system

Abstract

We provide the system. [Solution] A means of translating an input language into another specified language using a generative model, A means of displaying the translated text on the user's terminal, A means of managing medical sessions and mediating communication between users, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] While it is required to realize smooth online medical treatment between doctors and patients who speak different languages, the conventional system has a problem of requiring a great deal of cost and labor for multilingual support. Also, real-time translation is necessary, but in existing technologies, it may be difficult to perform translation with sufficient accuracy. For this reason, the users are limited, and there are limitations in online medical treatment in a multinational environment.

Means for Solving the Problems

[0005] This invention provides a system that uses a generative model to translate a user's input language into a specified language and displays the translation result on the user's terminal. This enables effective online medical consultations between doctors and patients who speak different languages ​​by managing consultation sessions and appropriately mediating communication between users. Furthermore, this system provides a secure and efficient medical environment by recording consultation history, performing user authentication, and controlling the start and end of sessions.

[0006] A "generative model" is a model that uses artificial intelligence to perform natural language processing and translate a given input text into another language.

[0007] "Translation means" refers to the process and related functions of converting input text into another language using a generative model.

[0008] A "user terminal" is a device used by a doctor or patient to display translated text or other medical information.

[0009] A "medical session" refers to the entire online medical consultation process between a doctor and a patient, including all interactions from start to finish.

[0010] "Communication intermediary means" refers to a function that manages the transmission and reception of data between users and enables appropriate translation and information sharing.

[0011] "Medical history" refers to a record of information generated during the medical treatment process, which is stored for later reference.

[0012] "User authentication" refers to the process of verifying a user's identity in order to grant them access to the system.

[0013] "Session control" is a function that properly manages the start and end of medical sessions to ensure system stability and security. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

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

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0035] This invention provides an online medical consultation system to support smooth medical consultations between doctors and patients who speak different languages. This system utilizes generative models to perform real-time translation and facilitates multilingual communication.

[0036] The system consists of a server, users (doctors and patients), and terminals used by each user. The server has the function of mediating medical sessions and executing generative models. Users participate in medical sessions using their terminals and input the necessary information.

[0037] Specifically, in this system, the user (foreign patient) enters their symptoms into a terminal in their native language. The information sent from the terminal is received by a server and translated by a generative model. The translated result is sent to the user's (doctor's) terminal, allowing the doctor to understand the content in Japanese and proceed with the treatment. The reverse process is also achieved by having the server receive information entered by the user (doctor) in Japanese, translating it into the patient's native language using a generative model, and then sending it to the patient's terminal.

[0038] This translation process allows users to enjoy the convenience of receiving online medical consultations smoothly without experiencing language barriers. By utilizing the high-precision translation of generative models throughout the entire consultation process, the aim is to streamline communication between doctors and patients and improve the quality of medical services. The system also includes a function to record consultation history and allow users to review past information as needed, thereby improving the safety and reliability of medical care.

[0039] As a concrete example, imagine a scenario where an English-speaking foreign patient residing in Japan enters their physical symptoms via smartphone, and the information is instantly translated into Japanese and transmitted to a doctor in Japan. Based on this translated information, the user (doctor) enters additional questions in Japanese to provide appropriate treatment, and this information is then sent back to the user (patient) in their native language, ensuring consistent treatment. This entire process is conducted via a secure server, and the security of the session is ensured through user authentication.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user (patient) launches the medical application using their own device and logs into the system. The login information is sent from the device to the server.

[0043] Step 2:

[0044] The server authenticates the received login information and verifies the user's (patient's) credentials. If authentication is successful, the server establishes a medical session.

[0045] Step 3:

[0046] The user (patient) enters their symptoms in their native language into the terminal. The entered text is then sent from the terminal to the server.

[0047] Step 4:

[0048] The server passes the received text to a generative model, which translates it into the specified language (usually the doctor's language). After the generative model translates the text, it returns the result to the server.

[0049] Step 5:

[0050] The server sends the translation results to the user's (doctor's) terminal. The user (doctor) checks the translated content on their terminal and proceeds with the medical consultation.

[0051] Step 6:

[0052] The user (doctor) enters questions and instructions regarding medical treatment in Japanese. This input is then sent from the terminal to the server.

[0053] Step 7:

[0054] The server passes the physician's input to a generative model, which translates it into the patient's native language. The translated text is returned to the server and sent to the user's (patient's) terminal.

[0055] Step 8:

[0056] The user (patient) checks the translated content on their device, enters further questions or answers as needed, and the translation process is repeated.

[0057] Step 9:

[0058] After all consultations are complete, the users (doctor and patient) terminate their respective sessions. The server confirms the end of the sessions and records the necessary consultation history.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In multilingual medical settings, language barriers hinder communication between doctors and patients, making accurate information transmission difficult. These language barriers can reduce the quality of care and potentially impact patient safety. Furthermore, a high level of security regarding medical information is essential.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for translating input information into another language using a generative model, means for presenting the translation results to the user terminal, and means for managing the medical treatment process and mediating data transmission between users. This enables accurate and rapid communication between doctors and patients who speak different languages, improving the quality of medical treatment and ensuring a high level of information security.

[0064] A "generative model" is a program that uses statistical and computational methods to translate natural language from a large dataset that artificial intelligence has learned from.

[0065] "Input information" refers to data that the system receives for processing, such as text or speech entered by the user in their native language.

[0066] "Another language" refers to a language different from the language originally used in the input information, and is the language to be translated.

[0067] "Translation result" refers to the text data obtained after the input information has been converted into another language by a generative model.

[0068] A "user terminal" refers to an electronic device used by doctors and patients to input and receive information, and includes personal computers and smartphones.

[0069] The term "medical process" refers to the entire set of actions and procedures related to diagnosis, treatment, and follow-up conducted online between the doctor and the patient.

[0070] "Data transmission" refers to the act of sending and receiving information between a user's terminal and a server, and between them.

[0071] "User authentication" refers to the process of verifying that doctors and patients using the system are legitimate users with the appropriate authority.

[0072] "Connection" refers to the state in which a server and a user's terminal communicate via the internet or similar means.

[0073] "Information security" refers to a state in which transmitted data is protected from unauthorized access and leakage, and privacy is preserved.

[0074] This invention is an online medical consultation system for facilitating medical consultations between doctors and patients who speak different languages. The system consists of a server, users (doctors and patients), and terminals used by each user.

[0075] The server has the capability to run a generative AI model and translate input information into other languages ​​in real time. Specifically, the server passes the collected data to the generative AI model for translation. The generative AI model utilizes language processing algorithms trained on a large dataset to convert the input text into the target language. The server then receives this result again and sends it to the appropriate user terminal.

[0076] The user (patient) enters their symptoms into the terminal in their native language. This input information is sent to the server via an application installed on the terminal. The server receives the information and uses a generative AI model to translate it. The translated result is then sent to the user (doctor)'s terminal, where the doctor reviews the content in Japanese. Conversely, medical information and questions entered by the user (doctor) in Japanese are similarly translated by the server, and the information converted to the patient's native language is sent to the patient's terminal.

[0077] This enables accurate and rapid communication between doctors and patients who speak different languages. Furthermore, the system ensures communication security by encrypting data. For example, a foreign patient from an English-speaking country living in Japan can input their symptoms via smartphone, which are instantly translated into Japanese and sent to a doctor in Japan. The doctor then proceeds with the consultation based on this information, inputting questions in Japanese, which are then translated back into English and sent to the patient. This entire process is conducted via a secure server, and security is ensured through user authentication.

[0078] Example of a prompt:

[0079] "Please enter the patient's symptoms in English. We will then translate them into Japanese."

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user (patient) uses an application installed on the terminal to input symptoms in their native language. The input text data is prepared by the terminal's transmission system and formatted as prompt messages to be sent to the server. Here, the input is text data in the patient's language, and the output is prompt messages sent to the server.

[0083] Step 2:

[0084] The server receives prompt messages from the terminal. The received text data is supplied to the generative AI model. The generative AI model translates the input text in the patient's native language into Japanese based on pre-trained data. The input is text data in the patient's language, and the output is the translated result into Japanese.

[0085] Step 3:

[0086] The server sends Japanese text data translated by a generative AI model to the user's (doctor's) terminal. The doctor's terminal has an interface for displaying this translation result, allowing the doctor to visually confirm the content. The input is the translated Japanese text data, and the output is the display on the doctor's terminal.

[0087] Step 4:

[0088] The user (doctor) conducts medical consultations based on translated information on their device, and inputs necessary questions and medical details in Japanese. This Japanese input data is prepared as prompt messages to be sent back to the server. The input is Japanese text data, and the output is prompt messages sent to the server.

[0089] Step 5:

[0090] The server receives a Japanese prompt message sent by the doctor and uses the generative AI model again to translate this information into the patient's native language. The high-speed processing of the generative AI model enables rapid language conversion. The input is Japanese text data, and the output is the translated result into the patient's native language.

[0091] Step 6:

[0092] The server sends the translated text data in the patient's native language back to the user's (patient's) terminal. The patient's terminal displays this translation result, allowing the patient to understand its content. The input is the translated text data, and the output is the display on the patient's terminal.

[0093] This series of processes allows users (doctors and patients) to communicate smoothly without experiencing language barriers.

[0094] (Application Example 1)

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

[0096] In sales promotion and consumer behavior in multilingual environments, smooth communication between customers and staff who speak different languages ​​is often hindered, resulting in significant time and effort. To address this challenge, a system that provides real-time and accurate multilingual translation is necessary.

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

[0098] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for displaying the translated information on an end-user device, and means for managing scenarios that mediate sales promotion and consumer behavior, and for mediating information exchange between target parties within the region. This enables smooth communication between customers and staff even in a multilingual environment.

[0099] A "generative model" is a machine learning algorithm used to translate a given language into another language.

[0100] The "input language" refers to the original language, which is the target of translation into the specified other language.

[0101] "Another language" refers to a language intended for a different purpose than the original language that was input.

[0102] "Translated information" refers to texts and data that have been converted into other languages ​​using generative models.

[0103] An "end-user device" is a device that receives and displays information, and is a terminal that the user operates directly.

[0104] "A setting that mediates sales promotion and consumer behavior" refers to an interactive environment in which consumers can obtain information about products and services and make purchases.

[0105] "Target users within the region" refers to a group of users who exchange information within a specific virtual or physical area.

[0106] This invention is a system that enables smooth communication between multiple languages ​​and can perform real-time translation using a generative model.

[0107] The system consists of a server, end-user devices (smartphones, smart glasses, head-mounted displays, robots, etc.), and users who operate them. The server utilizes a generative AI model to convert input languages ​​into other languages. The end-user devices are responsible for displaying the converted information to the user.

[0108] The server provides translation functionality by specifically using a natural language processing model, such as the OpenAI® API. This model processes text data and translates it into a specified language pair. It also establishes security and reliability using user authentication and mediates accurate information exchange for each session.

[0109] An example of a prompt is a translation request in the format: "Translate the following text from Japanese to English: Is this product waterproof?". Based on this prompt, the server applies a generative AI model to achieve accurate and rapid information conversion.

[0110] Translated information displayed on end-user devices allows customers and staff speaking different languages ​​to quickly understand each other's intentions and continue communicating. This process is particularly effective in multilingual consumer activities, such as in virtual stores.

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

[0112] Step 1:

[0113] The user enters their inquiry in their own language into the end-user device. This user input is the first input to the system. The terminal formats this input information into a data format and prepares to send it to the server.

