558] The server calls OpenAI's API and sends a prompt to the generating AI, authenticating the request with an API key.

[0559] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[0560] Healthcare provider notification

[0561] The server analyzes the response of the generation AI, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[0562] The server then returns customized notification content based on the recommended healthcare provider information and emotion label to the device as an HTTP response.

[0563] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[0564] Specific examples

[0565] For example, a user named Tanaka uses a device to input his / her health information. Tanaka enters his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and then presses the send button. The device sends the health information to the server along with an emotional label indicating the level of stress Tanaka felt while entering the information.

[0566] Based on the received information, the server sends the following prompt to the generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional label indicating high stress. Which healthcare provider is best?" The generative AI analyzes the list of available healthcare providers and replies, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[0567] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable medical provider for Mr. Tanaka, and adds a kind message that takes into consideration Mr. Tanaka's stress, and sends this to the device. The device receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended. He is an expert in reducing stress."

[0568] This allows Tanaka to be quickly and efficiently matched with the right medical provider and receive emotionally sensitive medical care.

[0569] The processing flow will be explained below.

[0570] Step 1:

[0571] The user enters health information into the terminal. The information includes name, age, medical history, current symptoms, etc. The user then presses the send button.

[0572] Step 2:

[0573] When the device transmits the user's health information, it collects the user's emotional indicators, including input speed, voice tone, and facial expression data (when using the camera).

[0574] Step 3:

[0575] The device sends the collected health information and emotional indicators to the server as an HTTP POST request.

[0576] Step 4:

[0577] The server receives the patient's health information and emotional indicators sent from the device, temporarily stores the received data, and verifies that the format is correct.

[0578] Step 5:

[0579] The server uses an emotion engine to analyze the emotion indicators and generate an emotion label for the user, which may include stress, satisfaction, relief, etc.

[0580] Step 6:

[0581] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[0582] Step 7:

[0583] The server combines the patient's health information with the emotion label and the list of healthcare providers to generate prompts for the generative AI, such as "Please select the most appropriate healthcare provider based on the patient's health information and emotion label."

[0584] Step 8:

[0585] The server calls OpenAI's API to send a prompt to the generating AI, authenticating using the API key.

[0586] Step 9:

[0587] The server receives the response from the generative AI, which includes the name and specialty of the recommended healthcare provider.

[0588] Step 10:

[0589] The server analyzes the generated AI's response and extracts information about the recommended healthcare provider.

[0590] Step 11:

[0591] The server generates customized notification content based on the recommended healthcare provider information and emotion labels, for example adding a message encouraging users to relax if they are feeling highly stressed.

[0592] Step 12:

[0593] The server returns the customized notification content to the device as an HTTP response.

[0594] Step 13:

[0595] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider.

[0596] Step 14:

[0597] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[0598] Example 2

[0599] 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."

[0600] Conventional patient-healthcare provider matching systems selected healthcare providers based solely on the patient's health information, making it difficult to select an appropriate healthcare provider that took the patient's emotional state into consideration. Furthermore, there was no way to collect and analyze emotional information, such as stress or anxiety, when the patient entered their information, making it difficult to select the healthcare provider best suited to the patient. This meant that patients were unable to receive appropriate healthcare services quickly and efficiently.

[0601] 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.

[0602] In this invention, the server includes a means for inputting a patient's health information and emotional information, a means for receiving the patient's health information and emotional information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, and a means for notifying the patient of a customized notification based on the healthcare provider information and emotional information selected by the generating AI means. This enables the selection of a healthcare provider that takes the patient's emotional state into consideration, enabling the patient to receive appropriate healthcare services quickly and efficiently.

[0603] "Patient health information" is data that indicates the patient's condition, including name, age, medical history, symptoms, etc.

[0604] "Emotional information" is data that indicates the emotional state of the patient, and includes information analyzed from voice, facial expression, and input speed.

[0605] The "input means" refers to a means by which a patient inputs health information and emotional information, and is a terminal such as a computer or smartphone.

[0606] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[0607] "Generative AI means" means means including artificial intelligence for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means.

[0608] "Notification means" means a means for notifying a patient of customized notification content based on the healthcare provider information and emotional information selected by the generation AI means.

[0609] "Server" means a central control unit that receives, processes, and stores data, selects healthcare providers using generative AI means, and notifies the results.

[0610] "Database" means a storage device for storing received patient health and emotional information and for maintaining available healthcare provider information.

[0611] "Prompts" are questions or instructions posed to the generative AI, which in this system are used to select a healthcare provider based on the patient's health and emotional information.

[0612] The "emotion engine" includes systems and algorithms for analyzing data such as voice, facial expressions, and input speed from the patient's input behavior and generating emotional information.

[0613] This invention is a system that utilizes generative AI and an emotion engine to efficiently match patients with healthcare providers. The system collects and analyzes patients' health and emotional information, and selects the most suitable healthcare provider based on this information.

[0614] System configuration

[0615] This system is composed of the following hardware and software: The hardware includes devices such as computers and smartphones. The software includes a web browser, mobile application, emotion engine, and generative AI (e.g., OpenAI API).

[0616] Specific processing flow

[0617] Entering patient health information

[0618] A user uses a device to enter their health information, for example, by entering their name, age, medical history, symptoms, etc. into a web form or mobile application, and then pressing a submit button. This entered health information is then sent to the system.

[0619] Recognition of emotional information

[0620] The device collects emotional indicators such as voice, facial expressions, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as "stress" and "anxiety."

[0621] Sending and receiving health and emotional information

[0622] The device sends the collected health information and emotion labels to the server via an HTTP POST request.

[0623] The server receives the data and stores it in a database. It also verifies that the received information is in the correct format.

[0624] Selection of healthcare provider

[0625] The server retrieves a list of available healthcare providers from a database, then generates a prompt containing the patient's health information and emotion label and sends it to a generative AI (e.g., OpenAI's API).

[0626] Acquisition and notification of recommended medical providers

[0627] The server receives the response from the AI ​​generator, extracts information about recommended healthcare providers, and generates customized notification content based on that information and the emotion label, which is then sent to the device as an HTTP response.

[0628] The device receives this response and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[0629] Specific examples

[0630] A 65-year-old user named Tanaka enters his health information using his smartphone. Tanaka enters his name "Taro Tanaka," his age "65," and his medical history of "risk of diabetes" into the input form, then presses the submit button. At this time, the device captures Tanaka's voice, facial expression, and input speed, and the emotion engine generates an emotion label such as "high stress." The device then sends this information to the server as an HTTP POST request.

[0631] The server receives the information and stores it in a database. It then sends the following prompt to the Generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional labels indicate high stress. Which healthcare provider is best?" The Generative AI responds, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[0632] Based on this answer, the server generates a response including information about Dr. Suzuki and a message that takes Mr. Tanaka into consideration, and sends it to the device. The device receives this and displays to Mr. Tanaka, "Dr. Suzuki is recommended. He is an expert in reducing stress." This allows Mr. Tanaka to be quickly and efficiently matched with an appropriate medical provider, and to receive medical services that are also considerate of his emotional state.

[0633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0634] Step 1:

[0635] Users use the device to enter their health information: they open a web browser or mobile application, enter information such as their name, age, medical history, and symptoms, and then press the submit button.

[0636] Input: Name, age, medical history, symptoms, and other health information

[0637] Output: The entered health information is saved on the device.

[0638] Specific behavior:

[0639] A user opens a web browser or mobile application.

[0640] Enter your health information in the form provided.

[0641] Click the send button to send the information.

[0642] Step 2:

[0643] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as stress or anxiety.

[0644] Input: User voice, facial expressions, and typing speed

[0645] Output: Emotion labels generated by the emotion engine

[0646] Specific behavior:

[0647] The device's microphone and camera capture the user's voice and facial expressions.

[0648] Collect behavioral data such as typing speed.

[0649] The collected data is sent to the emotion engine for analysis.

[0650] The emotion engine generates emotion labels.

[0651] Step 3:

[0652] The device sends the collected health information and emotion labels to the server using an HTTP POST request.

[0653] Input: Health information, emotion labels

[0654] Output: Data sent to the server

[0655] Specific behavior:

[0656] The device makes an HTTP POST request containing the health information and emotion label.

[0657] Send this request to the server.

[0658] Step 4:

[0659] The server validates the received data and stores it in the database. It checks whether the received data is in the correct format.

[0660] Input: Health information sent from the device, emotion label

[0661] Output: Validated data stored in a database

[0662] Specific behavior:

[0663] The server receives an HTTP POST request.

[0664] Validate that the data is in the correct format.

[0665] The validated data is stored in the database.

[0666] Step 5:

[0667] The server retrieves a list of available healthcare providers from the database and generates a prompt to the generative AI means, which includes the patient's health information and an emotion label.

[0668] Input: Patient health information stored in a database, emotion labels

[0669] Output: Generated prompt

[0670] Specific behavior:

[0671] The server retrieves a list of available healthcare providers from a database.

[0672] Prompts are generated based on provider information, patient health information, and emotion labels.

[0673] Step 6:

[0674] The server sends a prompt to a generative AI tool (e.g., OpenAI's API), which contains the patient's health information and an emotion label.

[0675] Input: Generated prompt

[0676] Output: Recommendation results from the generative AI

[0677] Specific behavior:

[0678] The server sends the prompt to the API, which generates the AI.

[0679] Receive the generative AI means' response to the prompt.

[0680] Step 7:

[0681] The server analyzes the response from the generation AI and extracts information on recommended healthcare providers, which is then used to generate notifications for patients.

[0682] Input: Response from the generation AI

[0683] Output: Information and emotionally sensitive message for the notified healthcare provider

[0684] Specific behavior:

[0685] The server analyzes the response from the generated AI.

[0686] Extract recommended healthcare provider information.

[0687] Create notifications that are patient-friendly.

[0688] Step 8:

[0689] The server sends the customized notification content to the terminal as an HTTP response.

[0690] Input: Notification content

[0691] Output: Notification content sent to device

[0692] Specific behavior:

[0693] The server embeds the customized notification content in the HTTP response.

[0694] This HTTP response is sent to the terminal.

[0695] Step 9:

[0696] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[0697] Input: Notification content received from the server

[0698] Output: The notification that is displayed to the user

[0699] Specific behavior:

[0700] The device receives the HTTP response.

[0701] Display notification content in a user-friendly format.

[0702] (Application example 2)

[0703] 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."

[0704] In today's healthcare delivery environment, it remains difficult to quickly and effectively select the most appropriate healthcare provider for a patient. This can result in patients not receiving the medical care they need in a timely manner, leading to treatment delays and inappropriate medical responses. Furthermore, while providing emotionally sensitive healthcare has a significant impact on patient satisfaction and treatment outcomes, the current system does not adequately consider this important aspect. Furthermore, healthcare service scheduling and electronic payments are not centralized, resulting in increased hassle.

[0705] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0706] In this invention, the server includes an input means for inputting the patient's health information, an emotion engine means for the receiving means to collect and analyze emotional information along with the health information, a generation AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, a notification means, and a payment means. This allows the selection of the most appropriate healthcare provider based on the patient's health information and emotional information, and enables recommendation of healthcare services, reservations, and electronic payment that take emotions into consideration.

