system

Abstract

The system according to this embodiment aims to facilitate communication between patients and medical professionals and enable the exchange of accurate medical information. [Solution] The system according to the embodiment comprises a translation unit, a specialized terminology translation unit, a real-time translation unit, a multilingual support unit, and a drug information analysis unit. The translation unit performs translations to facilitate communication between patients and medical professionals. The specialized terminology translation unit accurately translates medical terminology translated by the translation unit. The real-time translation unit provides the content translated by the specialized terminology translation unit in real time. The multilingual support unit provides the content provided by the real-time translation unit in multiple languages. The drug information analysis unit analyzes drug interactions based on the content provided by the multilingual support unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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 that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the communication between patients and medical experts is not smooth, and there is room for improvement especially in multi-language support and accurate translation of technical terms.

[0005] The system according to the embodiment aims to smooth the communication between patients and medical experts and enable accurate exchange of medical information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a translation unit, a specialized terminology translation unit, a real-time translation unit, a multilingual support unit, and a drug information analysis unit. The translation unit performs translations to facilitate communication between patients and medical professionals. The specialized terminology translation unit accurately translates medical terminology translated by the translation unit. The real-time translation unit provides the content translated by the specialized terminology translation unit in real time. The multilingual support unit provides the content provided by the real-time translation unit in multiple languages. The drug information analysis unit analyzes drug interactions based on the content provided by the multilingual support unit. [Effects of the Invention]

[0007] The system according to this embodiment can facilitate communication between patients and medical professionals and enable the exchange of accurate medical information. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The medical translation system according to an embodiment of the present invention is a system that utilizes generative AI to enable effective communication between patients and medical professionals. In particular, it allows foreign visitors to Japan to receive medical care smoothly and to take their medication with peace of mind, as it provides explanations of medications and information about drug interactions with medications brought from other countries. Specifically, it consists of the following steps. First, a medical translation service using generative AI is provided to facilitate communication between patients and medical professionals. This service supports communication between patients and doctors, nurses, and medical staff, enabling the exchange of accurate medical information. For example, when a patient describes their symptoms, the generative AI can translate the content in real time and convey it to the medical professional. Next, the generative AI performs accurate translation of medical terminology. Medical translation often involves specialized terminology and medical concepts, requiring more specialized knowledge than general translation tools. By using generative AI, accurate translation of specialized terminology becomes possible, facilitating smooth communication in medical settings. Furthermore, the medical translation service utilizing generative AI can operate in real time. This is particularly useful for communication in urgent situations, enabling a rapid response. For example, when a patient describes their symptoms in an emergency, the generative AI can instantly translate the content and convey it to the medical professional. Furthermore, the medical translation service supports multiple languages. This facilitates communication with multinational medical institutions and patients, and smooths communication between patients and medical professionals who speak different languages. For example, by supporting multiple languages ​​such as English, Chinese, and Spanish, it can serve patients from various countries. In addition, the generating AI can also inform patients about drug interactions with other medications they bring from other countries. When information about the medications a patient has brought is entered, the generating AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications. This allows patients to take their medication with peace of mind. This system facilitates communication between patients and medical professionals, allowing foreign visitors to Japan to receive medical care smoothly. Moreover, because it provides explanations of medications and information about drug interactions with medications brought from other countries, patients can take their medication with confidence.For example, when a patient inputs information about medications they have brought with them, the generated AI analyzes the drug's ingredients, effects, and side effects, and provides advice on potential interactions with other medications. This allows patients to take their medication with peace of mind. Thus, the medical translation system facilitates communication between patients and medical professionals, enabling foreign visitors to Japan to receive medical care smoothly. Furthermore, it provides information about medications and potential interactions with medications brought from other countries, allowing patients to take their medication with confidence.

[0029] The medical translation system according to this embodiment comprises a translation unit, a specialized terminology translation unit, a real-time translation unit, a multilingual support unit, and a drug information analysis unit. The translation unit is responsible for facilitating communication between patients and medical professionals. For example, the translation unit can use a generative AI to translate a patient's statements in real time and convey them to medical professionals. For example, when a patient describes their symptoms, the generative AI can instantly translate the content and convey it to medical professionals. The specialized terminology translation unit is responsible for accurately translating medical terminology translated by the translation unit. For example, the specialized terminology translation unit can use a generative AI to accurately translate medical terminology and convey it to medical professionals. For example, by accurately translating medical terminology, it facilitates communication in medical settings. The real-time translation unit is responsible for providing the content translated by the specialized terminology translation unit in real time. For example, the real-time translation unit instantly provides the content translated using a generative AI to support communication in emergencies. For example, when a patient describes their symptoms in an emergency, the generative AI can instantly translate the content and convey it to medical professionals. The Multilingual Support Department is responsible for translating the content provided by the Real-Time Translation Department into multiple languages. For example, the Multilingual Support Department uses generative AI to support multiple languages, facilitating communication between patients and medical professionals who speak different languages. By supporting multiple languages, such as English, Chinese, and Spanish, it can accommodate patients from various countries. The Drug Information Analysis Department analyzes drug interactions based on the content provided by the Multilingual Support Department. For example, the Drug Information Analysis Department uses generative AI to analyze the ingredients, effects, and side effects of medications brought by patients, and provides advice on drug interactions with other medications. For instance, when information on medications brought by a patient is entered, the generative AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications. This allows the medical translation system to facilitate smooth communication between patients and medical professionals and enable the exchange of accurate medical information.