[0114] Step 2:

[0115] The server receives user input sent from the terminal. Based on the received text, it generates a prompt for the generation AI model and sends that prompt to the generation AI model. Specifically, the prompt is created in the format "Translate the following text from source language to target language: user input".

[0116] Step 3:

[0117] The generative AI model processes the prompt and translates the text into the specified target language. During this process, the received text undergoes language conversion within the model, generating the translated text. The server then receives this translation result.

[0118] Step 4:

[0119] The server sends the generated translated text to the end-user device. This transmission prepares the user to receive the translation results.

[0120] Step 5:

[0121] The terminal displays the translated text received from the server, providing the user with visual feedback. This allows the user to see how their input in their own language has been translated into another language.

[0122] Step 6:

[0123] (Reverse flow) Similarly, staff members input their responses in their own language and send the content from their terminal to the server. The server then uses a generative AI model to translate this back into the user's language and sends it back to the user.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention provides a system for offering medical services that take into account the user's emotional state by combining an emotion engine with an online medical consultation system. This system utilizes a generative model and an emotion engine to not only translate communication between doctors and patients but also to provide medical support that incorporates emotional information.

[0126] This system consists of a server, users (doctors and patients), and terminals used by each user. The server manages communication between users, executes generative models, and includes an emotion engine that recognizes user emotions from input data.

[0127] The user (patient) inputs symptoms and conditions in their native language from their device. This input data is sent to the server, where it is translated by a generative model, and the user's emotional state is analyzed by an emotion engine. If the emotion engine determines, for example, that the user is feeling anxious, the server also sends that emotional information to the user's (doctor's) device.

[0128] The user (doctor) reviews the translated medical information and patient emotional data, and enters a response in Japanese. This information is then translated again via the server and returned to the user's (patient's) terminal along with advice and information tailored to their emotional state.

[0129] For example, if a patient enters "I've been really tired lately and I'm worried" in their native language during a consultation, that information is sent to the server for translation and sentiment analysis. The sentiment engine determines that the patient is highly anxious based on the word "worried" and transmits this data to the doctor. The doctor can then provide support such as advising the patient in their own language to "get plenty of rest" and suggesting future treatment plans.

[0130] This system performs user authentication, controls the start and end of sessions, and records all medical history and sentiment analysis data, thereby providing a better clinical environment and promoting the delivery of safe and effective medical services.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user (patient) logs into the medical application using their own device. Login information is sent from the device to the server for authentication.

[0134] Step 2:

[0135] The server authenticates the user (patient) login and establishes a secure medical session. During this process, it verifies that user authentication has been completed.

[0136] Step 3:

[0137] The user (patient) enters text, including symptoms and emotions, into the terminal in their native language. The entered data is then sent from the terminal to the server.

[0138] Step 4:

[0139] The server passes the input data to a generative model, which translates the text into a language the user (doctor) understands. Simultaneously, the emotion engine analyzes the input data and identifies the user's emotions.

[0140] Step 5:

[0141] The server sends the translated text and sentiment analysis results to the user's (doctor's) terminal. The user (doctor) then uses this information to conduct medical consultations.

[0142] Step 6:

[0143] The user (doctor) inputs medical information and advice in Japanese. The server receives this information and uses a generative model to translate it into the patient's native language.

[0144] Step 7:

[0145] The server generates translated doctor responses and, if necessary, emotional support information, and sends them to the user's (patient's) terminal. The user (patient) can review the content and ask further questions.

[0146] Step 8:

[0147] Once the consultation is complete, the users (doctor and patient) terminate the session. The server confirms the session's end and records all consultation history and sentiment analysis data.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] Conventional online medical consultation systems have the problem that communication between healthcare providers and patients does not take into account the patient's emotional state, making it difficult to provide appropriate medical support tailored to the patient's psychological condition. Furthermore, while translation functions are necessary for smooth communication between users who speak different languages, the loss of emotional information may lead to a decline in the quality of medical care.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes means for translating input information into specified different languages ​​using a generative model, means for extracting emotional information from the input information using an emotion recognition engine, and means for translating and providing a response based on medical information and emotional information to the user. This enables smoother communication between different languages ​​and medical support that takes into account the patient's emotional state.

[0153] A "generative model" is a model for translating input information into different languages, and it is a system that performs text conversion between languages ​​using natural language processing techniques.

[0154] A "translation tool" is a function that converts input information into a specified language in order to facilitate smooth communication between users who speak different languages.

[0155] "Receiving device" refers to a terminal device used by the user to receive translated information and responses from healthcare providers.

[0156] A "medical session" is a communication platform where healthcare providers and patients can exchange medical information in real time.

[0157] "Means of mediation" refers to functions that manage data communication between users and ensure the proper sending and receiving of necessary information.

[0158] An "emotion recognition engine" is a software system that analyzes emotions from input information and extracts that information.

[0159] "Emotional information" refers to data that indicates the psychological state of the user, analyzed from their input.

[0160] "Means of recording" refers to system functions that save medical history and emotional information, making them accessible later.

[0161] "User authentication" is the process of verifying the user's identity in order to use the system securely.

[0162] This invention provides medical support that takes into account the patient's emotional state in an online medical consultation system, using a generative AI model and an emotion recognition engine. This system consists of a server, users (doctors and patients), and terminals used by each user.

[0163] The server utilizes a generative AI model to translate information such as symptoms and situations received from the user into different languages ​​specified by the user. This enables smooth communication between users who speak different languages. The server also has an emotion recognition engine that analyzes and extracts the user's emotional information from the input data.

[0164] Specifically, the user (patient) inputs their situation into the terminal in their native language. This information is sent to the server, where it is translated by a generative model, and at the same time, the emotional state is analyzed by an emotion engine. For example, if the patient inputs, "I've been really tired and worried lately," the emotion recognition engine extracts the feeling of anxiety from the keyword "worry" and conveys that information to the doctor.

[0165] The doctor reviews the translated medical information and patient sentiment data on their device and enters a response in Japanese. This response is then translated again into the patient's native language via the server and sent to the patient's device. This allows the patient to receive the doctor's advice in their native language.

[0166] This system also includes a mechanism for recording medical history and emotional information, which can be referenced later. Furthermore, user authentication ensures a secure environment for managing the start and end of sessions.

[0167] A concrete example of a prompt message would be, "Please tell me how to respond if the user is feeling anxious." In this way, the server utilizes generative AI models and emotion recognition to achieve more effective medical communication.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The user (patient) enters symptoms and medical questions into the terminal in their native language. This input information is sent from the patient's terminal to the server. The input may include text such as, "I've been feeling tired and worried lately."

[0171] Step 2:

[0172] The server processes the received patient input information. First, it uses a generative AI model to translate the input information in the patient's native language into the specified language, in this case Japanese, which is understandable to doctors. This translation process converts the input text into a language for doctors.

[0173] Step 3:

[0174] The server uses an emotion recognition engine to analyze input information from the patient and extract the patient's emotional state. Specifically, the emotion of anxiety is extracted from the keyword "worry." This emotional information is important data for the server to understand the patient's feelings and communicate them to the doctor.

[0175] Step 4:

[0176] The server combines the translated medical information and extracted sentiment information and sends it to the user's (doctor's) terminal. The output includes the translated text and sentiment information.

[0177] Step 5:

[0178] The user (doctor) reviews the information received on the device. This includes translated descriptions of the patient's condition and information about the patient's emotional state. Based on this, the doctor considers a treatment plan and inputs responses to the patient in Japanese.

[0179] Step 6:

[0180] The response from the doctor's terminal is sent to the server. The server receives the doctor's input and uses a generative AI model to translate it back into the patient's native language. This translation ensures that the response is in a language that is easily understood by the patient.

[0181] Step 7:

[0182] The server sends the translated doctor's response to the user's (patient's) terminal. The patient can then review the doctor's advice and treatment plan in their native language. This enables effective communication across language barriers.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0185] Conventional autonomous vehicles have struggled to provide individualized service tailored to the emotional state of passengers, making it difficult to offer a comfortable ride. In particular, they have been unable to accurately understand passengers' moods and emotions and provide appropriate services and content based on that understanding. This invention aims to solve this problem and provide passengers with a comfortable and personalized ride.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0187] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for performing sentiment analysis and providing optimal information based on sentiment information, and means for analyzing the passenger's emotional state and providing appropriate content based on that. This makes it possible to provide personalized content that corresponds to the passenger's emotional state.

[0188] A "generative model" is an artificial intelligence technique used to convert input data into another format, and is primarily used in natural language processing.

[0189] "Translation methods" refer to the technology of converting text written in one language into another specified language.

[0190] "Means of displaying on a user terminal" refers to technologies for visually displaying information on the screen of a device.

[0191] "Means of managing medical sessions" refers to technologies that oversee communications and data processing during the provision of medical services, and that facilitate the smooth progress of these processes.

[0192] "Methods for performing emotion analysis" refer to technologies that automatically determine a person's emotions based on their statements and facial expressions.

[0193] "Means of providing optimal information" refers to technologies that select and present the most beneficial and appropriate information for the user based on analyzed data.

[0194] "Methods for analyzing passengers' emotional states" refers to technologies that interpret and analyze passengers' emotions from their facial expressions and voices.

[0195] "Means of providing appropriate content" refers to technologies that select and provide the most suitable entertainment and information to users based on the results of sentiment analysis.

[0196] This invention provides a system installed in an autonomous vehicle that analyzes passengers' emotional states in real time and provides them with appropriate content based on the results. The system comprises an emotion analysis engine, a generative model, and a content delivery module.

[0197] The system's operation begins with hardware such as cameras and microphones installed in the autonomous vehicle collecting passengers' facial expressions and voice data. This data is transmitted to a computer inside the vehicle. The computer analyzes this input data using Microsoft® Azure® Face API and Google® Cloud Vision API to perform sentiment analysis. Based on the analysis results, OpenAI's generative AI model is used to generate content tailored to the passengers.

[0198] The server then delivers this generated content through the vehicle's displays and speakers. This process allows passengers to receive entertainment and information optimized for their mood at the time. For example, if a passenger needs to relax, the system can choose to play calming music or nature footage.

[0199] For example, if a passenger appears depressed, the system can recommend and play relaxing music. An example of a prompt message would be: "Analyze the passenger's emotions and suggest the most suitable entertainment content based on the results. If the passenger is stressed, play relaxing music."

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

[0201] Step 1:

[0202] Cameras and microphones installed inside the autonomous vehicle collect passengers' facial expressions and voices in real time. Video and audio data are used as input. This data is first sent to a server.

[0203] Step 2:

[0204] The server performs emotion analysis based on the received video and audio data. Specifically, it uses Microsoft Azure's Face API and Google Cloud's Vision API to analyze the emotional state of passengers from their facial expressions. Data regarding the type and intensity of emotion is output. Data processing is performed by vectorizing various facial features and then analyzing them.

[0205] Step 3:

[0206] The server generates appropriate content using a generative AI model based on the analyzed emotional state. It utilizes pre-configured prompts to select music and video content that matches the passenger's emotions. The generative model's data calculations consider the influence of emotional state to determine the most appropriate content from multiple possibilities.

[0207] Step 4:

[0208] The server plays the generated content through the autonomous vehicle's displays and speakers. The output is the provision of selected music and videos to the passengers. The playback speed and volume of the content are also adjusted according to the passengers' current situation to ensure effective content delivery.

[0209] Step 5:

[0210] Passengers can relax emotionally through music and visuals. In this step, they can provide feedback on whether the provided content achieved its purpose, and the server can use that information for further analysis. This feedback feature allows for even more personalized experiences on subsequent rides.