[0707] "Patient Health Information" refers to a set of data related to a patient's health status, such as the patient's name, age, medical history, and current symptoms.

[0708] "Input means" refers to the means by which patients input their health information, and includes devices such as computers and smartphones, web forms, and mobile applications.

[0709] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[0710] The "emotion engine means" is a means for analyzing emotion indicators such as voice, facial expression, and input speed collected together with the received health information of the patient, and generating emotion labels.

[0711] "Generative AI methods" refer to artificial intelligence models and algorithms that select the most appropriate healthcare provider based on a patient's health and emotional information.

[0712] "Notification means and payment means" refers to means for notifying patients of the information about the healthcare provider selected by the generating AI means, and for making reservations for healthcare services and making electronic payments.

[0713] "Database" refers to a digital storage system for storing patient health and emotional information and available healthcare provider information.

[0714] "Healthcare provider" refers to a doctor, nurse, specialist, or other health care professional who provides medical services, treatment, or diagnosis to a patient.

[0715] The system of the present invention has the function of collecting and analyzing a patient's health information and emotional information to efficiently match patients with healthcare providers, and recommending the most suitable healthcare provider. It also enables medical service reservations and electronic payments. The system includes an input means, a receiving means, an emotion engine means, a generation AI means, a notification means, and a payment means.

[0716] System configuration

[0717] Entering patient health information

[0718] Users enter their own health information using a device such as a smartphone, entering the patient's name, age, medical history, symptoms, and other health information into a mobile application on the device, and then pressing the send button.

[0719] Collecting and analyzing emotional information

[0720] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[0721] Sending and receiving health and emotional information

[0722] The device sends the entered health information and emotion label to the server as an HTTP POST request. The server receives the patient's health information and emotion label from the device and stores them in a database.

[0723] Selection of healthcare provider

[0724] The server retrieves a list of available healthcare providers from the database. The retrieved list includes the provider's name, specialty, availability, etc. The server generates a prompt for the generative AI model mentioned above. The prompt includes a question about the most suitable healthcare provider based on the patient's health information and emotion label and the list of available healthcare providers. An example of a specific prompt is, "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is the most suitable?"

[0725] Notification of recommendation information

[0726] The server receives the response from the generation AI and extracts information about the recommended healthcare provider. The server then generates a response based on the extracted information and sends it back to the device with a message that takes emotional information into consideration. For example, the message might read, "Dr. Suzuki is recommended. He is an expert in stress reduction."

[0727] Medical appointment booking and electronic payment

[0728] Users can select medical services based on recommendations from the server and make electronic payments directly within the application, making the system an efficient and emotionally sensitive way to book and pay for medical services easily and quickly.

[0729] Technology used

[0730] The hardware used is a computer terminal such as a smartphone or server, and the software used is a mobile application, Python, OpenAI's GPT-3 API, etc. Data is sent and received via HTTP and stored in a database.

[0731] As a concrete example of the entire system, when Tanaka uses the "MedPay" app to make a medical appointment, the prompt that appears is as follows:

[0732] "Taro Tanaka, 65, at risk for diabetes. Emotional label indicating high stress. Which healthcare provider is best?"

[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 launches the mobile application on their smartphone and enters their health information. Here, the user enters their name, age, medical history, symptoms, etc. into the input form and presses the submit button. The input data is packaged in JSON format. The entered data is temporarily stored on the device and prepared for transmission.

[0736] Step 2:

[0737] The device collects emotional information at the same time as the health information is entered. Emotional information is an indicator of the stress or anxiety the user felt while entering data, and is acquired using the device's camera and microphone. Input speed and touch patterns are also analyzed. This data is analyzed by the emotion engine and generated as an emotional label. The analyzed emotional label is then generated in JSON format.

[0738] Step 3:

[0739] The device sends the health information and analyzed emotion label to the server using an HTTP POST request, with the data sent in JSON format. The data includes the following items: "Name," "Age," "Symptoms," and "Emotion Label."

[0740] Step 4:

[0741] The server receives the health information and emotion labels received from the device and stores them in a database that also contains a list of existing healthcare providers and their availability information, and verifies the received data for correct formatting.

[0742] Step 5:

[0743] The server retrieves a list of available providers from a database, including the provider's name, specialty, available hours, etc. The retrieved data is stored in an internal memory.

[0744] Step 6:

[0745] The server generates a prompt for the generative AI model. The prompt includes the patient's health information and emotion label received, as well as the list of healthcare providers obtained. A specific prompt sentence might be generated like this: "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is best?" The prompt sentence is in text format.

[0746] Step 7:

[0747] The server sends a prompt to a generative AI model (e.g., OpenAI's GPT-3) using an API request, with the data sent in plain text format. The API key is used to authenticate the request.

[0748] Step 8:

[0749] The server receives a response from the generative AI model, including the name and specialty of the healthcare provider that the generative AI model finds most suitable. This data is also returned in text format.

[0750] Step 9:

[0751] The server analyzes the response from the generative AI model and extracts information about the recommended healthcare provider. The extracted information is then converted back to JSON format and a response message is generated to be displayed to the user. The message also includes emotionally sensitive content.

[0752] Step 10:

[0753] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider. The user can then select the recommended healthcare provider based on this information.

[0754] Step 11:

[0755] The user selects a recommended medical provider and makes a medical appointment. Once the appointment details are confirmed, the appointment information is sent back to the server from the terminal.

[0756] Step 12:

[0757] The server processes the electronic payment based on the received reservation information. A payment gateway service is used to process the payment, and payment is made using credit card information or an online payment account. The payment success or failure status is returned to the terminal and displayed to the user.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] [Third embodiment]

[0762] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0763] 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.

[0764] 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).

[0765] 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.

[0766] 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.

[0767] 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).

[0768] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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."

[0774] The system of the present invention utilizes generative AI to efficiently match patients with healthcare providers. The system collects and analyzes the patient's health information and selects the most appropriate healthcare provider based on that information.

[0775] System configuration

[0776] Entering patient health information

[0777] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application provided on the device, and then press the submit button.

[0778] Sending and Receiving Health Information

[0779] The device sends the entered health information to the server, which sends the information as an HTTP POST request.

[0780] The server receives the patient's health information sent from the terminal and stores it in a database. After receiving the data, the server verifies that each element of the data is accurate.

[0781] Selection of healthcare provider

[0782] The server retrieves a list of available healthcare providers from a database, generates a prompt to select the most suitable healthcare provider for the patient, sends the generated prompt to the generation AI (OpenAI's GPT-based model), and receives a response from the AI ​​model.

[0783] The generative AI analyzes the prompts and responds with a text recommending the most suitable healthcare provider for the patient, including the provider's name and specialty.

[0784] Healthcare provider notification

[0785] The server analyzes the AI's response, extracts information about the healthcare provider recommended by the AI, and generates a response containing details of the selected healthcare provider based on that information and sends it back to the device.

[0786] The terminal receives the response from the server and displays to the user information about healthcare providers who recommend vaccinations.

[0787] Specific examples

[0788] For example, a user named Tanaka uses a terminal to input his / her health information. Tanaka writes his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and presses the send button. The terminal then sends the health information to the server.

[0789] Based on the received information, the server sends a prompt to the generating AI: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generating AI analyzes the list of available healthcare providers and returns the answer that "Dr. Suzuki (Internal Medicine)" is best.

[0790] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable healthcare provider for Mr. Tanaka, and sends it to the terminal. The terminal receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended."

[0791] This process ensures that Tanaka is quickly and efficiently matched with the appropriate healthcare provider and receives the medical services he needs.

[0792] The processing flow will be explained below.

[0793] Step 1:

[0794] The user enters health information into the terminal. The entered information includes name, age, medical history, symptoms, etc. The user presses the send button.

[0795] Step 2:

[0796] The device sends the health information entered by the user to the server as an HTTP POST request.

[0797] Step 3:

[0798] The server receives the patient's health information from the terminal and stores it in a database. It also verifies that the format of the received data is correct.

[0799] Step 4:

[0800] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[0801] Step 5:

[0802] The server generates a prompt for the AI, which includes the patient's health information and a list of available providers, in the format "Which provider is best?"

[0803] Step 6:

[0804] The server calls the OpenAI API and sends a prompt to the generated AI, authenticating the request with an API key.

[0805] Step 7:

[0806] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[0807] Step 8:

[0808] The server analyzes the AI's response, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[0809] Step 9:

[0810] The server returns the recommended healthcare provider information to the device as an HTTP response.

[0811] Step 10:

[0812] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider.

[0813] Step 11:

[0814] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[0815] Example 1

[0816] 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."

[0817] Conventional patient-healthcare provider matching systems have difficulty efficiently selecting the most appropriate healthcare provider based on the patient's detailed health information. Another problem is that it takes a lot of time and effort for patients to find the appropriate healthcare provider. Furthermore, there is a lack of a way to accurately and quickly convey patient information to healthcare providers.

[0818] 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.

[0819] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for storing the patient health information received by the receiving means in a database and selecting a healthcare provider based on the data, and a notifying means for notifying the patient of the healthcare provider selected by the generating AI means. This makes it possible to efficiently and accurately select the most appropriate healthcare provider based on the patient's health information and quickly notify the information.

[0820] "Patient health information" refers to information that indicates the patient's health condition, such as the patient's name, age, medical history, and symptoms.

[0821] "Input means" refers to the means used by patients to enter their health information, specifically a web form on a computer or smartphone or a mobile application.

[0822] The "receiving means" is a means for receiving the patient's health information transmitted from the input means, and the server is mainly responsible for this role.

[0823] "Database" means an electronic record system for storing patient health information and healthcare provider information.

[0824] "Generative AI method" refers to an artificial intelligence model used to select the most appropriate healthcare provider based on a patient's health information and a list of healthcare providers.

[0825] "Notification means" refers to a means for conveying information about the healthcare provider selected by the generation AI means to the patient, and primarily refers to an electronic message sent from the server to the terminal.

[0826] A "prompt" is text data to be input into the generative AI, and includes questions about the patient's health information and required medical services.

[0827] A "Response" is a reply message from the Generating AI that includes detailed information about a recommended healthcare provider.

[0828] The system of the present invention utilizes generative AI models to efficiently match patients with healthcare providers. The system collects and analyzes patient health information and then selects the most appropriate healthcare provider based on that information.

[0829] Entering and submitting health information

[0830] To enter their health information, users use devices such as computers or smartphones. They access a web form or mobile application on their device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses a submit button to send the information to the server. When the submit button is pressed, the device sends the data via an HTTP POST request.

[0831] Receiving and storing health information

[0832] The server receives the HTTP POST request sent from the device, analyzes the request, and stores the submitted patient health information in a database, performing checks to verify the accuracy of the data.

[0833] Selection of healthcare provider

[0834] The server retrieves a list of available healthcare providers from a database. This list includes information such as the provider's name, specialty, and location. Based on the patient's health information and the list of healthcare providers, the server generates a prompt for the generative AI model. For example, the server creates a prompt such as, "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generated prompt is then sent to the generative AI (e.g., OpenAI's GPT-based model).