[0030] The translation department is responsible for facilitating communication between patients and healthcare professionals. For example, it can use generative AI to translate patient statements in real time and convey them to healthcare professionals. Specifically, the generative AI utilizes natural language processing technology to recognize patient speech and convert it into text. It then translates the text into the target language and provides it to healthcare professionals via voice or text. For instance, when a patient describes their symptoms, the generative AI can instantly translate the content and convey it to the healthcare professional. The generative AI achieves accurate translation by understanding the context of the patient's statements and selecting appropriate medical terminology. Furthermore, the translation department can translate not only patient statements but also instructions and questions from healthcare professionals and convey them to the patient. This enables two-way communication between patients and healthcare professionals, improving the accuracy of diagnosis and treatment. Additionally, the translation department can prevent misunderstandings by considering the patient's cultural background and linguistic nuances and selecting appropriate expressions. For example, avoiding culturally sensitive expressions and phrases can enhance patient comfort. This allows the translation department to facilitate communication between patients and medical professionals and support the exchange of accurate medical information.

[0031] The Specialized Terminology Translation Department is responsible for accurately translating medical terminology translated by the Translation Department. For example, the Specialized Terminology Translation Department can use generative AI to accurately translate medical terminology and communicate it to medical professionals. Specifically, the generative AI consults medical-specific dictionaries and databases to understand the precise meaning and usage of specialized terminology. For instance, accurate translation of medical terminology facilitates smoother communication in medical settings. The generative AI learns from large amounts of medical data using machine learning algorithms to understand the context of medical terminology and provide appropriate translations. This allows the Specialized Terminology Translation Department to accurately translate advanced terminology and abbreviations used by medical professionals, preventing misunderstandings. Furthermore, the Specialized Terminology Translation Department can maintain a list of specific terminology and abbreviations used by medical professionals, ensuring that the information is always up-to-date. This improves the accuracy of communication in medical settings and enhances the quality of diagnosis and treatment. In addition to translating medical terminology, the Specialized Terminology Translation Department can also convert it into language easily understood by patients. This allows patients to accurately understand their medical condition and treatment plan, enabling them to make appropriate decisions.

[0032] The Real-Time Translation Department provides content translated by the Specialized Terminology Translation Department in real time. For example, the Real-Time Translation Department instantly provides content translated using generative AI, supporting communication in emergencies. Specifically, the generative AI has high processing capabilities and can instantly provide translated content in audio or text format. For example, when a patient describes their symptoms in an emergency, the generative AI can instantly translate that content and convey it to medical professionals. The generative AI combines speech recognition and natural language processing technologies to analyze the patient's statements in real time and provide translation results. This enables the Real-Time Translation Department to respond quickly in emergencies and ensure patient safety. Furthermore, the Real-Time Translation Department can also translate instructions and questions from medical professionals to patients in real time and convey them to the patients. This facilitates smooth two-way communication in emergencies and enables quick and appropriate responses. In addition, to continuously improve the accuracy of translation results, the Real-Time Translation Department regularly updates the generative AI's training data to reflect the latest medical information. This allows the Real-Time Translation Department to consistently provide highly accurate translation results and support communication in medical settings.

[0033] The Multilingual Support Department is responsible for translating content provided by the Real-Time Translation Department into multiple languages. For example, the Multilingual Support Department uses generative AI to support multiple languages, facilitating communication between patients and medical professionals who speak different languages. Specifically, the generative AI utilizes multilingual natural language processing technology to support multiple languages, such as English, Chinese, and Spanish. By supporting multiple languages, it can accommodate patients from various countries. The generative AI learns from a large amount of multilingual data using machine learning algorithms to understand the grammar, vocabulary, and cultural background of each language and provide appropriate translations. This allows the Multilingual Support Department to facilitate communication between patients and medical professionals who speak different languages, preventing misunderstandings and errors in medical settings. Furthermore, by supporting communication in the patient's native language, the Multilingual Support Department can enhance patient confidence and encourage active participation in treatment. In addition, the Multilingual Support Department can provide multilingual translations of specialized terminology and abbreviations used by medical professionals, improving the accuracy of communication in medical settings. This allows the multilingual support unit to facilitate communication between patients and medical professionals who speak different languages, enabling accurate information exchange in medical settings.

[0034] The Drug Information Analysis Department is responsible for analyzing drug interactions based on information provided by the Multilingual Support Department. For example, the Drug Information Analysis Department uses generative AI to analyze the ingredients, effects, and side effects of medications brought in by patients, and provides advice on drug interactions with other medications. Specifically, the generative AI refers to a drug ingredient database and analyzes the ingredients, effects, and side effects of each drug. For instance, when information on medications brought in by a patient is input, the generative AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications. The generative AI learns data on drug ingredients, effects, and side effects, and uses machine learning algorithms to evaluate the risks of drug interactions and drug combinations. This allows the Drug Information Analysis Department to ensure the safety of medications patients are taking and support appropriate treatment. Furthermore, the Drug Information Analysis Department can provide individualized advice by considering the patient's medical history and allergy information. This enables the selection of optimal medications according to the patient's health condition, minimizing the risks associated with side effects and drug interactions. Furthermore, the Drug Information Analysis Department can provide healthcare professionals with the latest information on drug interactions, thereby improving the quality of diagnosis and treatment. This allows the Drug Information Analysis Department to support accurate information exchange between patients and healthcare professionals, leading to safer and more effective treatment.