[0211] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0212] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0213] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0217] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0218] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0219] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0220] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0221] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0222] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0223] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0225] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0226] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0227] This invention provides an online medical consultation system to support smooth medical consultations between doctors and patients who speak different languages. This system utilizes generative models to perform real-time translation and facilitates multilingual communication.

[0228] The system consists of a server, users (doctors and patients), and terminals used by each user. The server has the function of mediating medical sessions and executing generative models. Users participate in medical sessions using their terminals and input the necessary information.

[0229] Specifically, in this system, the user (foreign patient) enters their symptoms into a terminal in their native language. The information sent from the terminal is received by a server and translated by a generative model. The translated result is sent to the user's (doctor's) terminal, allowing the doctor to understand the content in Japanese and proceed with the treatment. The reverse process is also achieved by having the server receive information entered by the user (doctor) in Japanese, translating it into the patient's native language using a generative model, and then sending it to the patient's terminal.

[0230] This translation process allows users to enjoy the convenience of receiving online medical consultations smoothly without experiencing language barriers. By utilizing the high-precision translation of generative models throughout the entire consultation process, the aim is to streamline communication between doctors and patients and improve the quality of medical services. The system also includes a function to record consultation history and allow users to review past information as needed, thereby improving the safety and reliability of medical care.

[0231] As a concrete example, imagine a scenario where an English-speaking foreign patient residing in Japan enters their physical symptoms via smartphone, and the information is instantly translated into Japanese and transmitted to a doctor in Japan. Based on this translated information, the user (doctor) enters additional questions in Japanese to provide appropriate treatment, and this information is then sent back to the user (patient) in their native language, ensuring consistent treatment. This entire process is conducted via a secure server, and the security of the session is ensured through user authentication.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The user (patient) launches the medical application using their own device and logs into the system. The login information is sent from the device to the server.

[0235] Step 2:

[0236] The server authenticates the received login information and verifies the user's (patient's) credentials. If authentication is successful, the server establishes a medical session.

[0237] Step 3:

[0238] The user (patient) enters their symptoms in their native language into the terminal. The entered text is then sent from the terminal to the server.

[0239] Step 4:

[0240] The server passes the received text to a generative model, which translates it into the specified language (usually the doctor's language). After the generative model translates the text, it returns the result to the server.

[0241] Step 5:

[0242] The server sends the translation results to the user's (doctor's) terminal. The user (doctor) checks the translated content on their terminal and proceeds with the medical consultation.

[0243] Step 6:

[0244] The user (doctor) enters questions and instructions regarding medical treatment in Japanese. This input is then sent from the terminal to the server.

[0245] Step 7:

[0246] The server passes the physician's input to a generative model, which translates it into the patient's native language. The translated text is returned to the server and sent to the user's (patient's) terminal.

[0247] Step 8:

[0248] The user (patient) checks the translated content on their device, enters further questions or answers as needed, and the translation process is repeated.

[0249] Step 9:

[0250] After all consultations are complete, the users (doctor and patient) terminate their respective sessions. The server confirms the end of the sessions and records the necessary consultation history.

[0251] (Example 1)

[0252] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0253] In multilingual medical settings, language barriers hinder communication between doctors and patients, making accurate information transmission difficult. These language barriers can reduce the quality of care and potentially impact patient safety. Furthermore, a high level of security regarding medical information is essential.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes means for translating input information into another language using a generative model, means for presenting the translation results to the user terminal, and means for managing the medical treatment process and mediating data transmission between users. This enables accurate and rapid communication between doctors and patients who speak different languages, improving the quality of medical treatment and ensuring a high level of information security.

[0256] A "generative model" is a program that uses statistical and computational methods to translate natural language from a large dataset that artificial intelligence has learned from.

[0257] "Input information" refers to data that the system receives for processing, such as text or speech entered by the user in their native language.

[0258] "Another language" refers to a language different from the language originally used in the input information, and is the language to be translated.

[0259] "Translation result" refers to the text data obtained after the input information has been converted into another language by a generative model.

[0260] A "user terminal" refers to an electronic device used by doctors and patients to input and receive information, and includes personal computers and smartphones.

[0261] The term "medical process" refers to the entire set of actions and procedures related to diagnosis, treatment, and follow-up conducted online between the doctor and the patient.

[0262] "Data transmission" refers to the act of sending and receiving information between a user's terminal and a server, and between them.

[0263] "User authentication" refers to the process of verifying that doctors and patients using the system are legitimate users with the appropriate authority.

[0264] "Connection" refers to the state in which a server and a user's terminal communicate via the internet or similar means.

[0265] "Information security" refers to a state in which transmitted data is protected from unauthorized access and leakage, and privacy is preserved.

[0266] This invention is an online medical consultation system for facilitating medical consultations between doctors and patients who speak different languages. The system consists of a server, users (doctors and patients), and terminals used by each user.

[0267] The server has the capability to run a generative AI model and translate input information into other languages ​​in real time. Specifically, the server passes the collected data to the generative AI model for translation. The generative AI model utilizes language processing algorithms trained on a large dataset to convert the input text into the target language. The server then receives this result again and sends it to the appropriate user terminal.

[0268] The user (patient) enters their symptoms into the terminal in their native language. This input information is sent to the server via an application installed on the terminal. The server receives the information and uses a generative AI model to translate it. The translated result is then sent to the user (doctor)'s terminal, where the doctor reviews the content in Japanese. Conversely, medical information and questions entered by the user (doctor) in Japanese are similarly translated by the server, and the information converted to the patient's native language is sent to the patient's terminal.

[0269] This enables accurate and rapid communication between doctors and patients who speak different languages. Furthermore, the system ensures communication security by encrypting data. For example, a foreign patient from an English-speaking country living in Japan can input their symptoms via smartphone, which are instantly translated into Japanese and sent to a doctor in Japan. The doctor then proceeds with the consultation based on this information, inputting questions in Japanese, which are then translated back into English and sent to the patient. This entire process is conducted via a secure server, and security is ensured through user authentication.

[0270] Example of a prompt:

[0271] "Please enter the patient's symptoms in English. We will then translate them into Japanese."

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The user (patient) uses an application installed on the terminal to input symptoms in their native language. The input text data is prepared by the terminal's transmission system and formatted as prompt messages to be sent to the server. Here, the input is text data in the patient's language, and the output is prompt messages sent to the server.

[0275] Step 2:

[0276] The server receives prompt messages from the terminal. The received text data is supplied to the generative AI model. The generative AI model translates the input text in the patient's native language into Japanese based on pre-trained data. The input is text data in the patient's language, and the output is the translated result into Japanese.

[0277] Step 3:

[0278] The server sends Japanese text data translated by a generative AI model to the user's (doctor's) terminal. The doctor's terminal has an interface for displaying this translation result, allowing the doctor to visually confirm the content. The input is the translated Japanese text data, and the output is the display on the doctor's terminal.

[0279] Step 4:

[0280] The user (doctor) conducts medical consultations based on translated information on their device, and inputs necessary questions and medical details in Japanese. This Japanese input data is prepared as prompt messages to be sent back to the server. The input is Japanese text data, and the output is prompt messages sent to the server.

[0281] Step 5:

[0282] The server receives the Japanese prompt text sent by the doctor and uses the generative AI model to translate this information into the patient's native language again. Due to the high-speed processing of the generative AI model, rapid language conversion is executed. The input is Japanese text data, and the output is the translation result into the patient's native language.

[0283] Step 6:

[0284] The server sends back the translated text data in the patient's native language to the user (patient)'s terminal. The patient's terminal displays this translation result so that the patient can understand the content. The input is the translated text data, and the output is the display on the patient's terminal.

[0285] Through this series of processes, users (doctors and patients) can communicate smoothly without feeling the language barrier.

[0286] (Application Example 1)

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

[0288] In the scenarios of sales promotion and consumer behavior in a multilingual environment, there are problems that the communication between customers and staff using different languages is not smooth and requires a lot of time and effort. To solve this problem, a system that provides real-time and accurate multilingual translation is necessary.

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

[0290] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for displaying the translated information on an end-user device, and means for managing scenarios that mediate sales promotion and consumer behavior, and for mediating information exchange between target parties within the region. This enables smooth communication between customers and staff even in a multilingual environment.

[0291] A "generative model" is a machine learning algorithm used to translate a given language into another language.

[0292] The "input language" refers to the original language, which is the target of translation into the specified other language.

[0293] "Another language" refers to a language intended for a different purpose than the original language that was input.

[0294] "Translated information" refers to texts and data that have been converted into other languages ​​using generative models.

[0295] An "end-user device" is a device that receives and displays information, and is a terminal that the user operates directly.

[0296] "A setting that mediates sales promotion and consumer behavior" refers to an interactive environment in which consumers can obtain information about products and services and make purchases.

[0297] "Target users within the region" refers to a group of users who exchange information within a specific virtual or physical area.

[0298] This invention is a system that enables smooth communication between multiple languages ​​and can perform real-time translation using a generative model.

[0299] The system consists of a server, end-user devices (smartphones, smart glasses, head-mounted displays, robots, etc.), and users who operate them. The server utilizes a generative AI model to convert input languages ​​into other languages. The end-user devices are responsible for displaying the converted information to the user.

[0300] The server provides translation functionality by specifically using a natural language processing model, such as the OpenAI API. This model processes text data and translates it into a specified language pair. It also establishes security and reliability using user authentication and mediates accurate information exchange for each session.

[0301] An example of a prompt is a translation request in the format: "Translate the following text from Japanese to English: Is this product waterproof?". Based on this prompt, the server applies a generative AI model to achieve accurate and rapid information conversion.

[0302] Translated information displayed on end-user devices allows customers and staff speaking different languages ​​to quickly understand each other's intentions and continue communicating. This process is particularly effective in multilingual consumer activities, such as in virtual stores.

[0303] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0304] Step 1:

[0305] The user enters their inquiry in their own language into the end-user device. This user input is the first input to the system. The terminal formats this input information into a data format and prepares to send it to the server.

[0306] Step 2:

[0307] The server receives the user input sent from the terminal. Based on the received text, it generates a prompt sentence for the generation AI model and sends the prompt to the generation AI model. Specifically, the prompt sentence is created in the form of "Translate the following text from source language to target language: user input".

[0308] Step 3:

[0309] The generation AI model processes the prompt and translates the text into the specified target language. At this time, the received text is subjected to language conversion processing within the model, and the translated text is generated. The server receives the translation result.

[0310] Step 4:

[0311] The server sends the generated translated text to the end-user device. By this transmission, the user is prepared to receive the translation result.

[0312] Step 5:

[0313] The terminal displays the translated text received from the server and provides visual feedback to the user. Thereby, the user can confirm how the content input in their own language is translated into another language.

[0314] Step 6:

[0315] (Reverse flow) Similarly, the staff also inputs a response in their own language and sends the content from the terminal to the server. The server translates this again into the user's language using the generation AI model and returns it to the user.

[0316] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0317] This invention provides a system for offering medical services that take into account the user's emotional state by combining an emotion engine with an online medical consultation system. This system utilizes a generative model and an emotion engine to not only translate communication between doctors and patients but also to provide medical support that incorporates emotional information.

[0318] This system consists of a server, users (doctors and patients), and terminals used by each user. The server manages communication between users, executes generative models, and includes an emotion engine that recognizes user emotions from input data.