[0835] Receiving a response from the AI

[0836] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[0837] Notification of recommendation information

[0838] The server analyzes the response from the AI ​​generator and extracts details of the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The device receives this response and displays the information to the user.

[0839] Specific examples

[0840] For example, a user, Mr. Takahashi, uses a terminal to input his health information. Mr. Takahashi writes "Ichiro Takahashi, 70 years old, at risk of high blood pressure" in the input form and presses the send button. The terminal then sends the health information to the server.

[0841] Based on the received information, the server sends the following prompt to the Generative AI: "Ichiro Takahashi, 70 years old, at risk of high blood pressure. Which healthcare provider is best?" The Generative AI analyzes the list of available healthcare providers and returns the answer that "Dr. Sato (cardiologist)" is best.

[0842] Based on this answer, the server generates a response containing information about Dr. Sato, the most suitable medical provider for Mr. Takahashi, and sends it to the terminal. The terminal receives this response and displays it to Mr. Takahashi, saying, "Dr. Sato is recommended."

[0843] This process ensures that Takahashi is quickly and efficiently matched with the appropriate medical provider and receives the medical services he needs.

[0844] Through the above steps, the system of the present invention is able to select the most suitable healthcare provider based on the patient's health information and notify the patient promptly and accurately.

[0845] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0846] Step 1: Enter patient health information

[0847] Users use devices such as computers or smartphones to enter their health information. They access a web form or mobile application on the device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses the send button, which prepares the input data for transmission to the device.

[0848] Step 2: Submit your health information

[0849] The device sends the health information entered by the user to the server as an HTTP POST request. The input at this point is the user's health information (name, age, medical history, symptoms), and the output is an HTTP request sent to the server. After sending, the device notifies the user that "Sending has been completed."

[0850] Step 3: Receiving and storing health information

[0851] The server receives the HTTP POST request sent from the device. The server analyzes the request, extracts the submitted patient health information, and stores it in a database. In this process, the input is the HTTP request, and the output is the patient health information stored in the database. The server also performs checks to verify the accuracy of the data.

[0852] Step 4: Get a list of healthcare providers

[0853] The server retrieves a list of available providers from a database, which includes information such as provider name, specialty, location, etc. The input is a query to the database, and the output is a list of providers.

[0854] Step 5: Generate and send the prompt

[0855] The server generates a prompt to send to the generative AI model based on the user's health information and list of healthcare providers. For example, it creates a prompt with the following content: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The input is the patient's health information and list of healthcare providers, and the output is the generated prompt text. The generated prompt is sent to the generative AI (e.g., OpenAI's GPT-based model).

[0856] Step 6: Receive a response from the AI

[0857] The server receives a response from the generation AI. The response includes the name and specialty of the recommended healthcare provider. The input is the response from the generation AI, and the output is information about the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[0858] Step 7: Parse the response and generate recommendations

[0859] The server analyzes the response received from the generation AI and extracts detailed information about the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The input is the response from the generation AI, and the output is a message to notify the patient.

[0860] Step 8: Submit and view your recommendations

[0861] The server sends the generated response to the terminal. The terminal analyzes the received response and displays detailed information about the recommended healthcare provider to the user. The input is the response from the server, and the output is the information displayed to the user (e.g., "Dr. Suzuki is recommended").

[0862] Through this series of processes, users are quickly and efficiently matched with appropriate medical providers, enabling them to receive medical services efficiently.

[0863] (Application example 1)

[0864] 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."

[0865] Conventional healthcare provider and patient matching systems have the problem that patients must manually enter their health information and it takes time to select an appropriate healthcare provider. It can also be difficult for patients to accurately enter their medical conditions and symptoms, which can lead to the wrong healthcare provider being recommended. This system is required to allow patients to easily enter their health information and quickly and accurately recommend the most appropriate healthcare provider.

[0866] 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.

[0867] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information received by the receiving means, a notification means for notifying the patient of the healthcare provider selected by the generating AI means, an input means for inputting the patient's health information in real time using a smart device, and a transmission means for acquiring and transmitting the health information by voice input or code scanning. This allows the patient to easily and quickly input their health information using a smart device, and enables the generating AI to quickly and accurately recommend the most suitable healthcare provider.

[0868] "Patient health information" refers to general information about the patient's health condition, such as the patient's name, age, medical history, current symptoms, allergy information, and medications currently being taken.

[0869] "Input means" refers to devices or interfaces through which patients input their health information, including smartphones, tablets, smart glasses, etc.

[0870] The "receiving means" refers to a server or a communication interface for receiving the patient's health information transmitted from the input means.

[0871] "Generative AI means" refers to the artificial intelligence model used to select healthcare providers based on received patient health information, specifically a generative AI model (e.g., a GPT-based model).

[0872] "Notification means" refers to a communication interface or display device used to notify patients of the information about the healthcare provider selected by the generation AI means.

[0873] "Smart devices" refer to electronic devices that are equipped with voice input, camera functions, displays, etc. and can collect and display patient health information, and specifically include smart glasses, smartphones, tablets, etc.

[0874] The "transmission means" refers to a function for transmitting patient health information acquired from a smart device to a server, specifically a data transmission means via an internet connection.

[0875] The present invention is a system for efficiently matching patients with healthcare providers, and in particular, it relates to the collection of real-time health information using smart devices and the selection of the most suitable healthcare provider using AI generation. The system is configured as follows:

[0876] Hardware and Software Use

[0877] 1. Hardware:

[0878] Smart devices (e.g., smart glasses, smartphones)

[0879] Voice input function

[0880] Camera features

[0881] Display Features

[0882] server:

[0883] Data Processing Server

[0884] Hospital Information System

[0885] Database server (storing patient and provider information)

[0886] 2. Software:

[0887] Data transmission API (e.g., using an HTTP POST request)

[0888] Server-side systems (e.g. web frameworks such as Flask and Django)

[0889] Generative AI models (e.g., OpenAI's GPT-based models)

[0890] Database management systems (e.g., MySQL, PostgreSQL)

[0891] Detailed System Description

[0892] Entering patient health information

[0893] Users input their health information using their smart devices. When using smart glasses, health information can be obtained using voice input or QR code scanning with the camera, and the information can be sent directly to the system. For example, users can input information such as "I have a headache" or "I have a history of high blood pressure" using voice input.

[0894] Sending and Receiving Health Information

[0895] The device sends the entered health information to the server via a data transmission API. The sent data reaches the server through a protocol (e.g., HTTP POST request) and is stored in a database.

[0896] Selection of healthcare provider

[0897] The server generates prompts based on the received patient health information and sends them to the generative AI model, which then selects the most appropriate healthcare provider based on the prompts shown below.

[0898] For example: "Taro Tanaka, 65 years old, at risk for diabetes. Which healthcare provider is best?"

[0899] The generative AI model analyzes the prompt and selects the most appropriate healthcare provider based on information about multiple healthcare providers retrieved from a database. For example, it may recommend an "internal medicine specialist."

[0900] Healthcare provider notification

[0901] The server analyzes the information on healthcare providers obtained from the generative AI model and notifies the patient of the results. The device receives the response from the server and displays details of the recommended healthcare provider to the patient. For example, the smart glasses display may show information such as "An internal medicine specialist is recommended."

[0902] This system allows patients to easily and quickly enter their health information using smart devices, and uses generative AI to quickly and accurately recommend the most suitable healthcare provider.

[0903] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0904] Step 1:

[0905] Users use smart devices to input their own health information. Specifically, they may use the voice input function to input information such as "I have a headache" or "I have a history of high blood pressure," or they may use the camera function of smart glasses to scan QR codes to obtain information about medications. These pieces of information are treated as input.

[0906] Step 2:

[0907] The device sends the collected health information to the server using a data transmission API. The data is packaged in JSON format and sent to the server via an HTTP POST request. The server receives this health information and stores it in a database. The input at this stage is the health information, and the output is storing it in the database and confirming receipt on the server side.

[0908] Step 3:

[0909] The server generates a prompt to be sent to the generative AI model based on the patient's health information stored in the database. Specifically, it creates a prompt in the format "Taro Tanaka, 65 years old, at risk of diabetes. Who is the best healthcare provider?" This prompt is sent to the generative AI model. The input is the health information, and the output is the generated prompt.

[0910] Step 4:

[0911] The generative AI model analyzes the sent prompt and selects the most suitable healthcare provider based on information on multiple healthcare providers retrieved from a database. Based on the prompt, the generative AI uses internal learning data and logic to output the name and specialty of the most suitable healthcare provider. The input at this stage is the prompt, and the output is the selection result of the most suitable healthcare provider.

[0912] Step 5:

[0913] The server receives the response from the generative AI model and processes the information of the healthcare provider selected by the generative AI. Specifically, it analyzes the healthcare provider's name, specialty, contact information, etc., and generates a message to notify the patient. The input at this stage is the response from the generative AI model, and the output is the notification message.

[0914] Step 6:

[0915] The terminal receives the notification message from the server and displays the details of the recommended healthcare provider to the patient. In the case of smart glasses, the display will show "An internal medicine specialist is recommended." The patient can check this information through the smart glasses and contact the healthcare provider. The input at this stage is the notification message, and the output is the display to the patient.

[0916] 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.

[0917] The system of the present invention utilizes generative AI and an emotion engine to efficiently match patients and healthcare providers. The system collects and analyzes the patient's health and emotion information, and then selects the most appropriate healthcare provider based on that information.

[0918] System configuration

[0919] Entering patient health information

[0920] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application on the device and press the submit button.

[0921] Recognition of emotional information

[0922] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[0923] Sending and receiving health and emotional information

[0924] The device sends the entered health information and emotion label to the server as an HTTP POST request.

[0925] The server receives the patient's health information and emotion label from the device, stores them in a database, and verifies that the format of the received data is correct.

[0926] Selection of healthcare provider

[0927] The server retrieves a list of available providers from the database, including the provider's name, specialty, availability, etc.

[0928] The server generates a prompt for the generative AI, which includes the patient's health information, an emotional label, and a list of available healthcare providers, in the form of "Which healthcare provider is best?"

[0929] The server calls OpenAI's API and sends a prompt to the generating AI, authenticating the request with an API key.

[0930] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[0931] Healthcare provider notification

[0932] The server analyzes the response of the generation AI, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[0933] The server then returns customized notification content based on the recommended healthcare provider information and emotion label to the device as an HTTP response.

[0934] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[0935] Specific examples

[0936] For example, a user named Tanaka uses a device to input his / her health information. Tanaka enters his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and then presses the send button. The device sends the health information to the server along with an emotional label indicating the level of stress Tanaka felt while entering the information.

[0937] Based on the received information, the server sends the following prompt to the generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional label indicating high stress. Which healthcare provider is best?" The generative AI analyzes the list of available healthcare providers and replies, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[0938] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable medical provider for Mr. Tanaka, and adds a kind message that takes into consideration Mr. Tanaka's stress, and sends this to the device. The device receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended. He is an expert in reducing stress."