[0035] The drug information input unit can input information about medications brought by the patient. For example, the drug information input unit can input information such as the name, ingredients, and dosage of the medication brought by the patient. For example, the drug information input unit provides an interface for inputting information about medications brought by the patient, making it easy for the patient to input the information. This makes it possible to analyze drug interactions by inputting information about the medications brought by the patient. Some or all of the above processing in the drug information input unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the drug information input unit can input information about medications brought by the patient into a generating AI, and the generating AI can analyze that information.

[0036] The information provision unit can provide information analyzed by the generating AI. For example, the information provision unit can provide information such as drug components, effects, and side effects analyzed by the generating AI. For example, the information provision unit can provide information analyzed by the generating AI to patients and medical professionals, supporting accurate information sharing. This facilitates information sharing between patients and medical professionals by providing information analyzed by the generating AI. Some or all of the above processing in the information provision unit may be performed using the generating AI or without it. For example, the information provision unit can provide information analyzed by the generating AI through web applications or mobile applications.

[0037] The Emergency Response Unit can support emergency response. For example, the Emergency Response Unit can use generative AI to provide emergency response methods and support a rapid response. For example, the Emergency Response Unit can immediately provide necessary information in an emergency, enabling medical professionals to respond quickly. This enables a rapid response by supporting emergency response. Some or all of the above-described processes in the Emergency Response Unit may be performed using generative AI or not. For example, the Emergency Response Unit may use generative AI to provide emergency response methods, enabling medical professionals to respond quickly.

[0038] The translation unit can select the optimal translation method by referring to the patient's past medical history during translation. For example, the translation unit can refer to the patient's past medical records and adjust the frequency of use of technical terms. For example, the translation unit can prioritize the translation of relevant information based on the patient's past medical history. The translation unit can also consider the patient's past treatment history and select appropriate medical terms for translation. In this way, the optimal translation method can be selected by referring to the patient's past medical history. Some or all of the above processing in the translation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the translation unit can input the patient's past medical history into a generation AI, and the generation AI can select the optimal translation method based on that history.

[0039] The translation unit can adjust the level of detail in the translation based on the patient's current health condition. For example, if the patient is in a critical condition, the translation unit will prioritize translating concise and important information. For example, if the patient is in a stable condition, the translation unit can provide a translation that includes detailed explanations. Furthermore, if the patient is in the recovery phase, the translation unit can provide detailed information regarding rehabilitation. This allows for the provision of more appropriate information by adjusting the level of detail in the translation according to the patient's current health condition. Some or all of the above processing in the translation unit may be performed using or without a generative AI. For example, the translation unit can input the patient's current health condition into the generative AI, which can then adjust the level of detail in the translation based on that condition.

[0040] The translation unit can prioritize highly relevant translations by considering the patient's geographical location during the translation process. For example, if the patient is in a specific region, the translation unit will prioritize translating medical information for that region. For example, if the patient is traveling, the translation unit can prioritize translating medical information for the travel destination. Also, if the patient is at home, the translation unit can prioritize translating information about nearby medical facilities. This allows the system to prioritize providing highly relevant information by considering the patient's geographical location. Some or all of the above processing in the translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the translation unit can input the patient's geographical location information into a generative AI, which can then prioritize highly relevant translations based on that information.

[0041] The translation unit can analyze the patient's social media activity during translation and translate relevant information. For example, the translation unit can translate relevant medical information based on health information shared by the patient on social media. For example, the translation unit can prioritize translating information from medical professionals the patient follows on social media. The translation unit can also translate information related to medical topics the patient has shown interest in on social media. This allows the unit to provide relevant information by analyzing the patient's social media activity. Some or all of the above processing in the translation unit may be performed using or without generative AI. For example, the translation unit can input the patient's social media activity into a generative AI, which can then translate relevant information based on that activity.

[0042] The specialized terminology translation unit can select the optimal translation method when translating specialized terminology by referring to the medical professional's past medical history. For example, the specialized terminology translation unit can adjust the frequency of use of specialized terminology by referring to the medical professional's past medical records. For example, the specialized terminology translation unit can prioritize the translation of relevant information based on the medical professional's past medical history. Furthermore, the specialized terminology translation unit can select and translate appropriate medical terms by considering the medical professional's past medical history. This allows the unit to select the optimal translation method by referring to the medical professional's past medical history. Some or all of the above processing in the specialized terminology translation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the specialized terminology translation unit can input the medical professional's past medical history into a generation AI, and the generation AI can select the optimal translation method based on that history.

[0043] The specialized terminology translation unit can apply different translation algorithms to each medical field when translating specialized terminology. For example, the specialized terminology translation unit can apply an internal medicine-specific translation algorithm to internal medicine terminology. For example, the specialized terminology translation unit can apply a surgical-specific translation algorithm to surgical terminology. Furthermore, the specialized terminology translation unit can apply a pediatrics-specific translation algorithm to pediatric terminology. By applying different translation algorithms to each medical field, the accuracy of the translation is improved. Some or all of the above processing in the specialized terminology translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the specialized terminology translation unit can input different translation algorithms for each medical field into a generative AI, and the generative AI can translate the specialized terminology based on that algorithm.