[0319] The user (patient) inputs symptoms and conditions in their native language from their device. This input data is sent to the server, where it is translated by a generative model, and the user's emotional state is analyzed by an emotion engine. If the emotion engine determines, for example, that the user is feeling anxious, the server also sends that emotional information to the user's (doctor's) device.

[0320] The user (doctor) reviews the translated medical information and patient emotional data, and enters a response in Japanese. This information is then translated again via the server and returned to the user's (patient's) terminal along with advice and information tailored to their emotional state.

[0321] For example, if a patient enters "I've been really tired lately and I'm worried" in their native language during a consultation, that information is sent to the server for translation and sentiment analysis. The sentiment engine determines that the patient is highly anxious based on the word "worried" and transmits this data to the doctor. The doctor can then provide support such as advising the patient in their own language to "get plenty of rest" and suggesting future treatment plans.

[0322] This system performs user authentication, controls the start and end of sessions, and records all medical history and sentiment analysis data, thereby providing a better clinical environment and promoting the delivery of safe and effective medical services.

[0323] The following describes the processing flow.

[0324] Step 1:

[0325] The user (patient) logs into the medical application using their own device. Login information is sent from the device to the server for authentication.

[0326] Step 2:

[0327] The server authenticates the user (patient) login and establishes a secure medical session. During this process, it verifies that user authentication has been completed.

[0328] Step 3:

[0329] The user (patient) enters text, including symptoms and emotions, into the terminal in their native language. The entered data is then sent from the terminal to the server.

[0330] Step 4:

[0331] The server passes the input data to a generative model, which translates the text into a language the user (doctor) understands. Simultaneously, the emotion engine analyzes the input data and identifies the user's emotions.

[0332] Step 5:

[0333] The server sends the translated text and sentiment analysis results to the user's (doctor's) terminal. The user (doctor) then uses this information to conduct medical consultations.

[0334] Step 6:

[0335] The user (doctor) inputs medical information and advice in Japanese. The server receives this information and uses a generative model to translate it into the patient's native language.

[0336] Step 7:

[0337] The server generates translated doctor responses and, if necessary, emotional support information, and sends them to the user's (patient's) terminal. The user (patient) can review the content and ask further questions.

[0338] Step 8:

[0339] Once the consultation is complete, the users (doctor and patient) terminate the session. The server confirms the session's end and records all consultation history and sentiment analysis data.

[0340] (Example 2)

[0341] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0342] Conventional online medical consultation systems have the problem that communication between healthcare providers and patients does not take into account the patient's emotional state, making it difficult to provide appropriate medical support tailored to the patient's psychological condition. Furthermore, while translation functions are necessary for smooth communication between users who speak different languages, the loss of emotional information may lead to a decline in the quality of medical care.

[0343] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0344] In this invention, the server includes means for translating input information into specified different languages ​​using a generative model, means for extracting emotional information from the input information using an emotion recognition engine, and means for translating and providing a response based on medical information and emotional information to the user. This enables smoother communication between different languages ​​and medical support that takes into account the patient's emotional state.

[0345] A "generative model" is a model for translating input information into different languages, and it is a system that performs text conversion between languages ​​using natural language processing techniques.

[0346] A "translation tool" is a function that converts input information into a specified language in order to facilitate smooth communication between users who speak different languages.

[0347] "Receiving device" refers to a terminal device used by the user to receive translated information and responses from healthcare providers.

[0348] A "medical session" is a communication platform where healthcare providers and patients can exchange medical information in real time.

[0349] "Means of mediation" refers to functions that manage data communication between users and ensure the proper sending and receiving of necessary information.

[0350] An "emotion recognition engine" is a software system that analyzes emotions from input information and extracts that information.

[0351] "Emotional information" refers to data that indicates the psychological state of the user, analyzed from their input.

[0352] "Means of recording" refers to system functions that save medical history and emotional information, making them accessible later.

[0353] "User authentication" is the process of verifying the user's identity in order to use the system securely.

[0354] This invention provides medical support that takes into account the patient's emotional state in an online medical consultation system, using a generative AI model and an emotion recognition engine. This system consists of a server, users (doctors and patients), and terminals used by each user.

[0355] The server utilizes a generative AI model to translate information such as symptoms and situations received from the user into different languages ​​specified by the user. This enables smooth communication between users who speak different languages. The server also has an emotion recognition engine that analyzes and extracts the user's emotional information from the input data.

[0356] Specifically, the user (patient) inputs their situation into the terminal in their native language. This information is sent to the server, where it is translated by a generative model, and at the same time, the emotional state is analyzed by an emotion engine. For example, if the patient inputs, "I've been really tired and worried lately," the emotion recognition engine extracts the feeling of anxiety from the keyword "worry" and conveys that information to the doctor.

[0357] The doctor reviews the translated medical information and patient sentiment data on their device and enters a response in Japanese. This response is then translated again into the patient's native language via the server and sent to the patient's device. This allows the patient to receive the doctor's advice in their native language.

[0358] This system also includes a mechanism for recording medical history and emotional information, which can be referenced later. Furthermore, user authentication ensures a secure environment for managing the start and end of sessions.

[0359] A concrete example of a prompt message would be, "Please tell me how to respond if the user is feeling anxious." In this way, the server utilizes generative AI models and emotion recognition to achieve more effective medical communication.

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The user (patient) enters symptoms and medical questions into the terminal in their native language. This input information is sent from the patient's terminal to the server. The input may include text such as, "I've been feeling tired and worried lately."

[0363] Step 2:

[0364] The server processes the received patient input information. First, it uses a generative AI model to translate the input information in the patient's native language into the specified language, in this case Japanese, which is understandable to doctors. This translation process converts the input text into a language for doctors.

[0365] Step 3:

[0366] The server uses an emotion recognition engine to analyze input information from the patient and extract the patient's emotional state. Specifically, the emotion of anxiety is extracted from the keyword "worry." This emotional information is important data for the server to understand the patient's feelings and communicate them to the doctor.

[0367] Step 4:

[0368] The server combines the translated medical information and extracted sentiment information and sends it to the user's (doctor's) terminal. The output includes the translated text and sentiment information.

[0369] Step 5:

[0370] The user (doctor) reviews the information received on the device. This includes translated descriptions of the patient's condition and information about the patient's emotional state. Based on this, the doctor considers a treatment plan and inputs responses to the patient in Japanese.

[0371] Step 6:

[0372] The response from the doctor's terminal is sent to the server. The server receives the doctor's input and uses a generative AI model to translate it back into the patient's native language. This translation ensures that the response is in a language that is easily understood by the patient.

[0373] Step 7:

[0374] The server sends the translated doctor's response to the user's (patient's) terminal. The patient can then review the doctor's advice and treatment plan in their native language. This enables effective communication across language barriers.

[0375] (Application Example 2)

[0376] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0377] Conventional autonomous vehicles have struggled to provide individualized service tailored to the emotional state of passengers, making it difficult to offer a comfortable ride. In particular, they have been unable to accurately understand passengers' moods and emotions and provide appropriate services and content based on that understanding. This invention aims to solve this problem and provide passengers with a comfortable and personalized ride.

[0378] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0379] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for performing sentiment analysis and providing optimal information based on sentiment information, and means for analyzing the passenger's emotional state and providing appropriate content based on that. This makes it possible to provide personalized content that corresponds to the passenger's emotional state.

[0380] A "generative model" is an artificial intelligence technique used to convert input data into another format, and is primarily used in natural language processing.

[0381] "Translation methods" refer to the technology of converting text written in one language into another specified language.

[0382] "Means of displaying on a user terminal" refers to technologies for visually displaying information on the screen of a device.

[0383] "Means of managing medical sessions" refers to technologies that oversee communications and data processing during the provision of medical services, and that facilitate the smooth progress of these processes.

[0384] "Methods for performing emotion analysis" refer to technologies that automatically determine a person's emotions based on their statements and facial expressions.

[0385] "Means of providing optimal information" refers to technologies that select and present the most beneficial and appropriate information for the user based on analyzed data.

[0386] "Methods for analyzing passengers' emotional states" refers to technologies that interpret and analyze passengers' emotions from their facial expressions and voices.

[0387] "Means of providing appropriate content" refers to technologies that select and provide the most suitable entertainment and information to users based on the results of sentiment analysis.

[0388] This invention provides a system installed in an autonomous vehicle that analyzes passengers' emotional states in real time and provides them with appropriate content based on the results. The system comprises an emotion analysis engine, a generative model, and a content delivery module.

[0389] The system's operation begins with hardware such as cameras and microphones installed in the autonomous vehicle collecting passengers' facial expressions and voice data. This data is transmitted to a computer inside the vehicle. The computer analyzes this input data using Microsoft Azure's Face API and Google Cloud's Vision API to perform sentiment analysis. Based on the analysis results, OpenAI's generative AI model is used to generate content tailored to the passengers.

[0390] The server then delivers this generated content through the vehicle's displays and speakers. This process allows passengers to receive entertainment and information optimized for their mood at the time. For example, if a passenger needs to relax, the system can choose to play calming music or nature footage.

[0391] For example, if a passenger appears depressed, the system can recommend and play relaxing music. An example of a prompt message would be: "Analyze the passenger's emotions and suggest the most suitable entertainment content based on the results. If the passenger is stressed, play relaxing music."

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

[0393] Step 1:

[0394] Cameras and microphones installed inside the autonomous vehicle collect passengers' facial expressions and voices in real time. Video and audio data are used as input. This data is first sent to a server.

[0395] Step 2:

[0396] The server performs emotion analysis based on the received video and audio data. Specifically, it uses Microsoft Azure's Face API and Google Cloud's Vision API to analyze the emotional state of passengers from their facial expressions. Data regarding the type and intensity of emotion is output. Data processing is performed by vectorizing various facial features and then analyzing them.

[0397] Step 3:

[0398] The server generates appropriate content using a generative AI model based on the analyzed emotional state. It utilizes pre-configured prompts to select music and video content that matches the passenger's emotions. The generative model's data calculations consider the influence of emotional state to determine the most appropriate content from multiple possibilities.

[0399] Step 4:

[0400] The server plays the generated content through the autonomous vehicle's displays and speakers. The output is the provision of selected music and videos to the passengers. The playback speed and volume of the content are also adjusted according to the passengers' current situation to ensure effective content delivery.

[0401] Step 5:

[0402] Passengers can relax emotionally through music and visuals. In this step, they can provide feedback on whether the provided content achieved its purpose, and the server can use that information for further analysis. This feedback feature allows for even more personalized experiences on subsequent rides.

[0403] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0404] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0405] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0406] [Third Embodiment]

[0407] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0408] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0409] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0410] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0411] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0412] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0413] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0414] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0415] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0416] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0417] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0418] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0419] This invention provides an online medical consultation system to support smooth medical consultations between doctors and patients who speak different languages. This system utilizes generative models to perform real-time translation and facilitates multilingual communication.

[0420] The system consists of a server, users (doctors and patients), and terminals used by each user. The server has the function of mediating medical sessions and executing generative models. Users participate in medical sessions using their terminals and input the necessary information.

[0421] Specifically, in this system, the user (foreign patient) enters their symptoms into a terminal in their native language. The information sent from the terminal is received by a server and translated by a generative model. The translated result is sent to the user's (doctor's) terminal, allowing the doctor to understand the content in Japanese and proceed with the treatment. The reverse process is also achieved by having the server receive information entered by the user (doctor) in Japanese, translating it into the patient's native language using a generative model, and then sending it to the patient's terminal.