[0939] This allows Tanaka to be quickly and efficiently matched with the right medical provider and receive emotionally sensitive medical care.

[0940] The processing flow will be explained below.

[0941] Step 1:

[0942] The user enters health information into the terminal. The information includes name, age, medical history, current symptoms, etc. The user then presses the send button.

[0943] Step 2:

[0944] When the device transmits the user's health information, it collects the user's emotional indicators, including input speed, voice tone, and facial expression data (when using the camera).

[0945] Step 3:

[0946] The device sends the collected health information and emotional indicators to the server as an HTTP POST request.

[0947] Step 4:

[0948] The server receives the patient's health information and emotional indicators sent from the device, temporarily stores the received data, and verifies that the format is correct.

[0949] Step 5:

[0950] The server uses an emotion engine to analyze the emotion indicators and generate an emotion label for the user, which may include stress, satisfaction, relief, etc.

[0951] Step 6:

[0952] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[0953] Step 7:

[0954] The server combines the patient's health information with the emotion label and the list of healthcare providers to generate prompts for the generative AI, such as "Please select the most appropriate healthcare provider based on the patient's health information and emotion label."

[0955] Step 8:

[0956] The server calls OpenAI's API to send a prompt to the generating AI, authenticating using the API key.

[0957] Step 9:

[0958] The server receives the response from the generative AI, which includes the name and specialty of the recommended healthcare provider.

[0959] Step 10:

[0960] The server analyzes the generated AI's response and extracts information about the recommended healthcare provider.

[0961] Step 11:

[0962] The server generates customized notification content based on the recommended healthcare provider information and emotion labels, for example adding a message encouraging users to relax if they are feeling highly stressed.

[0963] Step 12:

[0964] The server returns the customized notification content to the device as an HTTP response.

[0965] Step 13:

[0966] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider.

[0967] Step 14:

[0968] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[0969] Example 2

[0970] 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."

[0971] Conventional patient-healthcare provider matching systems selected healthcare providers based solely on the patient's health information, making it difficult to select an appropriate healthcare provider that took the patient's emotional state into consideration. Furthermore, there was no way to collect and analyze emotional information, such as stress or anxiety, when the patient entered their information, making it difficult to select the healthcare provider best suited to the patient. This meant that patients were unable to receive appropriate healthcare services quickly and efficiently.

[0972] 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.

[0973] In this invention, the server includes a means for inputting a patient's health information and emotional information, a means for receiving the patient's health information and emotional information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, and a means for notifying the patient of a customized notification based on the healthcare provider information and emotional information selected by the generating AI means. This enables the selection of a healthcare provider that takes the patient's emotional state into consideration, enabling the patient to receive appropriate healthcare services quickly and efficiently.

[0974] "Patient health information" is data that indicates the patient's condition, including name, age, medical history, symptoms, etc.

[0975] "Emotional information" is data that indicates the emotional state of the patient, and includes information analyzed from voice, facial expression, and input speed.

[0976] The "input means" refers to a means by which a patient inputs health information and emotional information, and is a terminal such as a computer or smartphone.

[0977] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[0978] "Generative AI means" means means including artificial intelligence for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means.

[0979] "Notification means" means a means for notifying a patient of customized notification content based on the healthcare provider information and emotional information selected by the generation AI means.

[0980] "Server" means a central control unit that receives, processes, and stores data, selects healthcare providers using generative AI means, and notifies the results.

[0981] "Database" means a storage device for storing received patient health and emotional information and for maintaining available healthcare provider information.

[0982] "Prompts" are questions or instructions posed to the generative AI, which in this system are used to select a healthcare provider based on the patient's health and emotional information.

[0983] The "emotion engine" includes systems and algorithms for analyzing data such as voice, facial expressions, and input speed from the patient's input behavior and generating emotional information.

[0984] This invention is a system that utilizes generative AI and an emotion engine to efficiently match patients with healthcare providers. The system collects and analyzes patients' health and emotional information, and selects the most suitable healthcare provider based on this information.

[0985] System configuration

[0986] This system is composed of the following hardware and software: The hardware includes devices such as computers and smartphones. The software includes a web browser, mobile application, emotion engine, and generative AI (e.g., OpenAI API).

[0987] Specific processing flow

[0988] Entering patient health information

[0989] A user uses a device to enter their health information, for example, by entering their name, age, medical history, symptoms, etc. into a web form or mobile application, and then pressing a submit button. This entered health information is then sent to the system.

[0990] Recognition of emotional information

[0991] The device collects emotional indicators such as voice, facial expressions, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as "stress" and "anxiety."

[0992] Sending and receiving health and emotional information

[0993] The device sends the collected health information and emotion labels to the server via an HTTP POST request.

[0994] The server receives the data and stores it in a database. It also verifies that the received information is in the correct format.

[0995] Selection of healthcare provider

[0996] The server retrieves a list of available healthcare providers from a database, then generates a prompt containing the patient's health information and emotion label and sends it to a generative AI (e.g., OpenAI's API).

[0997] Acquisition and notification of recommended medical providers

[0998] The server receives the response from the AI ​​generator, extracts information about recommended healthcare providers, and generates customized notification content based on that information and the emotion label, which is then sent to the device as an HTTP response.

[0999] The device receives this response and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[1000] Specific examples

[1001] A 65-year-old user named Tanaka enters his health information using his smartphone. Tanaka enters his name "Taro Tanaka," his age "65," and his medical history of "risk of diabetes" into the input form, then presses the submit button. At this time, the device captures Tanaka's voice, facial expression, and input speed, and the emotion engine generates an emotion label such as "high stress." The device then sends this information to the server as an HTTP POST request.

[1002] The server receives the information and stores it in a database. It then sends the following prompt to the Generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional labels indicate high stress. Which healthcare provider is best?" The Generative AI responds, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[1003] Based on this answer, the server generates a response including information about Dr. Suzuki and a message that takes Mr. Tanaka into consideration, and sends it to the device. The device receives this and displays to Mr. Tanaka, "Dr. Suzuki is recommended. He is an expert in reducing stress." This allows Mr. Tanaka to be quickly and efficiently matched with an appropriate medical provider, and to receive medical services that are also considerate of his emotional state.

[1004] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1005] Step 1:

[1006] Users use the device to enter their health information: they open a web browser or mobile application, enter information such as their name, age, medical history, and symptoms, and then press the submit button.

[1007] Input: Name, age, medical history, symptoms, and other health information

[1008] Output: The entered health information is saved on the device.

[1009] Specific behavior:

[1010] A user opens a web browser or mobile application.

[1011] Enter your health information in the form provided.

[1012] Click the send button to send the information.

[1013] Step 2:

[1014] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as stress or anxiety.

[1015] Input: User voice, facial expressions, and typing speed

[1016] Output: Emotion labels generated by the emotion engine

[1017] Specific behavior:

[1018] The device's microphone and camera capture the user's voice and facial expressions.

[1019] Collect behavioral data such as typing speed.

[1020] The collected data is sent to the emotion engine for analysis.

[1021] The emotion engine generates emotion labels.

[1022] Step 3:

[1023] The device sends the collected health information and emotion labels to the server using an HTTP POST request.

[1024] Input: Health information, emotion labels

[1025] Output: Data sent to the server

[1026] Specific behavior:

[1027] The device makes an HTTP POST request containing the health information and emotion label.

[1028] Send this request to the server.

[1029] Step 4:

[1030] The server validates the received data and stores it in the database. It checks whether the received data is in the correct format.

[1031] Input: Health information sent from the device, emotion label

[1032] Output: Validated data stored in a database

[1033] Specific behavior:

[1034] The server receives an HTTP POST request.

[1035] Validate that the data is in the correct format.

[1036] The validated data is stored in the database.

[1037] Step 5:

[1038] The server retrieves a list of available healthcare providers from the database and generates a prompt to the generative AI means, which includes the patient's health information and an emotion label.

[1039] Input: Patient health information stored in a database, emotion labels

[1040] Output: Generated prompt

[1041] Specific behavior:

[1042] The server retrieves a list of available healthcare providers from a database.

[1043] Prompts are generated based on provider information, patient health information, and emotion labels.

[1044] Step 6:

[1045] The server sends a prompt to a generative AI tool (e.g., OpenAI's API), which contains the patient's health information and an emotion label.

[1046] Input: Generated prompt

[1047] Output: Recommendation results from the generative AI

[1048] Specific behavior:

[1049] The server sends the prompt to the API, which generates the AI.

[1050] Receive the generative AI means' response to the prompt.

[1051] Step 7:

[1052] The server analyzes the response from the generation AI and extracts information on recommended healthcare providers, which is then used to generate notifications for patients.

[1053] Input: Response from the generation AI

[1054] Output: Information and emotionally sensitive message for the notified healthcare provider

[1055] Specific behavior:

[1056] The server analyzes the response from the generated AI.

[1057] Extract recommended healthcare provider information.

[1058] Create notifications that are patient-friendly.

[1059] Step 8:

[1060] The server sends the customized notification content to the terminal as an HTTP response.

[1061] Input: Notification content

[1062] Output: Notification content sent to device

[1063] Specific behavior:

[1064] The server embeds the customized notification content in the HTTP response.

[1065] This HTTP response is sent to the terminal.

[1066] Step 9:

[1067] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[1068] Input: Notification content received from the server

[1069] Output: The notification that is displayed to the user

[1070] Specific behavior:

[1071] The device receives the HTTP response.

[1072] Display notification content in a user-friendly format.

[1073] (Application example 2)

[1074] 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."

[1075] In today's healthcare delivery environment, it remains difficult to quickly and effectively select the most appropriate healthcare provider for a patient. This can result in patients not receiving the medical care they need in a timely manner, leading to treatment delays and inappropriate medical responses. Furthermore, while providing emotionally sensitive healthcare has a significant impact on patient satisfaction and treatment outcomes, the current system does not adequately consider this important aspect. Furthermore, healthcare service scheduling and electronic payments are not centralized, resulting in increased hassle.

[1076] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1077] In this invention, the server includes an input means for inputting the patient's health information, an emotion engine means for the receiving means to collect and analyze emotional information along with the health information, a generation AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, a notification means, and a payment means. This allows the selection of the most appropriate healthcare provider based on the patient's health information and emotional information, and enables recommendation of healthcare services, reservations, and electronic payment that take emotions into consideration.

[1078] "Patient Health Information" refers to a set of data related to a patient's health status, such as the patient's name, age, medical history, and current symptoms.

[1079] "Input means" refers to the means by which patients input their health information, and includes devices such as computers and smartphones, web forms, and mobile applications.

[1080] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[1081] The "emotion engine means" is a means for analyzing emotion indicators such as voice, facial expression, and input speed collected together with the received health information of the patient, and generating emotion labels.

[1082] "Generative AI methods" refer to artificial intelligence models and algorithms that select the most appropriate healthcare provider based on a patient's health and emotional information.

[1083] "Notification means and payment means" refers to means for notifying patients of the information about the healthcare provider selected by the generating AI means, and for making reservations for healthcare services and making electronic payments.