[0044] The specialized terminology translation unit can prioritize highly relevant translations by considering the geographical location of medical institutions when translating specialized terminology. For example, if a medical institution is located in a specific region, the specialized terminology translation unit can prioritize translating medical information for that region. For example, if a medical institution is located in a travel destination, the specialized terminology translation unit can prioritize translating medical information for that destination. Furthermore, if a medical institution is located near a patient's home, the specialized terminology translation unit can prioritize translating information for nearby medical institutions. In this way, by considering the geographical location of medical institutions, highly relevant information can be provided preferentially. Some or all of the above processing in the specialized terminology translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the specialized terminology translation unit can input the geographical location information of medical institutions into a generative AI, and the generative AI can prioritize highly relevant translations based on that information.

[0045] The specialized terminology translation unit can improve the accuracy of its translations by referring to relevant medical literature when translating specialized terms. For example, the specialized terminology translation unit can improve the accuracy of its translations by referring to the latest medical literature when translating specialized terms. For example, the specialized terminology translation unit can improve the accuracy of its translations by referring to past medical literature. In addition, the specialized terminology translation unit can improve the accuracy of its translations by referring to relevant academic papers. Thus, the accuracy of the translation is improved by referring to relevant medical literature. Some or all of the above processes in the specialized terminology translation unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the specialized terminology translation unit can input relevant medical literature into a generative AI, and the generative AI can translate specialized terms based on that literature.

[0046] The real-time translation unit can adjust the translation priority according to urgency during real-time translation. For example, if the urgency is high, the generating AI will prioritize translating important information. For example, if the urgency is low, the generating AI can produce a translation that includes detailed explanations. Furthermore, if the urgency is moderate, the generating AI can produce a translation using concise and easy-to-understand language. This allows for a rapid response by adjusting the translation priority according to urgency. Some or all of the above processing in the real-time translation unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the real-time translation unit can input the urgency level into the generating AI, and the generating AI can adjust the translation priority based on that urgency level.

[0047] The real-time translation unit can select the optimal translation method by referring to the medical professional's past medical history during real-time translation. For example, the real-time translation unit can refer to the medical professional's past medical records and adjust the frequency of use of technical terms. For example, the real-time translation unit can prioritize the translation of relevant information based on the medical professional's past medical history. The real-time translation unit can also consider the medical professional's past medical history and select appropriate medical terms for translation. This allows the optimal translation method to be selected by referring to the medical professional's past medical history. Some or all of the above processing in the real-time translation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the real-time translation unit can input the medical professional's past medical history into a generation AI, and the generation AI can select the optimal translation method based on that history.

[0048] The real-time translation unit can prioritize highly relevant translations by considering the patient's geographical location during real-time translation. For example, if the patient is in a specific region, the real-time translation unit will prioritize translating medical information for that region. For example, if the patient is traveling, the real-time translation unit can prioritize translating medical information for the travel destination. Also, if the patient is at home, the real-time translation unit can prioritize translating information about nearby medical facilities. In this way, by considering the patient's geographical location, highly relevant information can be provided preferentially. Some or all of the above processing in the real-time translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the real-time translation unit can input the patient's geographical location information into a generative AI, and the generative AI can prioritize highly relevant translations based on that information.

[0049] The real-time translation unit can improve translation accuracy by referring to relevant medical literature during real-time translation. For example, the real-time translation unit can improve translation accuracy by referring to the latest medical literature during real-time translation. For example, the real-time translation unit can improve translation accuracy by referring to past medical literature. In addition, the real-time translation unit can improve translation accuracy by referring to relevant academic papers. Thus, the accuracy of translation is improved by referring to relevant medical literature. Some or all of the above processing in the real-time translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the real-time translation unit can input relevant medical literature into a generative AI, and the generative AI can perform translation based on that literature.

[0050] The multilingual support unit can select the optimal language by referring to the patient's past medical history when providing multilingual support. For example, the multilingual support unit can refer to the patient's past medical records and select the most frequently used language. For example, based on the patient's past medical history, the multilingual support unit can select a language that prioritizes the translation of relevant information. The multilingual support unit can also consider the patient's past treatment history and select a language that includes appropriate medical terminology. In this way, the optimal language can be selected by referring to the patient's past medical history. Some or all of the above processing in the multilingual support unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the multilingual support unit can input the patient's past medical history into a generation AI, and the generation AI can select the optimal language based on that history.

[0051] The multilingual support unit can apply different language support algorithms to each medical field when handling multiple languages. For example, the multilingual support unit can apply a language support algorithm specifically for internal medicine to internal medicine terminology. For example, the multilingual support unit can apply a language support algorithm specifically for surgery to surgical terminology. Furthermore, the multilingual support unit can apply a language support algorithm specifically for pediatrics terminology. By applying different language support algorithms to each medical field, the accuracy of the translation is improved. Some or all of the above processing in the multilingual support unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the multilingual support unit can input different language support algorithms for each medical field into a generative AI, and the generative AI can translate the terminology based on that algorithm.