[0422] This translation process allows users to enjoy the convenience of receiving online medical consultations smoothly without experiencing language barriers. By utilizing the high-precision translation of generative models throughout the entire consultation process, the aim is to streamline communication between doctors and patients and improve the quality of medical services. The system also includes a function to record consultation history and allow users to review past information as needed, thereby improving the safety and reliability of medical care.

[0423] As a concrete example, imagine a scenario where an English-speaking foreign patient residing in Japan enters their physical symptoms via smartphone, and the information is instantly translated into Japanese and transmitted to a doctor in Japan. Based on this translated information, the user (doctor) enters additional questions in Japanese to provide appropriate treatment, and this information is then sent back to the user (patient) in their native language, ensuring consistent treatment. This entire process is conducted via a secure server, and the security of the session is ensured through user authentication.

[0424] The following describes the processing flow.

[0425] Step 1:

[0426] The user (patient) launches the medical application using their own device and logs into the system. The login information is sent from the device to the server.

[0427] Step 2:

[0428] The server authenticates the received login information and verifies the user's (patient's) credentials. If authentication is successful, the server establishes a medical session.

[0429] Step 3:

[0430] The user (patient) enters their symptoms in their native language into the terminal. The entered text is then sent from the terminal to the server.

[0431] Step 4:

[0432] The server passes the received text to a generative model, which translates it into the specified language (usually the doctor's language). After the generative model translates the text, it returns the result to the server.

[0433] Step 5:

[0434] The server sends the translation results to the user's (doctor's) terminal. The user (doctor) checks the translated content on their terminal and proceeds with the medical consultation.

[0435] Step 6:

[0436] The user (doctor) enters questions and instructions regarding medical treatment in Japanese. This input is then sent from the terminal to the server.

[0437] Step 7:

[0438] The server passes the physician's input to a generative model, which translates it into the patient's native language. The translated text is returned to the server and sent to the user's (patient's) terminal.

[0439] Step 8:

[0440] The user (patient) checks the translated content on their device, enters further questions or answers as needed, and the translation process is repeated.

[0441] Step 9:

[0442] After all consultations are complete, the users (doctor and patient) terminate their respective sessions. The server confirms the end of the sessions and records the necessary consultation history.

[0443] (Example 1)

[0444] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0445] In multilingual medical settings, language barriers hinder communication between doctors and patients, making accurate information transmission difficult. These language barriers can reduce the quality of care and potentially impact patient safety. Furthermore, a high level of security regarding medical information is essential.

[0446] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0447] In this invention, the server includes means for translating input information into another language using a generative model, means for presenting the translation results to the user terminal, and means for managing the medical treatment process and mediating data transmission between users. This enables accurate and rapid communication between doctors and patients who speak different languages, improving the quality of medical treatment and ensuring a high level of information security.

[0448] A "generative model" is a program that uses statistical and computational methods to translate natural language from a large dataset that artificial intelligence has learned from.

[0449] "Input information" refers to data that the system receives for processing, such as text or speech entered by the user in their native language.

[0450] "Another language" refers to a language different from the language originally used in the input information, and is the language to be translated.

[0451] "Translation result" refers to the text data obtained after the input information has been converted into another language by a generative model.

[0452] A "user terminal" refers to an electronic device used by doctors and patients to input and receive information, and includes personal computers and smartphones.

[0453] The term "medical process" refers to the entire set of actions and procedures related to diagnosis, treatment, and follow-up conducted online between the doctor and the patient.

[0454] "Data transmission" refers to the act of sending and receiving information between a user's terminal and a server, and between them.

[0455] "User authentication" refers to the process of verifying that doctors and patients using the system are legitimate users with the appropriate authority.

[0456] "Connection" refers to the state in which a server and a user's terminal communicate via the internet or similar means.

[0457] "Information security" refers to a state in which transmitted data is protected from unauthorized access and leakage, and privacy is preserved.

[0458] This invention is an online medical consultation system for facilitating medical consultations between doctors and patients who speak different languages. The system consists of a server, users (doctors and patients), and terminals used by each user.

[0459] The server has the capability to run a generative AI model and translate input information into other languages ​​in real time. Specifically, the server passes the collected data to the generative AI model for translation. The generative AI model utilizes language processing algorithms trained on a large dataset to convert the input text into the target language. The server then receives this result again and sends it to the appropriate user terminal.

[0460] The user (patient) enters their symptoms into the terminal in their native language. This input information is sent to the server via an application installed on the terminal. The server receives the information and uses a generative AI model to translate it. The translated result is then sent to the user (doctor)'s terminal, where the doctor reviews the content in Japanese. Conversely, medical information and questions entered by the user (doctor) in Japanese are similarly translated by the server, and the information converted to the patient's native language is sent to the patient's terminal.

[0461] This enables accurate and rapid communication between doctors and patients who speak different languages. Furthermore, the system ensures communication security by encrypting data. For example, a foreign patient from an English-speaking country living in Japan can input their symptoms via smartphone, which are instantly translated into Japanese and sent to a doctor in Japan. The doctor then proceeds with the consultation based on this information, inputting questions in Japanese, which are then translated back into English and sent to the patient. This entire process is conducted via a secure server, and security is ensured through user authentication.

[0462] Example of a prompt:

[0463] "Please enter the patient's symptoms in English. We will then translate them into Japanese."

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The user (patient) uses an application installed on the terminal to input symptoms in their native language. The input text data is prepared by the terminal's transmission system and formatted as prompt messages to be sent to the server. Here, the input is text data in the patient's language, and the output is prompt messages sent to the server.

[0467] Step 2:

[0468] The server receives prompt messages from the terminal. The received text data is supplied to the generative AI model. The generative AI model translates the input text in the patient's native language into Japanese based on pre-trained data. The input is text data in the patient's language, and the output is the translated result into Japanese.

[0469] Step 3:

[0470] The server sends Japanese text data translated by a generative AI model to the user's (doctor's) terminal. The doctor's terminal has an interface for displaying this translation result, allowing the doctor to visually confirm the content. The input is the translated Japanese text data, and the output is the display on the doctor's terminal.

[0471] Step 4:

[0472] The user (doctor) conducts medical consultations based on translated information on their device, and inputs necessary questions and medical details in Japanese. This Japanese input data is prepared as prompt messages to be sent back to the server. The input is Japanese text data, and the output is prompt messages sent to the server.

[0473] Step 5:

[0474] The server receives a Japanese prompt message sent by the doctor and uses the generative AI model again to translate this information into the patient's native language. The high-speed processing of the generative AI model enables rapid language conversion. The input is Japanese text data, and the output is the translated result into the patient's native language.

[0475] Step 6:

[0476] The server sends the translated text data in the patient's native language back to the user's (patient's) terminal. The patient's terminal displays this translation result, allowing the patient to understand its content. The input is the translated text data, and the output is the display on the patient's terminal.

[0477] This series of processes allows users (doctors and patients) to communicate smoothly without experiencing language barriers.

[0478] (Application Example 1)

[0479] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0480] In sales promotion and consumer behavior in multilingual environments, smooth communication between customers and staff who speak different languages ​​is often hindered, resulting in significant time and effort. To address this challenge, a system that provides real-time and accurate multilingual translation is necessary.

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

[0482] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for displaying the translated information on an end-user device, and means for managing scenarios that mediate sales promotion and consumer behavior, and for mediating information exchange between target parties within the region. This enables smooth communication between customers and staff even in a multilingual environment.

[0483] A "generative model" is a machine learning algorithm used to translate a given language into another language.

[0484] The "input language" refers to the original language, which is the target of translation into the specified other language.

[0485] "Another language" refers to a language intended for a different purpose than the original language that was input.

[0486] "Translated information" refers to texts and data that have been converted into other languages ​​using generative models.

[0487] An "end-user device" is a device that receives and displays information, and is a terminal that the user operates directly.

[0488] "A setting that mediates sales promotion and consumer behavior" refers to an interactive environment in which consumers can obtain information about products and services and make purchases.

[0489] "Target users within the region" refers to a group of users who exchange information within a specific virtual or physical area.

[0490] This invention is a system that enables smooth communication between multiple languages ​​and can perform real-time translation using a generative model.

[0491] The system consists of a server, end-user devices (smartphones, smart glasses, head-mounted displays, robots, etc.), and users who operate them. The server utilizes a generative AI model to convert input languages ​​into other languages. The end-user devices are responsible for displaying the converted information to the user.

[0492] The server provides translation functionality by specifically using a natural language processing model, such as the OpenAI API. This model processes text data and translates it into a specified language pair. It also establishes security and reliability using user authentication and mediates accurate information exchange for each session.

[0493] An example of a prompt is a translation request in the format: "Translate the following text from Japanese to English: Is this product waterproof?". Based on this prompt, the server applies a generative AI model to achieve accurate and rapid information conversion.

[0494] Translated information displayed on end-user devices allows customers and staff speaking different languages ​​to quickly understand each other's intentions and continue communicating. This process is particularly effective in multilingual consumer activities, such as in virtual stores.

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

[0496] Step 1:

[0497] The user enters their inquiry in their own language into the end-user device. This user input is the first input to the system. The terminal formats this input information into a data format and prepares to send it to the server.

[0498] Step 2:

[0499] The server receives user input sent from the terminal. Based on the received text, it generates a prompt for the generation AI model and sends that prompt to the generation AI model. Specifically, the prompt is created in the format "Translate the following text from source language to target language: user input".

[0500] Step 3:

[0501] The generative AI model processes the prompt and translates the text into the specified target language. During this process, the received text undergoes language conversion within the model, generating the translated text. The server then receives this translation result.

[0502] Step 4:

[0503] The server sends the generated translated text to the end-user device. This transmission prepares the user to receive the translation results.

[0504] Step 5:

[0505] The terminal displays the translated text received from the server, providing the user with visual feedback. This allows the user to see how their input in their own language has been translated into another language.

[0506] Step 6:

[0507] (Reverse flow) Similarly, staff members input their responses in their own language and send the content from their terminal to the server. The server then uses a generative AI model to translate this back into the user's language and sends it back to the user.

[0508] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0509] This invention provides a system for offering medical services that take into account the user's emotional state by combining an emotion engine with an online medical consultation system. This system utilizes a generative model and an emotion engine to not only translate communication between doctors and patients but also to provide medical support that incorporates emotional information.

[0510] This system consists of a server, users (doctors and patients), and terminals used by each user. The server manages communication between users, executes generative models, and includes an emotion engine that recognizes user emotions from input data.

[0511] The user (patient) inputs symptoms and conditions in their native language from their device. This input data is sent to the server, where it is translated by a generative model, and the user's emotional state is analyzed by an emotion engine. If the emotion engine determines, for example, that the user is feeling anxious, the server also sends that emotional information to the user's (doctor's) device.

[0512] The user (doctor) reviews the translated medical information and patient emotional data, and enters a response in Japanese. This information is then translated again via the server and returned to the user's (patient's) terminal along with advice and information tailored to their emotional state.

[0513] For example, if a patient enters "I've been really tired lately and I'm worried" in their native language during a consultation, that information is sent to the server for translation and sentiment analysis. The sentiment engine determines that the patient is highly anxious based on the word "worried" and transmits this data to the doctor. The doctor can then provide support such as advising the patient in their own language to "get plenty of rest" and suggesting future treatment plans.

[0514] This system performs user authentication, controls the start and end of sessions, and records all medical history and sentiment analysis data, thereby providing a better clinical environment and promoting the delivery of safe and effective medical services.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] The user (patient) logs into the medical application using their own device. Login information is sent from the device to the server for authentication.