[1084] "Database" refers to a digital storage system for storing patient health and emotional information and available healthcare provider information.

[1085] "Healthcare provider" refers to a doctor, nurse, specialist, or other health care professional who provides medical services, treatment, or diagnosis to a patient.

[1086] The system of the present invention has the function of collecting and analyzing a patient's health information and emotional information to efficiently match patients with healthcare providers, and recommending the most suitable healthcare provider. It also enables medical service reservations and electronic payments. The system includes an input means, a receiving means, an emotion engine means, a generation AI means, a notification means, and a payment means.

[1087] System configuration

[1088] Entering patient health information

[1089] Users enter their own health information using a device such as a smartphone, entering the patient's name, age, medical history, symptoms, and other health information into a mobile application on the device, and then pressing the send button.

[1090] Collecting and analyzing emotional information

[1091] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[1092] Sending and receiving health and emotional information

[1093] The device sends the entered health information and emotion label to the server as an HTTP POST request. The server receives the patient's health information and emotion label from the device and stores them in a database.

[1094] Selection of healthcare provider

[1095] The server retrieves a list of available healthcare providers from the database. The retrieved list includes the provider's name, specialty, availability, etc. The server generates a prompt for the generative AI model mentioned above. The prompt includes a question about the most suitable healthcare provider based on the patient's health information and emotion label and the list of available healthcare providers. An example of a specific prompt is, "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is the most suitable?"

[1096] Notification of recommendation information

[1097] The server receives the response from the generation AI and extracts information about the recommended healthcare provider. The server then generates a response based on the extracted information and sends it back to the device with a message that takes emotional information into consideration. For example, the message might read, "Dr. Suzuki is recommended. He is an expert in stress reduction."

[1098] Medical appointment booking and electronic payment

[1099] Users can select medical services based on recommendations from the server and make electronic payments directly within the application, making the system an efficient and emotionally sensitive way to book and pay for medical services easily and quickly.

[1100] Technology used

[1101] The hardware used is a computer terminal such as a smartphone or server, and the software used is a mobile application, Python, OpenAI's GPT-3 API, etc. Data is sent and received via HTTP and stored in a database.

[1102] As a concrete example of the entire system, when Tanaka uses the "MedPay" app to make a medical appointment, the prompt that appears is as follows:

[1103] "Taro Tanaka, 65, at risk for diabetes. Emotional label indicating high stress. Which healthcare provider is best?"

[1104] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1105] Step 1:

[1106] The user launches the mobile application on their smartphone and enters their health information. Here, the user enters their name, age, medical history, symptoms, etc. into the input form and presses the submit button. The input data is packaged in JSON format. The entered data is temporarily stored on the device and prepared for transmission.

[1107] Step 2:

[1108] The device collects emotional information at the same time as the health information is entered. Emotional information is an indicator of the stress or anxiety the user felt while entering data, and is acquired using the device's camera and microphone. Input speed and touch patterns are also analyzed. This data is analyzed by the emotion engine and generated as an emotional label. The analyzed emotional label is then generated in JSON format.

[1109] Step 3:

[1110] The device sends the health information and analyzed emotion label to the server using an HTTP POST request, with the data sent in JSON format. The data includes the following items: "Name," "Age," "Symptoms," and "Emotion Label."

[1111] Step 4:

[1112] The server receives the health information and emotion labels received from the device and stores them in a database that also contains a list of existing healthcare providers and their availability information, and verifies the received data for correct formatting.

[1113] Step 5:

[1114] The server retrieves a list of available providers from a database, including the provider's name, specialty, available hours, etc. The retrieved data is stored in an internal memory.

[1115] Step 6:

[1116] The server generates a prompt for the generative AI model. The prompt includes the patient's health information and emotion label received, as well as the list of healthcare providers obtained. A specific prompt sentence might be generated like this: "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is best?" The prompt sentence is in text format.

[1117] Step 7:

[1118] The server sends a prompt to a generative AI model (e.g., OpenAI's GPT-3) using an API request, with the data sent in plain text format. The API key is used to authenticate the request.

[1119] Step 8:

[1120] The server receives a response from the generative AI model, including the name and specialty of the healthcare provider that the generative AI model finds most suitable. This data is also returned in text format.

[1121] Step 9:

[1122] The server analyzes the response from the generative AI model and extracts information about the recommended healthcare provider. The extracted information is then converted back to JSON format and a response message is generated to be displayed to the user. The message also includes emotionally sensitive content.

[1123] Step 10:

[1124] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider. The user can then select the recommended healthcare provider based on this information.

[1125] Step 11:

[1126] The user selects a recommended medical provider and makes a medical appointment. Once the appointment details are confirmed, the appointment information is sent back to the server from the terminal.

[1127] Step 12:

[1128] The server processes the electronic payment based on the received reservation information. A payment gateway service is used to process the payment, and payment is made using credit card information or an online payment account. The payment success or failure status is returned to the terminal and displayed to the user.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] [Fourth embodiment]

[1133] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1134] 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.

[1135] 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).

[1136] 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.

[1137] 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.

[1138] 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).

[1139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] 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.

[1145] 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."

[1146] The system of the present invention utilizes generative AI to efficiently match patients with healthcare providers. The system collects and analyzes the patient's health information and selects the most appropriate healthcare provider based on that information.

[1147] System configuration

[1148] Entering patient health information

[1149] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application provided on the device, and then press the submit button.

[1150] Sending and Receiving Health Information

[1151] The device sends the entered health information to the server, which sends the information as an HTTP POST request.

[1152] The server receives the patient's health information sent from the terminal and stores it in a database. After receiving the data, the server verifies that each element of the data is accurate.

[1153] Selection of healthcare provider

[1154] The server retrieves a list of available healthcare providers from a database, generates a prompt to select the most suitable healthcare provider for the patient, sends the generated prompt to the generation AI (OpenAI's GPT-based model), and receives a response from the AI ​​model.

[1155] The generative AI analyzes the prompts and responds with a text recommending the most suitable healthcare provider for the patient, including the provider's name and specialty.

[1156] Healthcare provider notification

[1157] The server analyzes the AI's response, extracts information about the healthcare provider recommended by the AI, and generates a response containing details of the selected healthcare provider based on that information and sends it back to the device.

[1158] The terminal receives the response from the server and displays to the user information about healthcare providers who recommend vaccinations.

[1159] Specific examples

[1160] For example, a user named Tanaka uses a terminal to input his / her health information. Tanaka writes his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and presses the send button. The terminal then sends the health information to the server.

[1161] Based on the received information, the server sends a prompt to the generating AI: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generating AI analyzes the list of available healthcare providers and returns the answer that "Dr. Suzuki (Internal Medicine)" is best.

[1162] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable healthcare provider for Mr. Tanaka, and sends it to the terminal. The terminal receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended."

[1163] This process ensures that Tanaka is quickly and efficiently matched with the appropriate healthcare provider and receives the medical services he needs.

[1164] The processing flow will be explained below.

[1165] Step 1:

[1166] The user enters health information into the terminal. The entered information includes name, age, medical history, symptoms, etc. The user presses the send button.

[1167] Step 2:

[1168] The device sends the health information entered by the user to the server as an HTTP POST request.

[1169] Step 3:

[1170] The server receives the patient's health information from the terminal and stores it in a database. It also verifies that the format of the received data is correct.

[1171] Step 4:

[1172] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[1173] Step 5:

[1174] The server generates a prompt for the AI, which includes the patient's health information and a list of available providers, in the format "Which provider is best?"

[1175] Step 6:

[1176] The server calls the OpenAI API and sends a prompt to the generated AI, authenticating the request with an API key.

[1177] Step 7:

[1178] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[1179] Step 8:

[1180] The server analyzes the AI's response, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[1181] Step 9:

[1182] The server returns the recommended healthcare provider information to the device as an HTTP response.

[1183] Step 10:

[1184] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider.

[1185] Step 11:

[1186] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[1187] Example 1

[1188] 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."

[1189] Conventional patient-healthcare provider matching systems have difficulty efficiently selecting the most appropriate healthcare provider based on the patient's detailed health information. Another problem is that it takes a lot of time and effort for patients to find the appropriate healthcare provider. Furthermore, there is a lack of a way to accurately and quickly convey patient information to healthcare providers.

[1190] 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.

[1191] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for storing the patient health information received by the receiving means in a database and selecting a healthcare provider based on the data, and a notifying means for notifying the patient of the healthcare provider selected by the generating AI means. This makes it possible to efficiently and accurately select the most appropriate healthcare provider based on the patient's health information and quickly notify the information.

[1192] "Patient health information" refers to information that indicates the patient's health condition, such as the patient's name, age, medical history, and symptoms.

[1193] "Input means" refers to the means used by patients to enter their health information, specifically a web form on a computer or smartphone or a mobile application.

[1194] The "receiving means" is a means for receiving the patient's health information transmitted from the input means, and the server is mainly responsible for this role.

[1195] "Database" means an electronic record system for storing patient health information and healthcare provider information.

[1196] "Generative AI method" refers to an artificial intelligence model used to select the most appropriate healthcare provider based on a patient's health information and a list of healthcare providers.

[1197] "Notification means" refers to a means for conveying information about the healthcare provider selected by the generation AI means to the patient, and primarily refers to an electronic message sent from the server to the terminal.

[1198] A "prompt" is text data to be input into the generative AI, and includes questions about the patient's health information and required medical services.

[1199] A "Response" is a reply message from the Generating AI that includes detailed information about a recommended healthcare provider.

[1200] The system of the present invention utilizes generative AI models to efficiently match patients with healthcare providers. The system collects and analyzes patient health information and then selects the most appropriate healthcare provider based on that information.

[1201] Entering and submitting health information

[1202] To enter their health information, users use devices such as computers or smartphones. They access a web form or mobile application on their device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses a submit button to send the information to the server. When the submit button is pressed, the device sends the data via an HTTP POST request.

[1203] Receiving and storing health information

[1204] The server receives the HTTP POST request sent from the device, analyzes the request, and stores the submitted patient health information in a database, performing checks to verify the accuracy of the data.

[1205] Selection of healthcare provider

[1206] The server retrieves a list of available healthcare providers from a database. This list includes information such as the provider's name, specialty, and location. Based on the patient's health information and the list of healthcare providers, the server generates a prompt for the generative AI model. For example, the server creates a prompt such as, "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The generated prompt is then sent to the generative AI (e.g., OpenAI's GPT-based model).

[1207] Receiving a response from the AI

[1208] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[1209] Notification of recommendation information

[1210] The server analyzes the response from the AI ​​generator and extracts details of the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The device receives this response and displays the information to the user.

[1211] Specific examples

[1212] For example, a user, Mr. Takahashi, uses a terminal to input his health information. Mr. Takahashi writes "Ichiro Takahashi, 70 years old, at risk of high blood pressure" in the input form and presses the send button. The terminal then sends the health information to the server.

[1213] Based on the received information, the server sends the following prompt to the Generative AI: "Ichiro Takahashi, 70 years old, at risk of high blood pressure. Which healthcare provider is best?" The Generative AI analyzes the list of available healthcare providers and returns the answer that "Dr. Sato (cardiologist)" is best.