[0052] The multilingual support unit can prioritize the most relevant language when providing multilingual support, taking into account the patient's geographical location. For example, if the patient is in a specific region, the multilingual support unit can prioritize the language of that region. For example, if the patient is traveling, the multilingual support unit can prioritize the language of the travel destination. Furthermore, if the patient is at home, the multilingual support unit can prioritize the language of nearby medical institutions. This allows for the provision of more relevant information by considering the patient's geographical location. Some or all of the above processing in the multilingual support unit may be performed using or without a generative AI. For example, the multilingual support unit can input the patient's geographical location information into a generative AI, which can then prioritize the most relevant language based on that information.

[0053] The multilingual support unit can improve the accuracy of language support by referring to relevant medical literature during multilingual support. For example, the multilingual support unit can improve the accuracy of language support by referring to the latest medical literature during multilingual support. For example, the multilingual support unit can improve the accuracy of language support by referring to past medical literature. In addition, the multilingual support unit can improve the accuracy of language support by referring to relevant academic papers. Thus, the accuracy of language support is improved by referring to relevant medical literature. Some or all of the above processing in the multilingual support unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the multilingual support unit can input relevant medical literature into a generation AI, and the generation AI can perform language support based on that literature.

[0054] The drug information analysis unit can select the optimal analysis method by referring to the patient's past drug use history during drug information analysis. For example, the drug information analysis unit can refer to the patient's past drug use history and prioritize the analysis of the most frequently used drugs. For example, the drug information analysis unit can prioritize the analysis of relevant drug information based on the patient's past drug use history. Furthermore, the drug information analysis unit can select and analyze appropriate drug information considering the patient's past drug use history. In this way, the optimal analysis method can be selected by referring to the patient's past drug use history. Some or all of the above processing in the drug information analysis unit may be performed using a generating AI, or it may be performed without using a generating AI. For example, the drug information analysis unit can input the patient's past drug use history into a generating AI, and the generating AI can select the optimal analysis method based on that history.

[0055] The drug information analysis unit can apply different analysis algorithms to each drug component during drug information analysis. For example, the drug information analysis unit can apply an analysis algorithm specifically for antibiotics to the components of antibiotics. For example, the drug information analysis unit can apply an analysis algorithm specifically for analgesics to the components of analgesics. Furthermore, the drug information analysis unit can apply an analysis algorithm specifically for antiviral drugs to the components of antiviral drugs. By applying different analysis algorithms to each drug component, the accuracy of the analysis is improved. Some or all of the above processing in the drug information analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the drug information analysis unit can input different analysis algorithms for each drug component into the generation AI, and the generation AI can analyze the drug information based on that algorithm.

[0056] The drug information analysis unit can prioritize the analysis of highly relevant drug information by considering the patient's geographical location during drug information analysis. For example, if the patient is in a specific region, the drug information analysis unit will prioritize the analysis of drug information for that region. For example, if the patient is traveling, the drug information analysis unit can prioritize the analysis of drug information for the travel destination. Furthermore, if the patient is at home, the drug information analysis unit can prioritize the analysis of drug information for nearby medical institutions. In this way, by considering the patient's geographical location, highly relevant information can be provided preferentially. Some or all of the above processing in the drug information analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the drug information analysis unit can input the patient's geographical location information into a generating AI, and the generating AI can prioritize the analysis of highly relevant drug information based on that information.

[0057] The drug information analysis unit can improve the accuracy of its analysis by referring to relevant medical literature during drug information analysis. For example, the drug information analysis unit can improve the accuracy of its analysis by referring to the latest medical literature during drug information analysis. For example, the drug information analysis unit can improve the accuracy of its analysis by referring to past medical literature. In addition, the drug information analysis unit can improve the accuracy of its analysis by referring to relevant academic papers. Thus, the accuracy of the analysis is improved by referring to relevant medical literature. Some or all of the above processing in the drug information analysis unit may be performed using a generating AI, or it may be performed without using a generating AI. For example, the drug information analysis unit can input relevant medical literature into a generating AI, and the generating AI can analyze drug information based on that literature.

[0058] The drug information input unit can select the optimal input method by referring to the patient's past drug use history when inputting drug information. For example, the drug information input unit can refer to the patient's past drug use history and automatically display the most frequently used drug as a candidate. For example, the drug information input unit can prioritize inputting relevant drug information based on the patient's past drug use history. Furthermore, the drug information input unit can select and input appropriate drug information considering the patient's past drug use history. In this way, the optimal input method can be selected by referring to the patient's past drug use history. Some or all of the above processing in the drug information input unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the drug information input unit can input the patient's past drug use history into a generation AI, and the generation AI can select the optimal input method based on that history.

[0059] The drug information input unit can prioritize inputting highly relevant drug information by considering the patient's geographical location when inputting drug information. For example, if the patient is in a specific region, the drug information input unit will prioritize inputting drug information for that region. For example, if the patient is traveling, the drug information input unit can prioritize inputting drug information for the travel destination. Also, if the patient is at home, the drug information input unit can prioritize inputting drug information for nearby medical institutions. In this way, highly relevant information can be prioritized by considering the patient's geographical location. Some or all of the above processing in the drug information input unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the drug information input unit can input the patient's geographical location information into a generation AI, and the generation AI can prioritize inputting highly relevant drug information based on that information.