[0518] Step 2:

[0519] The server authenticates the user (patient) login and establishes a secure medical session. During this process, it verifies that user authentication has been completed.

[0520] Step 3:

[0521] The user (patient) enters text, including symptoms and emotions, into the terminal in their native language. The entered data is then sent from the terminal to the server.

[0522] Step 4:

[0523] The server passes the input data to a generative model, which translates the text into a language the user (doctor) understands. Simultaneously, the emotion engine analyzes the input data and identifies the user's emotions.

[0524] Step 5:

[0525] The server sends the translated text and sentiment analysis results to the user's (doctor's) terminal. The user (doctor) then uses this information to conduct medical consultations.

[0526] Step 6:

[0527] The user (doctor) inputs medical information and advice in Japanese. The server receives this information and uses a generative model to translate it into the patient's native language.

[0528] Step 7:

[0529] The server generates translated doctor responses and, if necessary, emotional support information, and sends them to the user's (patient's) terminal. The user (patient) can review the content and ask further questions.

[0530] Step 8:

[0531] Once the consultation is complete, the users (doctor and patient) terminate the session. The server confirms the session's end and records all consultation history and sentiment analysis data.

[0532] (Example 2)

[0533] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0534] Conventional online medical consultation systems have the problem that communication between healthcare providers and patients does not take into account the patient's emotional state, making it difficult to provide appropriate medical support tailored to the patient's psychological condition. Furthermore, while translation functions are necessary for smooth communication between users who speak different languages, the loss of emotional information may lead to a decline in the quality of medical care.

[0535] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0536] In this invention, the server includes means for translating input information into specified different languages ​​using a generative model, means for extracting emotional information from the input information using an emotion recognition engine, and means for translating and providing a response based on medical information and emotional information to the user. This enables smoother communication between different languages ​​and medical support that takes into account the patient's emotional state.

[0537] A "generative model" is a model for translating input information into different languages, and it is a system that performs text conversion between languages ​​using natural language processing techniques.

[0538] A "translation tool" is a function that converts input information into a specified language in order to facilitate smooth communication between users who speak different languages.

[0539] "Receiving device" refers to a terminal device used by the user to receive translated information and responses from healthcare providers.

[0540] A "medical session" is a communication platform where healthcare providers and patients can exchange medical information in real time.

[0541] "Means of mediation" refers to functions that manage data communication between users and ensure the proper sending and receiving of necessary information.

[0542] An "emotion recognition engine" is a software system that analyzes emotions from input information and extracts that information.

[0543] "Emotional information" refers to data that indicates the psychological state of the user, analyzed from their input.

[0544] "Means of recording" refers to system functions that save medical history and emotional information, making them accessible later.

[0545] "User authentication" is the process of verifying the user's identity in order to use the system securely.

[0546] This invention provides medical support that takes into account the patient's emotional state in an online medical consultation system, using a generative AI model and an emotion recognition engine. This system consists of a server, users (doctors and patients), and terminals used by each user.

[0547] The server utilizes a generative AI model to translate information such as symptoms and situations received from the user into different languages ​​specified by the user. This enables smooth communication between users who speak different languages. The server also has an emotion recognition engine that analyzes and extracts the user's emotional information from the input data.

[0548] Specifically, the user (patient) inputs their situation into the terminal in their native language. This information is sent to the server, where it is translated by a generative model, and at the same time, the emotional state is analyzed by an emotion engine. For example, if the patient inputs, "I've been really tired and worried lately," the emotion recognition engine extracts the feeling of anxiety from the keyword "worry" and conveys that information to the doctor.

[0549] The doctor reviews the translated medical information and patient sentiment data on their device and enters a response in Japanese. This response is then translated again into the patient's native language via the server and sent to the patient's device. This allows the patient to receive the doctor's advice in their native language.

[0550] This system also includes a mechanism for recording medical history and emotional information, which can be referenced later. Furthermore, user authentication ensures a secure environment for managing the start and end of sessions.

[0551] A concrete example of a prompt message would be, "Please tell me how to respond if the user is feeling anxious." In this way, the server utilizes generative AI models and emotion recognition to achieve more effective medical communication.

[0552] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0553] Step 1:

[0554] The user (patient) enters symptoms and medical questions into the terminal in their native language. This input information is sent from the patient's terminal to the server. The input may include text such as, "I've been feeling tired and worried lately."

[0555] Step 2:

[0556] The server processes the received patient input information. First, it uses a generative AI model to translate the input information in the patient's native language into the specified language, in this case Japanese, which is understandable to doctors. This translation process converts the input text into a language for doctors.

[0557] Step 3:

[0558] The server uses an emotion recognition engine to analyze input information from the patient and extract the patient's emotional state. Specifically, the emotion of anxiety is extracted from the keyword "worry." This emotional information is important data for the server to understand the patient's feelings and communicate them to the doctor.

[0559] Step 4:

[0560] The server combines the translated medical information and extracted sentiment information and sends it to the user's (doctor's) terminal. The output includes the translated text and sentiment information.

[0561] Step 5:

[0562] The user (doctor) reviews the information received on the device. This includes translated descriptions of the patient's condition and information about the patient's emotional state. Based on this, the doctor considers a treatment plan and inputs responses to the patient in Japanese.

[0563] Step 6:

[0564] The response from the doctor's terminal is sent to the server. The server receives the doctor's input and uses a generative AI model to translate it back into the patient's native language. This translation ensures that the response is in a language that is easily understood by the patient.

[0565] Step 7:

[0566] The server sends the translated doctor's response to the user's (patient's) terminal. The patient can then review the doctor's advice and treatment plan in their native language. This enables effective communication across language barriers.

[0567] (Application Example 2)

[0568] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0569] Conventional autonomous vehicles have struggled to provide individualized service tailored to the emotional state of passengers, making it difficult to offer a comfortable ride. In particular, they have been unable to accurately understand passengers' moods and emotions and provide appropriate services and content based on that understanding. This invention aims to solve this problem and provide passengers with a comfortable and personalized ride.

[0570] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0571] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for performing sentiment analysis and providing optimal information based on sentiment information, and means for analyzing the passenger's emotional state and providing appropriate content based on that. This makes it possible to provide personalized content that corresponds to the passenger's emotional state.

[0572] A "generative model" is an artificial intelligence technique used to convert input data into another format, and is primarily used in natural language processing.

[0573] "Translation methods" refer to the technology of converting text written in one language into another specified language.

[0574] "Means of displaying on a user terminal" refers to technologies for visually displaying information on the screen of a device.

[0575] "Means of managing medical sessions" refers to technologies that oversee communications and data processing during the provision of medical services, and that facilitate the smooth progress of these processes.

[0576] "Methods for performing emotion analysis" refer to technologies that automatically determine a person's emotions based on their statements and facial expressions.

[0577] "Means of providing optimal information" refers to technologies that select and present the most beneficial and appropriate information for the user based on analyzed data.

[0578] "Methods for analyzing passengers' emotional states" refers to technologies that interpret and analyze passengers' emotions from their facial expressions and voices.

[0579] "Means of providing appropriate content" refers to technologies that select and provide the most suitable entertainment and information to users based on the results of sentiment analysis.

[0580] This invention provides a system installed in an autonomous vehicle that analyzes passengers' emotional states in real time and provides them with appropriate content based on the results. The system comprises an emotion analysis engine, a generative model, and a content delivery module.

[0581] The system's operation begins with hardware such as cameras and microphones installed in the autonomous vehicle collecting passengers' facial expressions and voice data. This data is transmitted to a computer inside the vehicle. The computer analyzes this input data using Microsoft Azure's Face API and Google Cloud's Vision API to perform sentiment analysis. Based on the analysis results, OpenAI's generative AI model is used to generate content tailored to the passengers.

[0582] The server then delivers this generated content through the vehicle's displays and speakers. This process allows passengers to receive entertainment and information optimized for their mood at the time. For example, if a passenger needs to relax, the system can choose to play calming music or nature footage.

[0583] For example, if a passenger appears depressed, the system can recommend and play relaxing music. An example of a prompt message would be: "Analyze the passenger's emotions and suggest the most suitable entertainment content based on the results. If the passenger is stressed, play relaxing music."

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

[0585] Step 1:

[0586] Cameras and microphones installed inside the autonomous vehicle collect passengers' facial expressions and voices in real time. Video and audio data are used as input. This data is first sent to a server.

[0587] Step 2:

[0588] The server performs emotion analysis based on the received video and audio data. Specifically, it uses Microsoft Azure's Face API and Google Cloud's Vision API to analyze the emotional state of passengers from their facial expressions. Data regarding the type and intensity of emotion is output. Data processing is performed by vectorizing various facial features and then analyzing them.

[0589] Step 3:

[0590] The server generates appropriate content using a generative AI model based on the analyzed emotional state. It utilizes pre-configured prompts to select music and video content that matches the passenger's emotions. The generative model's data calculations consider the influence of emotional state to determine the most appropriate content from multiple possibilities.

[0591] Step 4:

[0592] The server plays the generated content through the autonomous vehicle's displays and speakers. The output is the provision of selected music and videos to the passengers. The playback speed and volume of the content are also adjusted according to the passengers' current situation to ensure effective content delivery.

[0593] Step 5:

[0594] Passengers can relax emotionally through music and visuals. In this step, they can provide feedback on whether the provided content achieved its purpose, and the server can use that information for further analysis. This feedback feature allows for even more personalized experiences on subsequent rides.

[0595] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0596] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0597] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0598] [Fourth Embodiment]

[0599] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0600] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0601] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0602] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0603] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0604] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0605] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0606] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0607] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0608] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0609] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0610] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0611] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] This invention provides an online medical consultation system to support smooth medical consultations between doctors and patients who speak different languages. This system utilizes generative models to perform real-time translation and facilitates multilingual communication.

[0613] The system consists of a server, users (doctors and patients), and terminals used by each user. The server has the function of mediating medical sessions and executing generative models. Users participate in medical sessions using their terminals and input the necessary information.

[0614] Specifically, in this system, the user (foreign patient) enters their symptoms into a terminal in their native language. The information sent from the terminal is received by a server and translated by a generative model. The translated result is sent to the user's (doctor's) terminal, allowing the doctor to understand the content in Japanese and proceed with the treatment. The reverse process is also achieved by having the server receive information entered by the user (doctor) in Japanese, translating it into the patient's native language using a generative model, and then sending it to the patient's terminal.

[0615] This translation process allows users to enjoy the convenience of receiving online medical consultations smoothly without experiencing language barriers. By utilizing the high-precision translation of generative models throughout the entire consultation process, the aim is to streamline communication between doctors and patients and improve the quality of medical services. The system also includes a function to record consultation history and allow users to review past information as needed, thereby improving the safety and reliability of medical care.

[0616] As a concrete example, imagine a scenario where an English-speaking foreign patient residing in Japan enters their physical symptoms via smartphone, and the information is instantly translated into Japanese and transmitted to a doctor in Japan. Based on this translated information, the user (doctor) enters additional questions in Japanese to provide appropriate treatment, and this information is then sent back to the user (patient) in their native language, ensuring consistent treatment. This entire process is conducted via a secure server, and the security of the session is ensured through user authentication.

[0617] The following describes the processing flow.

[0618] Step 1:

[0619] The user (patient) launches the medical application using their own device and logs into the system. The login information is sent from the device to the server.

[0620] Step 2:

[0621] The server authenticates the received login information and verifies the user's (patient's) credentials. If authentication is successful, the server establishes a medical session.