[1214] Based on this answer, the server generates a response containing information about Dr. Sato, the most suitable medical provider for Mr. Takahashi, and sends it to the terminal. The terminal receives this response and displays it to Mr. Takahashi, saying, "Dr. Sato is recommended."

[1215] This process ensures that Takahashi is quickly and efficiently matched with the appropriate medical provider and receives the medical services he needs.

[1216] Through the above steps, the system of the present invention is able to select the most suitable healthcare provider based on the patient's health information and notify the patient promptly and accurately.

[1217] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1218] Step 1: Enter patient health information

[1219] Users use devices such as computers or smartphones to enter their health information. They access a web form or mobile application on the device and enter information such as their name, age, medical history, and symptoms. Once the information is complete, the user presses the send button, which prepares the input data for transmission to the device.

[1220] Step 2: Submit your health information

[1221] The device sends the health information entered by the user to the server as an HTTP POST request. The input at this point is the user's health information (name, age, medical history, symptoms), and the output is an HTTP request sent to the server. After sending, the device notifies the user that "Sending has been completed."

[1222] Step 3: Receiving and storing health information

[1223] The server receives the HTTP POST request sent from the device. The server analyzes the request, extracts the submitted patient health information, and stores it in a database. In this process, the input is the HTTP request, and the output is the patient health information stored in the database. The server also performs checks to verify the accuracy of the data.

[1224] Step 4: Get a list of healthcare providers

[1225] The server retrieves a list of available providers from a database, which includes information such as provider name, specialty, location, etc. The input is a query to the database, and the output is a list of providers.

[1226] Step 5: Generate and send the prompt

[1227] The server generates a prompt to send to the generative AI model based on the user's health information and list of healthcare providers. For example, it creates a prompt with the following content: "Taro Tanaka, 65 years old, at risk of diabetes. Which healthcare provider is best?" The input is the patient's health information and list of healthcare providers, and the output is the generated prompt text. The generated prompt is sent to the generative AI (e.g., OpenAI's GPT-based model).

[1228] Step 6: Receive a response from the AI

[1229] The server receives a response from the generation AI. The response includes the name and specialty of the recommended healthcare provider. The input is the response from the generation AI, and the output is information about the recommended healthcare provider. For example, information such as "Dr. Suzuki (Internal Medicine)" is returned.

[1230] Step 7: Parse the response and generate recommendations

[1231] The server analyzes the response received from the generation AI and extracts detailed information about the recommended healthcare provider. It then generates a response to notify the patient. For example, it creates a response that reads, "Dr. Suzuki is recommended." The input is the response from the generation AI, and the output is a message to notify the patient.

[1232] Step 8: Submit and view your recommendations

[1233] The server sends the generated response to the terminal. The terminal analyzes the received response and displays detailed information about the recommended healthcare provider to the user. The input is the response from the server, and the output is the information displayed to the user (e.g., "Dr. Suzuki is recommended").

[1234] Through this series of processes, users are quickly and efficiently matched with appropriate medical providers, enabling them to receive medical services efficiently.

[1235] (Application example 1)

[1236] 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."

[1237] Conventional healthcare provider and patient matching systems have the problem that patients must manually enter their health information and it takes time to select an appropriate healthcare provider. It can also be difficult for patients to accurately enter their medical conditions and symptoms, which can lead to the wrong healthcare provider being recommended. This system is required to allow patients to easily enter their health information and quickly and accurately recommend the most appropriate healthcare provider.

[1238] 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.

[1239] In this invention, the server includes an input means for inputting patient health information, a receiving means for receiving the patient health information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information received by the receiving means, a notification means for notifying the patient of the healthcare provider selected by the generating AI means, an input means for inputting the patient's health information in real time using a smart device, and a transmission means for acquiring and transmitting the health information by voice input or code scanning. This allows the patient to easily and quickly input their health information using a smart device, and enables the generating AI to quickly and accurately recommend the most suitable healthcare provider.

[1240] "Patient health information" refers to general information about the patient's health condition, such as the patient's name, age, medical history, current symptoms, allergy information, and medications currently being taken.

[1241] "Input means" refers to devices or interfaces through which patients input their health information, including smartphones, tablets, smart glasses, etc.

[1242] The "receiving means" refers to a server or a communication interface for receiving the patient's health information transmitted from the input means.

[1243] "Generative AI means" refers to the artificial intelligence model used to select healthcare providers based on received patient health information, specifically a generative AI model (e.g., a GPT-based model).

[1244] "Notification means" refers to a communication interface or display device used to notify patients of the information about the healthcare provider selected by the generation AI means.

[1245] "Smart devices" refer to electronic devices that are equipped with voice input, camera functions, displays, etc. and can collect and display patient health information, and specifically include smart glasses, smartphones, tablets, etc.

[1246] The "transmission means" refers to a function for transmitting patient health information acquired from a smart device to a server, specifically a data transmission means via an internet connection.

[1247] The present invention is a system for efficiently matching patients with healthcare providers, and in particular, it relates to the collection of real-time health information using smart devices and the selection of the most suitable healthcare provider using AI generation. The system is configured as follows:

[1248] Hardware and Software Use

[1249] 1. Hardware:

[1250] Smart devices (e.g., smart glasses, smartphones)

[1251] Voice input function

[1252] Camera features

[1253] Display Features

[1254] server:

[1255] Data Processing Server

[1256] Hospital Information System

[1257] Database server (storing patient and provider information)

[1258] 2. Software:

[1259] Data transmission API (e.g., using an HTTP POST request)

[1260] Server-side systems (e.g. web frameworks such as Flask and Django)

[1261] Generative AI models (e.g., OpenAI's GPT-based models)

[1262] Database management systems (e.g., MySQL, PostgreSQL)

[1263] Detailed System Description

[1264] Entering patient health information

[1265] Users input their health information using their smart devices. When using smart glasses, health information can be obtained using voice input or QR code scanning with the camera, and the information can be sent directly to the system. For example, users can input information such as "I have a headache" or "I have a history of high blood pressure" using voice input.

[1266] Sending and Receiving Health Information

[1267] The device sends the entered health information to the server via a data transmission API. The sent data reaches the server through a protocol (e.g., HTTP POST request) and is stored in a database.

[1268] Selection of healthcare provider

[1269] The server generates prompts based on the received patient health information and sends them to the generative AI model, which then selects the most appropriate healthcare provider based on the prompts shown below.

[1270] For example: "Taro Tanaka, 65 years old, at risk for diabetes. Which healthcare provider is best?"

[1271] The generative AI model analyzes the prompt and selects the most appropriate healthcare provider based on information about multiple healthcare providers retrieved from a database. For example, it may recommend an "internal medicine specialist."

[1272] Healthcare provider notification

[1273] The server analyzes the information on healthcare providers obtained from the generative AI model and notifies the patient of the results. The device receives the response from the server and displays details of the recommended healthcare provider to the patient. For example, the smart glasses display may show information such as "An internal medicine specialist is recommended."

[1274] This system allows patients to easily and quickly enter their health information using smart devices, and uses generative AI to quickly and accurately recommend the most suitable healthcare provider.

[1275] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1276] Step 1:

[1277] Users use smart devices to input their own health information. Specifically, they may use the voice input function to input information such as "I have a headache" or "I have a history of high blood pressure," or they may use the camera function of smart glasses to scan QR codes to obtain information about medications. These pieces of information are treated as input.

[1278] Step 2:

[1279] The device sends the collected health information to the server using a data transmission API. The data is packaged in JSON format and sent to the server via an HTTP POST request. The server receives this health information and stores it in a database. The input at this stage is the health information, and the output is storing it in the database and confirming receipt on the server side.

[1280] Step 3:

[1281] The server generates a prompt to be sent to the generative AI model based on the patient's health information stored in the database. Specifically, it creates a prompt in the format "Taro Tanaka, 65 years old, at risk of diabetes. Who is the best healthcare provider?" This prompt is sent to the generative AI model. The input is the health information, and the output is the generated prompt.

[1282] Step 4:

[1283] The generative AI model analyzes the sent prompt and selects the most suitable healthcare provider based on information on multiple healthcare providers retrieved from a database. Based on the prompt, the generative AI uses internal learning data and logic to output the name and specialty of the most suitable healthcare provider. The input at this stage is the prompt, and the output is the selection result of the most suitable healthcare provider.

[1284] Step 5:

[1285] The server receives the response from the generative AI model and processes the information of the healthcare provider selected by the generative AI. Specifically, it analyzes the healthcare provider's name, specialty, contact information, etc., and generates a message to notify the patient. The input at this stage is the response from the generative AI model, and the output is the notification message.

[1286] Step 6:

[1287] The terminal receives the notification message from the server and displays the details of the recommended healthcare provider to the patient. In the case of smart glasses, the display will show "An internal medicine specialist is recommended." The patient can check this information through the smart glasses and contact the healthcare provider. The input at this stage is the notification message, and the output is the display to the patient.

[1288] 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.

[1289] The system of the present invention utilizes generative AI and an emotion engine to efficiently match patients and healthcare providers. The system collects and analyzes the patient's health and emotion information, and then selects the most appropriate healthcare provider based on that information.

[1290] System configuration

[1291] Entering patient health information

[1292] To enter their own health information, users use devices such as computers or smartphones. They enter health information such as the patient's name, age, medical history, and symptoms into a web form or mobile application on the device and press the submit button.

[1293] Recognition of emotional information

[1294] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[1295] Sending and receiving health and emotional information

[1296] The device sends the entered health information and emotion label to the server as an HTTP POST request.

[1297] The server receives the patient's health information and emotion label from the device, stores them in a database, and verifies that the format of the received data is correct.

[1298] Selection of healthcare provider

[1299] The server retrieves a list of available providers from the database, including the provider's name, specialty, availability, etc.

[1300] The server generates a prompt for the generative AI, which includes the patient's health information, an emotional label, and a list of available healthcare providers, in the form of "Which healthcare provider is best?"

[1301] The server calls OpenAI's API and sends a prompt to the generating AI, authenticating the request with an API key.

[1302] The server receives a response from the AI ​​generator, which includes the name and specialty of the recommended healthcare provider in text format.

[1303] Healthcare provider notification

[1304] The server analyzes the response of the generation AI, extracts information about recommended healthcare providers, and generates a response based on the extracted information.

[1305] The server then returns customized notification content based on the recommended healthcare provider information and emotion label to the device as an HTTP response.

[1306] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[1307] Specific examples

[1308] For example, a user named Tanaka uses a device to input his / her health information. Tanaka enters his / her name, age 65, and medical history indicating that he / she is at risk of diabetes in the input form, and then presses the send button. The device sends the health information to the server along with an emotional label indicating the level of stress Tanaka felt while entering the information.