[0060] The information provision unit can select the optimal method of information provision by referring to the patient's past medical history when providing information. For example, the information provision unit can refer to the patient's past medical records and prioritize providing the most frequently used information. For example, the information provision unit can prioritize providing relevant information based on the patient's past medical history. The information provision unit can also consider the patient's past treatment history and select and provide appropriate medical information. In this way, the optimal method of information provision can be selected by referring to the patient's past medical history. Some or all of the above processing in the information provision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the information provision unit can input the patient's past medical history into a generating AI, and the generating AI can select the optimal method of information provision based on that history.

[0061] The information provision unit can prioritize providing highly relevant information by considering the patient's geographical location when providing information. For example, if the patient is in a specific region, the information provision unit can prioritize providing medical information for that region. For example, if the patient is traveling, the information provision unit can prioritize providing medical information for the travel destination. Also, if the patient is at home, the information provision unit can prioritize providing information on nearby medical institutions. In this way, highly relevant information can be prioritized by considering the patient's geographical location. Some or all of the above processing in the information provision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the information provision unit can input the patient's geographical location information into a generating AI, and the generating AI can prioritize providing highly relevant information based on that information.

[0062] The emergency response unit can select the optimal response method by referring to the patient's past medical history during an emergency. For example, the emergency response unit can refer to the patient's past medical records to select the most appropriate emergency response method. For example, the emergency response unit can select relevant emergency response methods based on the patient's past medical history. The emergency response unit can also consider the patient's past treatment history to select an appropriate emergency response method. In this way, the optimal response method can be selected by referring to the patient's past medical history. Some or all of the above processing in the emergency response unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the emergency response unit can input the patient's past medical history into a generation AI, and the generation AI can select the optimal response method based on that history.

[0063] The emergency response unit can prioritize highly relevant responses during an emergency by considering the patient's geographical location. For example, if the patient is in a specific region, the emergency response unit can prioritize emergency response methods for that region. For example, if the patient is traveling, the emergency response unit can prioritize emergency response methods for the travel destination. Also, if the patient is at home, the emergency response unit can prioritize emergency response methods for nearby medical facilities. In this way, by considering the patient's geographical location, highly relevant responses can be prioritized. Some or all of the above processing in the emergency response unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emergency response unit can input the patient's geographical location information into a generative AI, and the generative AI can prioritize highly relevant responses based on that information.

[0064] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0065] The medical translation system can also include a health monitoring unit to monitor the patient's health status. This unit can collect the patient's vital signs and health data in real time and provide it to medical professionals. For example, it can collect data such as the patient's heart rate, blood pressure, and body temperature, and send alerts to medical professionals if abnormalities are detected. Furthermore, the health monitoring unit can record the patient's health data over the long term and track changes in their health status. This allows medical professionals to more accurately understand the patient's health status and provide appropriate treatment. In addition, the health monitoring unit can analyze the patient's health data and provide preventative advice. For example, based on the patient's data, it can provide advice on improving lifestyle habits and maintaining health.

[0066] The medical translation system can also include a medical history management unit that manages the patient's medical history. This unit can centrally manage the patient's past medical records and treatment history and provide it to medical professionals. For example, it can refer to the patient's past medical records and provide information related to their current symptoms and treatment. Furthermore, the medical history management unit can analyze the patient's treatment history and propose the most suitable treatment method. This allows medical professionals to provide more appropriate treatment, taking into account the patient's past treatment history. Additionally, the medical history management unit can share the patient's medical history with other medical institutions. For example, it can quickly provide past medical records when a patient seeks treatment at another medical institution.

[0067] The medical translation system can also include a lifestyle management unit to manage patients' lifestyle habits. This unit can collect data on patients' lifestyle habits, such as diet, exercise, and sleep, and provide this data to medical professionals. For example, it can collect data on patients' diet, exercise levels, and sleep duration to identify factors that affect their health. Furthermore, the lifestyle management unit can provide advice to improve patients' lifestyle habits. This allows patients to maintain healthy lifestyles and contribute to disease prevention and health maintenance. Additionally, the lifestyle management unit can record patients' lifestyle data over the long term and track changes in their health. This allows medical professionals to understand changes in patients' lifestyles and provide appropriate advice.

[0068] The medical translation system may also include a nutrition assessment unit that evaluates the patient's nutritional status. This unit can assess the patient's nutritional status and provide this information to healthcare professionals. For example, it can evaluate the patient's diet and nutrient intake to ensure nutritional balance. Furthermore, based on the patient's nutritional status, the unit can provide advice for nutritional supplementation and dietary improvements. This allows patients to receive appropriate nutrition and maintain their health. Additionally, the nutrition assessment unit can record the patient's nutritional status over the long term and track changes. This allows healthcare professionals to understand changes in the patient's nutritional status and provide appropriate advice.

[0069] The medical translation system may also include an exercise assessment unit that evaluates the patient's exercise status. This unit can assess the patient's exercise status and provide this information to medical professionals. For example, it can evaluate the patient's exercise volume and habits to confirm whether appropriate exercise is being performed. Furthermore, based on the patient's exercise status, the unit can provide suggestions for exercise programs and advice for improving exercise habits. This allows patients to exercise appropriately and maintain their health. Additionally, the exercise assessment unit can record the patient's exercise status over the long term and track changes in their exercise status. This allows medical professionals to understand changes in the patient's exercise status and provide appropriate advice.