[0622] Step 3:

[0623] The user (patient) enters their symptoms in their native language into the terminal. The entered text is then sent from the terminal to the server.

[0624] Step 4:

[0625] The server passes the received text to a generative model, which translates it into the specified language (usually the doctor's language). After the generative model translates the text, it returns the result to the server.

[0626] Step 5:

[0627] The server sends the translation results to the user's (doctor's) terminal. The user (doctor) checks the translated content on their terminal and proceeds with the medical consultation.

[0628] Step 6:

[0629] The user (doctor) enters questions and instructions regarding medical treatment in Japanese. This input is then sent from the terminal to the server.

[0630] Step 7:

[0631] The server passes the physician's input to a generative model, which translates it into the patient's native language. The translated text is returned to the server and sent to the user's (patient's) terminal.

[0632] Step 8:

[0633] The user (patient) checks the translated content on their device, enters further questions or answers as needed, and the translation process is repeated.

[0634] Step 9:

[0635] After all consultations are complete, the users (doctor and patient) terminate their respective sessions. The server confirms the end of the sessions and records the necessary consultation history.

[0636] (Example 1)

[0637] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0638] In multilingual medical settings, language barriers hinder communication between doctors and patients, making accurate information transmission difficult. These language barriers can reduce the quality of care and potentially impact patient safety. Furthermore, a high level of security regarding medical information is essential.

[0639] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0640] In this invention, the server includes means for translating input information into another language using a generative model, means for presenting the translation results to the user terminal, and means for managing the medical treatment process and mediating data transmission between users. This enables accurate and rapid communication between doctors and patients who speak different languages, improving the quality of medical treatment and ensuring a high level of information security.

[0641] A "generative model" is a program that uses statistical and computational methods to translate natural language from a large dataset that artificial intelligence has learned from.

[0642] "Input information" refers to data that the system receives for processing, such as text or speech entered by the user in their native language.

[0643] "Another language" refers to a language different from the language originally used in the input information, and is the language to be translated.

[0644] "Translation result" refers to the text data obtained after the input information has been converted into another language by a generative model.

[0645] A "user terminal" refers to an electronic device used by doctors and patients to input and receive information, and includes personal computers and smartphones.

[0646] The term "medical process" refers to the entire set of actions and procedures related to diagnosis, treatment, and follow-up conducted online between the doctor and the patient.

[0647] "Data transmission" refers to the act of sending and receiving information between a user's terminal and a server, and between them.

[0648] "User authentication" refers to the process of verifying that doctors and patients using the system are legitimate users with the appropriate authority.

[0649] "Connection" refers to the state in which a server and a user's terminal communicate via the internet or similar means.

[0650] "Information security" refers to a state in which transmitted data is protected from unauthorized access and leakage, and privacy is preserved.

[0651] This invention is an online medical consultation system for facilitating medical consultations between doctors and patients who speak different languages. The system consists of a server, users (doctors and patients), and terminals used by each user.

[0652] The server has the capability to run a generative AI model and translate input information into other languages ​​in real time. Specifically, the server passes the collected data to the generative AI model for translation. The generative AI model utilizes language processing algorithms trained on a large dataset to convert the input text into the target language. The server then receives this result again and sends it to the appropriate user terminal.

[0653] The user (patient) enters their symptoms into the terminal in their native language. This input information is sent to the server via an application installed on the terminal. The server receives the information and uses a generative AI model to translate it. The translated result is then sent to the user (doctor)'s terminal, where the doctor reviews the content in Japanese. Conversely, medical information and questions entered by the user (doctor) in Japanese are similarly translated by the server, and the information converted to the patient's native language is sent to the patient's terminal.

[0654] This enables accurate and rapid communication between doctors and patients who speak different languages. Furthermore, the system ensures communication security by encrypting data. For example, a foreign patient from an English-speaking country living in Japan can input their symptoms via smartphone, which are instantly translated into Japanese and sent to a doctor in Japan. The doctor then proceeds with the consultation based on this information, inputting questions in Japanese, which are then translated back into English and sent to the patient. This entire process is conducted via a secure server, and security is ensured through user authentication.

[0655] Example of a prompt:

[0656] "Please enter the patient's symptoms in English. We will then translate them into Japanese."

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] The user (patient) uses an application installed on the terminal to input symptoms in their native language. The input text data is prepared by the terminal's transmission system and formatted as prompt messages to be sent to the server. Here, the input is text data in the patient's language, and the output is prompt messages sent to the server.

[0660] Step 2:

[0661] The server receives prompt messages from the terminal. The received text data is supplied to the generative AI model. The generative AI model translates the input text in the patient's native language into Japanese based on pre-trained data. The input is text data in the patient's language, and the output is the translated result into Japanese.

[0662] Step 3:

[0663] The server sends Japanese text data translated by a generative AI model to the user's (doctor's) terminal. The doctor's terminal has an interface for displaying this translation result, allowing the doctor to visually confirm the content. The input is the translated Japanese text data, and the output is the display on the doctor's terminal.

[0664] Step 4:

[0665] The user (doctor) conducts medical consultations based on translated information on their device, and inputs necessary questions and medical details in Japanese. This Japanese input data is prepared as prompt messages to be sent back to the server. The input is Japanese text data, and the output is prompt messages sent to the server.

[0666] Step 5:

[0667] The server receives a Japanese prompt message sent by the doctor and uses the generative AI model again to translate this information into the patient's native language. The high-speed processing of the generative AI model enables rapid language conversion. The input is Japanese text data, and the output is the translated result into the patient's native language.

[0668] Step 6:

[0669] The server sends the translated text data in the patient's native language back to the user's (patient's) terminal. The patient's terminal displays this translation result, allowing the patient to understand its content. The input is the translated text data, and the output is the display on the patient's terminal.

[0670] This series of processes allows users (doctors and patients) to communicate smoothly without experiencing language barriers.

[0671] (Application Example 1)

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

[0673] In sales promotion and consumer behavior in multilingual environments, smooth communication between customers and staff who speak different languages ​​is often hindered, resulting in significant time and effort. To address this challenge, a system that provides real-time and accurate multilingual translation is necessary.

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

[0675] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for displaying the translated information on an end-user device, and means for managing scenarios that mediate sales promotion and consumer behavior, and for mediating information exchange between target parties within the region. This enables smooth communication between customers and staff even in a multilingual environment.

[0676] A "generative model" is a machine learning algorithm used to translate a given language into another language.

[0677] The "input language" refers to the original language, which is the target of translation into the specified other language.

[0678] "Another language" refers to a language intended for a different purpose than the original language that was input.

[0679] "Translated information" refers to texts and data that have been converted into other languages ​​using generative models.

[0680] An "end-user device" is a device that receives and displays information, and is a terminal that the user operates directly.

[0681] "A setting that mediates sales promotion and consumer behavior" refers to an interactive environment in which consumers can obtain information about products and services and make purchases.

[0682] "Target users within the region" refers to a group of users who exchange information within a specific virtual or physical area.

[0683] This invention is a system that enables smooth communication between multiple languages ​​and can perform real-time translation using a generative model.

[0684] The system consists of a server, end-user devices (smartphones, smart glasses, head-mounted displays, robots, etc.), and users who operate them. The server utilizes a generative AI model to convert input languages ​​into other languages. The end-user devices are responsible for displaying the converted information to the user.

[0685] The server provides translation functionality by specifically using a natural language processing model, such as the OpenAI API. This model processes text data and translates it into a specified language pair. It also establishes security and reliability using user authentication and mediates accurate information exchange for each session.

[0686] An example of a prompt is a translation request in the format: "Translate the following text from Japanese to English: Is this product waterproof?". Based on this prompt, the server applies a generative AI model to achieve accurate and rapid information conversion.

[0687] Translated information displayed on end-user devices allows customers and staff speaking different languages ​​to quickly understand each other's intentions and continue communicating. This process is particularly effective in multilingual consumer activities, such as in virtual stores.

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

[0689] Step 1:

[0690] The user enters their inquiry in their own language into the end-user device. This user input is the first input to the system. The terminal formats this input information into a data format and prepares to send it to the server.

[0691] Step 2:

[0692] The server receives user input sent from the terminal. Based on the received text, it generates a prompt for the generation AI model and sends that prompt to the generation AI model. Specifically, the prompt is created in the format "Translate the following text from source language to target language: user input".

[0693] Step 3:

[0694] The generative AI model processes the prompt and translates the text into the specified target language. During this process, the received text undergoes language conversion within the model, generating the translated text. The server then receives this translation result.

[0695] Step 4:

[0696] The server sends the generated translated text to the end-user device. This transmission prepares the user to receive the translation results.

[0697] Step 5:

[0698] The terminal displays the translated text received from the server, providing the user with visual feedback. This allows the user to see how their input in their own language has been translated into another language.

[0699] Step 6:

[0700] (Reverse flow) Similarly, staff members input their responses in their own language and send the content from their terminal to the server. The server then uses a generative AI model to translate this back into the user's language and sends it back to the user.

[0701] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0702] This invention provides a system for offering medical services that take into account the user's emotional state by combining an emotion engine with an online medical consultation system. This system utilizes a generative model and an emotion engine to not only translate communication between doctors and patients but also to provide medical support that incorporates emotional information.

[0703] This system consists of a server, users (doctors and patients), and terminals used by each user. The server manages communication between users, executes generative models, and includes an emotion engine that recognizes user emotions from input data.

[0704] The user (patient) inputs symptoms and conditions in their native language from their device. This input data is sent to the server, where it is translated by a generative model, and the user's emotional state is analyzed by an emotion engine. If the emotion engine determines, for example, that the user is feeling anxious, the server also sends that emotional information to the user's (doctor's) device.

[0705] The user (doctor) reviews the translated medical information and patient emotional data, and enters a response in Japanese. This information is then translated again via the server and returned to the user's (patient's) terminal along with advice and information tailored to their emotional state.

[0706] For example, if a patient enters "I've been really tired lately and I'm worried" in their native language during a consultation, that information is sent to the server for translation and sentiment analysis. The sentiment engine determines that the patient is highly anxious based on the word "worried" and transmits this data to the doctor. The doctor can then provide support such as advising the patient in their own language to "get plenty of rest" and suggesting future treatment plans.

[0707] This system performs user authentication, controls the start and end of sessions, and records all medical history and sentiment analysis data, thereby providing a better clinical environment and promoting the delivery of safe and effective medical services.

[0708] The following describes the processing flow.

[0709] Step 1:

[0710] The user (patient) logs into the medical application using their own device. Login information is sent from the device to the server for authentication.

[0711] Step 2:

[0712] The server authenticates the user (patient) login and establishes a secure medical session. During this process, it verifies that user authentication has been completed.

[0713] Step 3:

[0714] The user (patient) enters text, including symptoms and emotions, into the terminal in their native language. The entered data is then sent from the terminal to the server.

[0715] Step 4:

[0716] The server passes the input data to a generative model, which translates the text into a language the user (doctor) understands. Simultaneously, the emotion engine analyzes the input data and identifies the user's emotions.

[0717] Step 5:

[0718] The server sends the translated text and sentiment analysis results to the user's (doctor's) terminal. The user (doctor) then uses this information to conduct medical consultations.

[0719] Step 6:

[0720] The user (doctor) inputs medical information and advice in Japanese. The server receives this information and uses a generative model to translate it into the patient's native language.

[0721] Step 7:

[0722] The server generates translated doctor responses and, if necessary, emotional support information, and sends them to the user's (patient's) terminal. The user (patient) can review the content and ask further questions.