[1309] Based on the received information, the server sends the following prompt to the generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional label indicating high stress. Which healthcare provider is best?" The generative AI analyzes the list of available healthcare providers and replies, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[1310] Based on this answer, the server generates a response including information about Dr. Suzuki, the most suitable medical provider for Mr. Tanaka, and adds a kind message that takes into consideration Mr. Tanaka's stress, and sends this to the device. The device receives this response and displays it to Mr. Tanaka in the form of "Dr. Suzuki is recommended. He is an expert in reducing stress."

[1311] This allows Tanaka to be quickly and efficiently matched with the right medical provider and receive emotionally sensitive medical care.

[1312] The processing flow will be explained below.

[1313] Step 1:

[1314] The user enters health information into the terminal. The information includes name, age, medical history, current symptoms, etc. The user then presses the send button.

[1315] Step 2:

[1316] When the device transmits the user's health information, it collects the user's emotional indicators, including input speed, voice tone, and facial expression data (when using the camera).

[1317] Step 3:

[1318] The device sends the collected health information and emotional indicators to the server as an HTTP POST request.

[1319] Step 4:

[1320] The server receives the patient's health information and emotional indicators sent from the device, temporarily stores the received data, and verifies that the format is correct.

[1321] Step 5:

[1322] The server uses an emotion engine to analyze the emotion indicators and generate an emotion label for the user, which may include stress, satisfaction, relief, etc.

[1323] Step 6:

[1324] The server retrieves a list of available providers from a database, including the provider's name, specialty, availability, etc.

[1325] Step 7:

[1326] The server combines the patient's health information with the emotion label and the list of healthcare providers to generate prompts for the generative AI, such as "Please select the most appropriate healthcare provider based on the patient's health information and emotion label."

[1327] Step 8:

[1328] The server calls OpenAI's API to send a prompt to the generating AI, authenticating using the API key.

[1329] Step 9:

[1330] The server receives the response from the generative AI, which includes the name and specialty of the recommended healthcare provider.

[1331] Step 10:

[1332] The server analyzes the generated AI's response and extracts information about the recommended healthcare provider.

[1333] Step 11:

[1334] The server generates customized notification content based on the recommended healthcare provider information and emotion labels, for example adding a message encouraging users to relax if they are feeling highly stressed.

[1335] Step 12:

[1336] The server returns the customized notification content to the device as an HTTP response.

[1337] Step 13:

[1338] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider.

[1339] Step 14:

[1340] The user reviews the displayed information and either contacts a recommended healthcare provider or selects an appropriate action.

[1341] Example 2

[1342] 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."

[1343] Conventional patient-healthcare provider matching systems selected healthcare providers based solely on the patient's health information, making it difficult to select an appropriate healthcare provider that took the patient's emotional state into consideration. Furthermore, there was no way to collect and analyze emotional information, such as stress or anxiety, when the patient entered their information, making it difficult to select the healthcare provider best suited to the patient. This meant that patients were unable to receive appropriate healthcare services quickly and efficiently.

[1344] 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.

[1345] In this invention, the server includes a means for inputting a patient's health information and emotional information, a means for receiving the patient's health information and emotional information transmitted from the input means, a generating AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, and a means for notifying the patient of a customized notification based on the healthcare provider information and emotional information selected by the generating AI means. This enables the selection of a healthcare provider that takes the patient's emotional state into consideration, enabling the patient to receive appropriate healthcare services quickly and efficiently.

[1346] "Patient health information" is data that indicates the patient's condition, including name, age, medical history, symptoms, etc.

[1347] "Emotional information" is data that indicates the emotional state of the patient, and includes information analyzed from voice, facial expression, and input speed.

[1348] The "input means" refers to a means by which a patient inputs health information and emotional information, and is a terminal such as a computer or smartphone.

[1349] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[1350] "Generative AI means" means means including artificial intelligence for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means.

[1351] "Notification means" means a means for notifying a patient of customized notification content based on the healthcare provider information and emotional information selected by the generation AI means.

[1352] "Server" means a central control unit that receives, processes, and stores data, selects healthcare providers using generative AI means, and notifies the results.

[1353] "Database" means a storage device for storing received patient health and emotional information and for maintaining available healthcare provider information.

[1354] "Prompts" are questions or instructions posed to the generative AI, which in this system are used to select a healthcare provider based on the patient's health and emotional information.

[1355] The "emotion engine" includes systems and algorithms for analyzing data such as voice, facial expressions, and input speed from the patient's input behavior and generating emotional information.

[1356] This invention is a system that utilizes generative AI and an emotion engine to efficiently match patients with healthcare providers. The system collects and analyzes patients' health and emotional information, and selects the most suitable healthcare provider based on this information.

[1357] System configuration

[1358] This system is composed of the following hardware and software: The hardware includes devices such as computers and smartphones. The software includes a web browser, mobile application, emotion engine, and generative AI (e.g., OpenAI API).

[1359] Specific processing flow

[1360] Entering patient health information

[1361] A user uses a device to enter their health information, for example, by entering their name, age, medical history, symptoms, etc. into a web form or mobile application, and then pressing a submit button. This entered health information is then sent to the system.

[1362] Recognition of emotional information

[1363] The device collects emotional indicators such as voice, facial expressions, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as "stress" and "anxiety."

[1364] Sending and receiving health and emotional information

[1365] The device sends the collected health information and emotion labels to the server via an HTTP POST request.

[1366] The server receives the data and stores it in a database. It also verifies that the received information is in the correct format.

[1367] Selection of healthcare provider

[1368] The server retrieves a list of available healthcare providers from a database, then generates a prompt containing the patient's health information and emotion label and sends it to a generative AI (e.g., OpenAI's API).

[1369] Acquisition and notification of recommended medical providers

[1370] The server receives the response from the AI ​​generator, extracts information about recommended healthcare providers, and generates customized notification content based on that information and the emotion label, which is then sent to the device as an HTTP response.

[1371] The device receives this response and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[1372] Specific examples

[1373] A 65-year-old user named Tanaka enters his health information using his smartphone. Tanaka enters his name "Taro Tanaka," his age "65," and his medical history of "risk of diabetes" into the input form, then presses the submit button. At this time, the device captures Tanaka's voice, facial expression, and input speed, and the emotion engine generates an emotion label such as "high stress." The device then sends this information to the server as an HTTP POST request.

[1374] The server receives the information and stores it in a database. It then sends the following prompt to the Generative AI: "Taro Tanaka, 65 years old, at risk of diabetes. Emotional labels indicate high stress. Which healthcare provider is best?" The Generative AI responds, "Dr. Suzuki (internal medicine) is best because he is good at managing stress."

[1375] Based on this answer, the server generates a response including information about Dr. Suzuki and a message that takes Mr. Tanaka into consideration, and sends it to the device. The device receives this and displays to Mr. Tanaka, "Dr. Suzuki is recommended. He is an expert in reducing stress." This allows Mr. Tanaka to be quickly and efficiently matched with an appropriate medical provider, and to receive medical services that are also considerate of his emotional state.

[1376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1377] Step 1:

[1378] Users use the device to enter their health information: they open a web browser or mobile application, enter information such as their name, age, medical history, and symptoms, and then press the submit button.

[1379] Input: Name, age, medical history, symptoms, and other health information

[1380] Output: The entered health information is saved on the device.

[1381] Specific behavior:

[1382] A user opens a web browser or mobile application.

[1383] Enter your health information in the form provided.

[1384] Click the send button to send the information.

[1385] Step 2:

[1386] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. This data is analyzed by an emotion engine to generate emotional labels such as stress or anxiety.

[1387] Input: User voice, facial expressions, and typing speed

[1388] Output: Emotion labels generated by the emotion engine

[1389] Specific behavior:

[1390] The device's microphone and camera capture the user's voice and facial expressions.

[1391] Collect behavioral data such as typing speed.

[1392] The collected data is sent to the emotion engine for analysis.

[1393] The emotion engine generates emotion labels.

[1394] Step 3:

[1395] The device sends the collected health information and emotion labels to the server using an HTTP POST request.

[1396] Input: Health information, emotion labels

[1397] Output: Data sent to the server

[1398] Specific behavior:

[1399] The device makes an HTTP POST request containing the health information and emotion label.

[1400] Send this request to the server.

[1401] Step 4:

[1402] The server validates the received data and stores it in the database. It checks whether the received data is in the correct format.

[1403] Input: Health information sent from the device, emotion label

[1404] Output: Validated data stored in a database

[1405] Specific behavior:

[1406] The server receives an HTTP POST request.

[1407] Validate that the data is in the correct format.

[1408] The validated data is stored in the database.

[1409] Step 5:

[1410] The server retrieves a list of available healthcare providers from the database and generates a prompt to the generative AI means, which includes the patient's health information and an emotion label.

[1411] Input: Patient health information stored in a database, emotion labels

[1412] Output: Generated prompt

[1413] Specific behavior:

[1414] The server retrieves a list of available healthcare providers from a database.

[1415] Prompts are generated based on provider information, patient health information, and emotion labels.

[1416] Step 6:

[1417] The server sends a prompt to a generative AI tool (e.g., OpenAI's API), which contains the patient's health information and an emotion label.

[1418] Input: Generated prompt

[1419] Output: Recommendation results from the generative AI

[1420] Specific behavior:

[1421] The server sends the prompt to the API, which generates the AI.

[1422] Receive the generative AI means' response to the prompt.

[1423] Step 7:

[1424] The server analyzes the response from the generation AI and extracts information on recommended healthcare providers, which is then used to generate notifications for patients.

[1425] Input: Response from the generation AI

[1426] Output: Information and emotionally sensitive message for the notified healthcare provider

[1427] Specific behavior:

[1428] The server analyzes the response from the generated AI.

[1429] Extract recommended healthcare provider information.

[1430] Create notifications that are patient-friendly.

[1431] Step 8:

[1432] The server sends the customized notification content to the terminal as an HTTP response.

[1433] Input: Notification content

[1434] Output: Notification content sent to device

[1435] Specific behavior:

[1436] The server embeds the customized notification content in the HTTP response.

[1437] This HTTP response is sent to the terminal.

[1438] Step 9:

[1439] The device receives the response from the server and displays it to the user, including the name and specialty of the recommended healthcare provider and a sensitive message.

[1440] Input: Notification content received from the server

[1441] Output: The notification that is displayed to the user

[1442] Specific behavior:

[1443] The device receives the HTTP response.

[1444] Display notification content in a user-friendly format.

[1445] (Application example 2)

[1446] 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."

[1447] In today's healthcare delivery environment, it remains difficult to quickly and effectively select the most appropriate healthcare provider for a patient. This can result in patients not receiving the medical care they need in a timely manner, leading to treatment delays and inappropriate medical responses. Furthermore, while providing emotionally sensitive healthcare has a significant impact on patient satisfaction and treatment outcomes, the current system does not adequately consider this important aspect. Furthermore, healthcare service scheduling and electronic payments are not centralized, resulting in increased hassle.

[1448] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1449] In this invention, the server includes an input means for inputting the patient's health information, an emotion engine means for the receiving means to collect and analyze emotional information along with the health information, a generation AI means for selecting a healthcare provider based on the patient's health information and emotional information received by the receiving means, a notification means, and a payment means. This allows the selection of the most appropriate healthcare provider based on the patient's health information and emotional information, and enables recommendation of healthcare services, reservations, and electronic payment that take emotions into consideration.