[0070] The medical translation system may also include a sleep assessment unit that evaluates the patient's sleep state. This unit can assess the patient's sleep state and provide this information to medical professionals. For example, it can evaluate the patient's sleep duration and quality to confirm whether they are getting adequate sleep. Furthermore, the sleep assessment unit can provide advice for improving sleep based on the patient's sleep state. This allows the patient to get adequate sleep and maintain their health. Additionally, the sleep assessment unit can record the patient's sleep state over the long term and track changes in sleep patterns. This allows medical professionals to understand changes in the patient's sleep state and provide appropriate advice.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The translation department is responsible for facilitating communication between patients and medical professionals. For example, it can use generative AI to translate patients' statements in real time and convey them to medical professionals. When a patient describes their symptoms, the generative AI can instantly translate what they say and convey it to the medical professional. Step 2: The Specialized Terminology Translation Department is responsible for accurately translating medical terminology translated by the Translation Department. For example, it can use generative AI to accurately translate medical terminology and communicate it to medical professionals. By accurately translating medical terminology, it facilitates smoother communication in medical settings. Step 3: The Real-Time Translation Department is responsible for providing content translated by the Specialized Terminology Translation Department in real time. For example, it instantly provides content translated using generative AI to support emergency communication. When a patient describes their symptoms in an emergency, the generative AI can instantly translate that content and convey it to medical professionals. Step 4: The Multilingual Support Department is responsible for translating the content provided by the Real-Time Translation Department into multiple languages. For example, it uses generative AI to support multiple languages ​​and facilitate communication between patients and medical professionals who speak different languages. By supporting multiple languages ​​such as English, Chinese, and Spanish, it can serve patients from various countries. Step 5: The Drug Information Analysis Department is responsible for analyzing drug interactions based on information provided by the Multilingual Support Department. For example, it uses a generating AI to analyze the ingredients, effects, and side effects of medications brought in by patients and provides advice on drug interactions with other medications. When information on medications brought in by patients is entered, the generating AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications.

[0073] (Example of form 2) The medical translation system according to an embodiment of the present invention is a system that utilizes generative AI to enable effective communication between patients and medical professionals. In particular, it allows foreign visitors to Japan to receive medical care smoothly and to take their medication with peace of mind, as it provides explanations of medications and information about drug interactions with medications brought from other countries. Specifically, it consists of the following steps. First, a medical translation service using generative AI is provided to facilitate communication between patients and medical professionals. This service supports communication between patients and doctors, nurses, and medical staff, enabling the exchange of accurate medical information. For example, when a patient describes their symptoms, the generative AI can translate the content in real time and convey it to the medical professional. Next, the generative AI performs accurate translation of medical terminology. Medical translation often involves specialized terminology and medical concepts, requiring more specialized knowledge than general translation tools. By using generative AI, accurate translation of specialized terminology becomes possible, facilitating smooth communication in medical settings. Furthermore, the medical translation service utilizing generative AI can operate in real time. This is particularly useful for communication in urgent situations, enabling a rapid response. For example, when a patient describes their symptoms in an emergency, the generative AI can instantly translate the content and convey it to the medical professional. Furthermore, the medical translation service supports multiple languages. This facilitates communication with multinational medical institutions and patients, and smooths communication between patients and medical professionals who speak different languages. For example, by supporting multiple languages ​​such as English, Chinese, and Spanish, it can serve patients from various countries. In addition, the generating AI can also inform patients about drug interactions with other medications they bring from other countries. When information about the medications a patient has brought is entered, the generating AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications. This allows patients to take their medication with peace of mind. This system facilitates communication between patients and medical professionals, allowing foreign visitors to Japan to receive medical care smoothly. Moreover, because it provides explanations of medications and information about drug interactions with medications brought from other countries, patients can take their medication with confidence.For example, when a patient inputs information about medications they have brought with them, the generated AI analyzes the drug's ingredients, effects, and side effects, and provides advice on potential interactions with other medications. This allows patients to take their medication with peace of mind. Thus, the medical translation system facilitates communication between patients and medical professionals, enabling foreign visitors to Japan to receive medical care smoothly. Furthermore, it provides information about medications and potential interactions with medications brought from other countries, allowing patients to take their medication with confidence.

[0074] The medical translation system according to this embodiment comprises a translation unit, a specialized terminology translation unit, a real-time translation unit, a multilingual support unit, and a drug information analysis unit. The translation unit is responsible for facilitating communication between patients and medical professionals. For example, the translation unit can use a generative AI to translate a patient's statements in real time and convey them to medical professionals. For example, when a patient describes their symptoms, the generative AI can instantly translate the content and convey it to medical professionals. The specialized terminology translation unit is responsible for accurately translating medical terminology translated by the translation unit. For example, the specialized terminology translation unit can use a generative AI to accurately translate medical terminology and convey it to medical professionals. For example, by accurately translating medical terminology, it facilitates communication in medical settings. The real-time translation unit is responsible for providing the content translated by the specialized terminology translation unit in real time. For example, the real-time translation unit instantly provides the content translated using a generative AI to support communication in emergencies. For example, when a patient describes their symptoms in an emergency, the generative AI can instantly translate the content and convey it to medical professionals. The Multilingual Support Department is responsible for translating the content provided by the Real-Time Translation Department into multiple languages. For example, the Multilingual Support Department uses generative AI to support multiple languages, facilitating communication between patients and medical professionals who speak different languages. By supporting multiple languages, such as English, Chinese, and Spanish, it can accommodate patients from various countries. The Drug Information Analysis Department analyzes drug interactions based on the content provided by the Multilingual Support Department. For example, the Drug Information Analysis Department uses generative AI to analyze the ingredients, effects, and side effects of medications brought by patients, and provides advice on drug interactions with other medications. For instance, when information on medications brought by a patient is entered, the generative AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications. This allows the medical translation system to facilitate smooth communication between patients and medical professionals and enable the exchange of accurate medical information.