[0723] Step 8:

[0724] Once the consultation is complete, the users (doctor and patient) terminate the session. The server confirms the session's end and records all consultation history and sentiment analysis data.

[0725] (Example 2)

[0726] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0727] Conventional online medical consultation systems have the problem that communication between healthcare providers and patients does not take into account the patient's emotional state, making it difficult to provide appropriate medical support tailored to the patient's psychological condition. Furthermore, while translation functions are necessary for smooth communication between users who speak different languages, the loss of emotional information may lead to a decline in the quality of medical care.

[0728] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0729] In this invention, the server includes means for translating input information into specified different languages ​​using a generative model, means for extracting emotional information from the input information using an emotion recognition engine, and means for translating and providing a response based on medical information and emotional information to the user. This enables smoother communication between different languages ​​and medical support that takes into account the patient's emotional state.

[0730] A "generative model" is a model for translating input information into different languages, and it is a system that performs text conversion between languages ​​using natural language processing techniques.

[0731] A "translation tool" is a function that converts input information into a specified language in order to facilitate smooth communication between users who speak different languages.

[0732] "Receiving device" refers to a terminal device used by the user to receive translated information and responses from healthcare providers.

[0733] A "medical session" is a communication platform where healthcare providers and patients can exchange medical information in real time.

[0734] "Means of mediation" refers to functions that manage data communication between users and ensure the proper sending and receiving of necessary information.

[0735] An "emotion recognition engine" is a software system that analyzes emotions from input information and extracts that information.

[0736] "Emotional information" refers to data that indicates the psychological state of the user, analyzed from their input.

[0737] "Means of recording" refers to system functions that save medical history and emotional information, making them accessible later.

[0738] "User authentication" is the process of verifying the user's identity in order to use the system securely.

[0739] This invention provides medical support that takes into account the patient's emotional state in an online medical consultation system, using a generative AI model and an emotion recognition engine. This system consists of a server, users (doctors and patients), and terminals used by each user.

[0740] The server utilizes a generative AI model to translate information such as symptoms and situations received from the user into different languages ​​specified by the user. This enables smooth communication between users who speak different languages. The server also has an emotion recognition engine that analyzes and extracts the user's emotional information from the input data.

[0741] Specifically, the user (patient) inputs their situation into the terminal in their native language. This information is sent to the server, where it is translated by a generative model, and at the same time, the emotional state is analyzed by an emotion engine. For example, if the patient inputs, "I've been really tired and worried lately," the emotion recognition engine extracts the feeling of anxiety from the keyword "worry" and conveys that information to the doctor.

[0742] The doctor reviews the translated medical information and patient sentiment data on their device and enters a response in Japanese. This response is then translated again into the patient's native language via the server and sent to the patient's device. This allows the patient to receive the doctor's advice in their native language.

[0743] This system also includes a mechanism for recording medical history and emotional information, which can be referenced later. Furthermore, user authentication ensures a secure environment for managing the start and end of sessions.

[0744] A concrete example of a prompt message would be, "Please tell me how to respond if the user is feeling anxious." In this way, the server utilizes generative AI models and emotion recognition to achieve more effective medical communication.

[0745] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0746] Step 1:

[0747] The user (patient) enters symptoms and medical questions into the terminal in their native language. This input information is sent from the patient's terminal to the server. The input may include text such as, "I've been feeling tired and worried lately."

[0748] Step 2:

[0749] The server processes the received patient input information. First, it uses a generative AI model to translate the input information in the patient's native language into the specified language, in this case Japanese, which is understandable to doctors. This translation process converts the input text into a language for doctors.

[0750] Step 3:

[0751] The server uses an emotion recognition engine to analyze input information from the patient and extract the patient's emotional state. Specifically, the emotion of anxiety is extracted from the keyword "worry." This emotional information is important data for the server to understand the patient's feelings and communicate them to the doctor.

[0752] Step 4:

[0753] The server combines the translated medical information and extracted sentiment information and sends it to the user's (doctor's) terminal. The output includes the translated text and sentiment information.

[0754] Step 5:

[0755] The user (doctor) reviews the information received on the device. This includes translated descriptions of the patient's condition and information about the patient's emotional state. Based on this, the doctor considers a treatment plan and inputs responses to the patient in Japanese.

[0756] Step 6:

[0757] The response from the doctor's terminal is sent to the server. The server receives the doctor's input and uses a generative AI model to translate it back into the patient's native language. This translation ensures that the response is in a language that is easily understood by the patient.

[0758] Step 7:

[0759] The server sends the translated doctor's response to the user's (patient's) terminal. The patient can then review the doctor's advice and treatment plan in their native language. This enables effective communication across language barriers.

[0760] (Application Example 2)

[0761] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] Conventional autonomous vehicles have struggled to provide individualized service tailored to the emotional state of passengers, making it difficult to offer a comfortable ride. In particular, they have been unable to accurately understand passengers' moods and emotions and provide appropriate services and content based on that understanding. This invention aims to solve this problem and provide passengers with a comfortable and personalized ride.

[0763] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0764] In this invention, the server includes means for translating an input language into a specified other language using a generative model, means for performing sentiment analysis and providing optimal information based on sentiment information, and means for analyzing the passenger's emotional state and providing appropriate content based on that. This makes it possible to provide personalized content that corresponds to the passenger's emotional state.

[0765] A "generative model" is an artificial intelligence technique used to convert input data into another format, and is primarily used in natural language processing.

[0766] "Translation methods" refer to the technology of converting text written in one language into another specified language.

[0767] "Means of displaying on a user terminal" refers to technologies for visually displaying information on the screen of a device.

[0768] "Means of managing medical sessions" refers to technologies that oversee communications and data processing during the provision of medical services, and that facilitate the smooth progress of these processes.

[0769] "Methods for performing emotion analysis" refer to technologies that automatically determine a person's emotions based on their statements and facial expressions.

[0770] "Means of providing optimal information" refers to technologies that select and present the most beneficial and appropriate information for the user based on analyzed data.

[0771] "Methods for analyzing passengers' emotional states" refers to technologies that interpret and analyze passengers' emotions from their facial expressions and voices.

[0772] "Means of providing appropriate content" refers to technologies that select and provide the most suitable entertainment and information to users based on the results of sentiment analysis.

[0773] This invention provides a system installed in an autonomous vehicle that analyzes passengers' emotional states in real time and provides them with appropriate content based on the results. The system comprises an emotion analysis engine, a generative model, and a content delivery module.

[0774] The system's operation begins with hardware such as cameras and microphones installed in the autonomous vehicle collecting passengers' facial expressions and voice data. This data is transmitted to a computer inside the vehicle. The computer analyzes this input data using Microsoft Azure's Face API and Google Cloud's Vision API to perform sentiment analysis. Based on the analysis results, OpenAI's generative AI model is used to generate content tailored to the passengers.

[0775] The server then delivers this generated content through the vehicle's displays and speakers. This process allows passengers to receive entertainment and information optimized for their mood at the time. For example, if a passenger needs to relax, the system can choose to play calming music or nature footage.

[0776] For example, if a passenger appears depressed, the system can recommend and play relaxing music. An example of a prompt message would be: "Analyze the passenger's emotions and suggest the most suitable entertainment content based on the results. If the passenger is stressed, play relaxing music."

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

[0778] Step 1:

[0779] Cameras and microphones installed inside the autonomous vehicle collect passengers' facial expressions and voices in real time. Video and audio data are used as input. This data is first sent to a server.

[0780] Step 2:

[0781] The server performs emotion analysis based on the received video and audio data. Specifically, it uses Microsoft Azure's Face API and Google Cloud's Vision API to analyze the emotional state of passengers from their facial expressions. Data regarding the type and intensity of emotion is output. Data processing is performed by vectorizing various facial features and then analyzing them.

[0782] Step 3:

[0783] The server generates appropriate content using a generative AI model based on the analyzed emotional state. It utilizes pre-configured prompts to select music and video content that matches the passenger's emotions. The generative model's data calculations consider the influence of emotional state to determine the most appropriate content from multiple possibilities.

[0784] Step 4:

[0785] The server plays the generated content through the autonomous vehicle's displays and speakers. The output is the provision of selected music and videos to the passengers. The playback speed and volume of the content are also adjusted according to the passengers' current situation to ensure effective content delivery.

[0786] Step 5:

[0787] Passengers can relax emotionally through music and visuals. In this step, they can provide feedback on whether the provided content achieved its purpose, and the server can use that information for further analysis. This feedback feature allows for even more personalized experiences on subsequent rides.

[0788] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0789] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0790] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0791] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0792] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0793] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0794] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0795] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0796] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0797] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0798] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0799] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0800] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0801] 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.

[0802] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0803] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0804] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0805] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0806] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0807] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0808] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0809] The following is further disclosed regarding the embodiments described above.

[0810] (Claim 1)

[0811] A means of translating an input language into another specified language using a generative model,

[0812] A means of displaying the translated text on the user's terminal,

[0813] A means of managing medical sessions and mediating communication between users,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, which can record and later display medical history.

[0817] (Claim 3)

[0818] The system according to claim 1, which performs user authentication and controls the start and end of a session.

[0819] "Example 1"

[0820] (Claim 1)

[0821] A method for translating input information into another language using a generative model,

[0822] A means of displaying the translation result on the user's terminal,

[0823] A means of managing the medical treatment process and mediating data transmission between users,

[0824] A means to verify the user and ensure the security of the connection,

[0825] By performing translation in real time, it becomes a means of eliminating language barriers,

[0826] A means of encrypting data and protecting information,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, which stores a medical history and can display it as needed.

[0830] (Claim 3)

[0831] The system according to claim 1, which performs user authentication and manages the initiation and termination of connections.

[0832] "Application Example 1"

[0833] (Claim 1)

[0834] A means of translating an input language into another specified language using a generative model,

[0835] Means for displaying translated information on an end-user device,

[0836] A means of managing situations that mediate sales promotion and consumer behavior, and mediating information exchange among target individuals within the region,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, which can record and later display a customer's consumption history.

[0840] (Claim 3)

[0841] The system according to claim 1, which verifies the user and controls the start and end of communication.

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

[0843] (Claim 1)

[0844] A means of translating input information into a specified different language using a generative model,

[0845] A means of displaying the translated information on a receiving device,

[0846] A means of controlling medical sessions and mediating communication between users,

[0847] A means for extracting emotional information from input information using an emotion recognition engine,

[0848] A means of transmitting information to healthcare providers along with translated information using extracted emotional information,

[0849] A means of translating and providing responses to users based on medical information and emotional information,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, which records medical history and emotional information and makes it available for later display.

[0853] (Claim 3)

[0854] The system according to claim 1, which performs user authentication and controls the start and end of medical sessions.

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

[0856] (Claim 1)

[0857] A means of translating an input language into another specified language using a generative model,

[0858] A means of displaying the translated text on the user's terminal,

[0859] A means of managing medical sessions and mediating communication between users,

[0860] A means of performing emotion analysis and providing optimal information based on emotional information,

[0861] A means of analyzing the emotional state of passengers and providing appropriate content based on that analysis,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, which can record and later display medical history.

[0865] (Claim 3)

[0866] The system according to claim 1, which performs user authentication and controls the start and end of a session. [Explanation of Symbols]

[0867] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of translating an input language into another specified language using a generative model, A means of displaying the translated text on the user's terminal, A means of managing medical sessions and mediating communication between users, A system that includes this.

2. The system according to claim 1, which can record and later display medical history.

3. The system according to claim 1, which performs user authentication and controls the start and end of a session.

Images