[1450] "Patient Health Information" refers to a set of data related to a patient's health status, such as the patient's name, age, medical history, and current symptoms.

[1451] "Input means" refers to the means by which patients input their health information, and includes devices such as computers and smartphones, web forms, and mobile applications.

[1452] The "receiving means" is a means for receiving the patient's health information and emotional information transmitted from the input means.

[1453] The "emotion engine means" is a means for analyzing emotion indicators such as voice, facial expression, and input speed collected together with the received health information of the patient, and generating emotion labels.

[1454] "Generative AI methods" refer to artificial intelligence models and algorithms that select the most appropriate healthcare provider based on a patient's health and emotional information.

[1455] "Notification means and payment means" refers to means for notifying patients of the information about the healthcare provider selected by the generating AI means, and for making reservations for healthcare services and making electronic payments.

[1456] "Database" refers to a digital storage system for storing patient health and emotional information and available healthcare provider information.

[1457] "Healthcare provider" refers to a doctor, nurse, specialist, or other health care professional who provides medical services, treatment, or diagnosis to a patient.

[1458] The system of the present invention has the function of collecting and analyzing a patient's health information and emotional information to efficiently match patients with healthcare providers, and recommending the most suitable healthcare provider. It also enables medical service reservations and electronic payments. The system includes an input means, a receiving means, an emotion engine means, a generation AI means, a notification means, and a payment means.

[1459] System configuration

[1460] Entering patient health information

[1461] Users enter their own health information using a device such as a smartphone, entering the patient's name, age, medical history, symptoms, and other health information into a mobile application on the device, and then pressing the send button.

[1462] Collecting and analyzing emotional information

[1463] The device collects emotional indicators such as voice, facial expression, and input speed when the user enters health information. These emotional indicators are analyzed by an emotion engine to generate emotional labels.

[1464] Sending and receiving health and emotional information

[1465] The device sends the entered health information and emotion label to the server as an HTTP POST request. The server receives the patient's health information and emotion label from the device and stores them in a database.

[1466] Selection of healthcare provider

[1467] The server retrieves a list of available healthcare providers from the database. The retrieved list includes the provider's name, specialty, availability, etc. The server generates a prompt for the generative AI model mentioned above. The prompt includes a question about the most suitable healthcare provider based on the patient's health information and emotion label and the list of available healthcare providers. An example of a specific prompt is, "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is the most suitable?"

[1468] Notification of recommendation information

[1469] The server receives the response from the generation AI and extracts information about the recommended healthcare provider. The server then generates a response based on the extracted information and sends it back to the device with a message that takes emotional information into consideration. For example, the message might read, "Dr. Suzuki is recommended. He is an expert in stress reduction."

[1470] Medical appointment booking and electronic payment

[1471] Users can select medical services based on recommendations from the server and make electronic payments directly within the application, making the system an efficient and emotionally sensitive way to book and pay for medical services easily and quickly.

[1472] Technology used

[1473] The hardware used is a computer terminal such as a smartphone or server, and the software used is a mobile application, Python, OpenAI's GPT-3 API, etc. Data is sent and received via HTTP and stored in a database.

[1474] As a concrete example of the entire system, when Tanaka uses the "MedPay" app to make a medical appointment, the prompt that appears is as follows:

[1475] "Taro Tanaka, 65, at risk for diabetes. Emotional label indicating high stress. Which healthcare provider is best?"

[1476] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1477] Step 1:

[1478] The user launches the mobile application on their smartphone and enters their health information. Here, the user enters their name, age, medical history, symptoms, etc. into the input form and presses the submit button. The input data is packaged in JSON format. The entered data is temporarily stored on the device and prepared for transmission.

[1479] Step 2:

[1480] The device collects emotional information at the same time as the health information is entered. Emotional information is an indicator of the stress or anxiety the user felt while entering data, and is acquired using the device's camera and microphone. Input speed and touch patterns are also analyzed. This data is analyzed by the emotion engine and generated as an emotional label. The analyzed emotional label is then generated in JSON format.

[1481] Step 3:

[1482] The device sends the health information and analyzed emotion label to the server using an HTTP POST request, with the data sent in JSON format. The data includes the following items: "Name," "Age," "Symptoms," and "Emotion Label."

[1483] Step 4:

[1484] The server receives the health information and emotion labels received from the device and stores them in a database that also contains a list of existing healthcare providers and their availability information, and verifies the received data for correct formatting.

[1485] Step 5:

[1486] The server retrieves a list of available providers from a database, including the provider's name, specialty, available hours, etc. The retrieved data is stored in an internal memory.

[1487] Step 6:

[1488] The server generates a prompt for the generative AI model. The prompt includes the patient's health information and emotion label received, as well as the list of healthcare providers obtained. A specific prompt sentence might be generated like this: "Taro Tanaka, 65 years old, at risk of diabetes. Emotion label indicates high stress. Which healthcare provider is best?" The prompt sentence is in text format.

[1489] Step 7:

[1490] The server sends a prompt to a generative AI model (e.g., OpenAI's GPT-3) using an API request, with the data sent in plain text format. The API key is used to authenticate the request.

[1491] Step 8:

[1492] The server receives a response from the generative AI model, including the name and specialty of the healthcare provider that the generative AI model finds most suitable. This data is also returned in text format.

[1493] Step 9:

[1494] The server analyzes the response from the generative AI model and extracts information about the recommended healthcare provider. The extracted information is then converted back to JSON format and a response message is generated to be displayed to the user. The message also includes emotionally sensitive content.

[1495] Step 10:

[1496] The device receives the response from the server and displays it to the user, including the name, specialty, and emotionally sensitive message of the recommended healthcare provider. The user can then select the recommended healthcare provider based on this information.

[1497] Step 11:

[1498] The user selects a recommended medical provider and makes a medical appointment. Once the appointment details are confirmed, the appointment information is sent back to the server from the terminal.

[1499] Step 12:

[1500] The server processes the electronic payment based on the received reservation information. A payment gateway service is used to process the payment, and payment is made using credit card information or an online payment account. The payment success or failure status is returned to the terminal and displayed to the user.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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).

[1508] 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.

[1509] 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."

[1510] 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.

[1511] 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).

[1512] 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.

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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.

[1520] 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.

[1521] 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.

[1522] The following is further disclosed regarding the above embodiment.

[1523] (Claim 1)

[1524] an input means for inputting patient health information;

[1525] a receiving means for receiving the patient's health information transmitted from the input means;

[1526] a generating AI means for selecting a healthcare provider based on the patient's health information received by the receiving means;

[1527] a notification means for notifying a patient of information about a healthcare provider selected by the generating AI means;

[1528] A system including:

[1529] (Claim 2)

[1530] 10. The system of claim 1, wherein the generative AI means selects an optimal healthcare provider for the patient based on the patient's health information and the availability of multiple healthcare providers.

[1531] (Claim 3)

[1532] 10. The system of claim 1, wherein said receiving means stores the patient's health information in a database and simultaneously obtains information about available healthcare providers.

[1533] "Example 1"

[1534] (Claim 1)

[1535] an input means for inputting patient health information;

[1536] a receiving means for receiving the patient's health information transmitted from the input means;

[1537] a generating AI means for storing the patient's health information received by the receiving means in a database and selecting a healthcare provider based on the data;

[1538] a notification means for notifying a patient of information about a healthcare provider selected by the generating AI means;

[1539] A system including:

[1540] (Claim 2)

[1541] The system of claim 1, wherein the generating AI generates prompt sentences based on the patient's health information and a list of multiple healthcare providers, and selects the healthcare provider that is best suited to the patient.

[1542] (Claim 3)

[1543] The system of claim 1, further comprising: analyzing the response from the generation AI; extracting details of a recommended healthcare provider; and generating a response to notify the patient.

[1544] "Application Example 1"

[1545] New Claims

[1546] (Claim 1)

[1547] an input means for inputting patient health information;

[1548] a receiving means for receiving the patient's health information transmitted from the input means;

[1549] a generating AI means for selecting a healthcare provider based on the patient's health information received by the receiving means;

[1550] a notification means for notifying a patient of information about a healthcare provider selected by the generating AI means;

[1551] an input means for inputting patient health information in real time using a smart device;

[1552] a transmitting means for acquiring and transmitting health information by voice input or code scanning;

[1553] A system including:

[1554] (Claim 2)

[1555] 10. The system of claim 1, wherein the generative AI means selects an optimal healthcare provider for the patient based on the patient's health information and the availability of multiple healthcare providers.

[1556] (Claim 3)

[1557] 10. The system of claim 1, wherein said receiving means stores the patient's health information in a database and simultaneously obtains information about available healthcare providers.

[1558] "Example 2: Combining Emotion Engines"

[1559] (Claim 1)

[1560] an input means for inputting patient health information;

[1561] a receiving means for receiving the patient's health information and emotion information transmitted from the input means;

[1562] a generating AI means for selecting a healthcare provider based on the patient's health information and emotion information received by the receiving means;

[1563] a notification means for notifying the patient of customized notification content based on the information and emotional information of the healthcare provider selected by the generating AI means;

[1564] A system including:

[1565] (Claim 2)

[1566] 10. The system of claim 1, wherein the generative AI means selects the most appropriate healthcare provider for the patient based on the patient's health and emotional information and the availability of multiple healthcare providers.

[1567] (Claim 3)

[1568] 10. The system of claim 1, wherein the receiving means stores the patient's health and emotional information in a database and simultaneously obtains available healthcare provider information.

[1569] "Application example 2 when combining emotion engines"

[1570] (Claim 1)

[1571] an input means for inputting patient health information;

[1572] a receiving means for receiving the patient's health information transmitted from the input means;

[1573] The receiving means has an emotion engine means for collecting and analyzing emotion information together with health information;

[1574] a generating AI means for selecting a healthcare provider based on the patient's health information and emotion information received by the receiving means;

[1575] a notification means and a payment means for notifying a patient of information on a medical provider selected by the generating AI means, and for making a reservation for a medical service and making an electronic payment;

[1576] A system including:

[1577] (Claim 2)

[1578] 10. The system of claim 1, wherein the generative AI means selects an optimal healthcare provider for the patient based on the patient's health and emotional information and the availability of multiple healthcare providers.

[1579] (Claim 3)

[1580] 10. The system of claim 1, wherein the receiving means stores the patient's health and emotional information in a database and simultaneously obtains available healthcare provider information. [Explanation of symbols]

[1581] 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. an input means for inputting patient health information; a receiving means for receiving the patient's health information transmitted from the input means; a generating AI means for selecting a healthcare provider based on the patient's health information received by the receiving means; a notification means for notifying a patient of information about a healthcare provider selected by the generating AI means; A system including:

2. 10. The system of claim 1, wherein the generative AI means selects an optimal healthcare provider for the patient based on the patient's health information and the availability of multiple healthcare providers.

3. 2. The system of claim 1, wherein said receiving means stores patient health information in a database and simultaneously obtains available health care provider information.

Images