[0075] The translation department is responsible for facilitating communication between patients and healthcare professionals. For example, it can use generative AI to translate patient statements in real time and convey them to healthcare professionals. Specifically, the generative AI utilizes natural language processing technology to recognize patient speech and convert it into text. It then translates the text into the target language and provides it to healthcare professionals via voice or text. For instance, when a patient describes their symptoms, the generative AI can instantly translate the content and convey it to the healthcare professional. The generative AI achieves accurate translation by understanding the context of the patient's statements and selecting appropriate medical terminology. Furthermore, the translation department can translate not only patient statements but also instructions and questions from healthcare professionals and convey them to the patient. This enables two-way communication between patients and healthcare professionals, improving the accuracy of diagnosis and treatment. Additionally, the translation department can prevent misunderstandings by considering the patient's cultural background and linguistic nuances and selecting appropriate expressions. For example, avoiding culturally sensitive expressions and phrases can enhance patient comfort. This allows the translation department to facilitate communication between patients and medical professionals and support the exchange of accurate medical information.

[0076] The Specialized Terminology Translation Department is responsible for accurately translating medical terminology translated by the Translation Department. For example, the Specialized Terminology Translation Department can use generative AI to accurately translate medical terminology and communicate it to medical professionals. Specifically, the generative AI consults medical-specific dictionaries and databases to understand the precise meaning and usage of specialized terminology. For instance, accurate translation of medical terminology facilitates smoother communication in medical settings. The generative AI learns from large amounts of medical data using machine learning algorithms to understand the context of medical terminology and provide appropriate translations. This allows the Specialized Terminology Translation Department to accurately translate advanced terminology and abbreviations used by medical professionals, preventing misunderstandings. Furthermore, the Specialized Terminology Translation Department can maintain a list of specific terminology and abbreviations used by medical professionals, ensuring that the information is always up-to-date. This improves the accuracy of communication in medical settings and enhances the quality of diagnosis and treatment. In addition to translating medical terminology, the Specialized Terminology Translation Department can also convert it into language easily understood by patients. This allows patients to accurately understand their medical condition and treatment plan, enabling them to make appropriate decisions.

[0077] The Real-Time Translation Department provides content translated by the Specialized Terminology Translation Department in real time. For example, the Real-Time Translation Department instantly provides content translated using generative AI, supporting communication in emergencies. Specifically, the generative AI has high processing capabilities and can instantly provide translated content in audio or text format. For example, when a patient describes their symptoms in an emergency, the generative AI can instantly translate that content and convey it to medical professionals. The generative AI combines speech recognition and natural language processing technologies to analyze the patient's statements in real time and provide translation results. This enables the Real-Time Translation Department to respond quickly in emergencies and ensure patient safety. Furthermore, the Real-Time Translation Department can also translate instructions and questions from medical professionals to patients in real time and convey them to the patients. This facilitates smooth two-way communication in emergencies and enables quick and appropriate responses. In addition, to continuously improve the accuracy of translation results, the Real-Time Translation Department regularly updates the generative AI's training data to reflect the latest medical information. This allows the Real-Time Translation Department to consistently provide highly accurate translation results and support communication in medical settings.

[0078] The Multilingual Support Department is responsible for translating content provided by the Real-Time Translation Department into multiple languages. For example, the Multilingual Support Department uses generative AI to support multiple languages, facilitating communication between patients and medical professionals who speak different languages. Specifically, the generative AI utilizes multilingual natural language processing technology to support multiple languages, such as English, Chinese, and Spanish. By supporting multiple languages, it can accommodate patients from various countries. The generative AI learns from a large amount of multilingual data using machine learning algorithms to understand the grammar, vocabulary, and cultural background of each language and provide appropriate translations. This allows the Multilingual Support Department to facilitate communication between patients and medical professionals who speak different languages, preventing misunderstandings and errors in medical settings. Furthermore, by supporting communication in the patient's native language, the Multilingual Support Department can enhance patient confidence and encourage active participation in treatment. In addition, the Multilingual Support Department can provide multilingual translations of specialized terminology and abbreviations used by medical professionals, improving the accuracy of communication in medical settings. This allows the multilingual support unit to facilitate communication between patients and medical professionals who speak different languages, enabling accurate information exchange in medical settings.

[0079] The Drug Information Analysis Department is responsible for analyzing drug interactions based on information provided by the Multilingual Support Department. For example, the Drug Information Analysis Department uses generative AI to analyze the ingredients, effects, and side effects of medications brought in by patients, and provides advice on drug interactions with other medications. Specifically, the generative AI refers to a drug ingredient database and analyzes the ingredients, effects, and side effects of each drug. For instance, when information on medications brought in by a patient is input, the generative AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications. The generative AI learns data on drug ingredients, effects, and side effects, and uses machine learning algorithms to evaluate the risks of drug interactions and drug combinations. This allows the Drug Information Analysis Department to ensure the safety of medications patients are taking and support appropriate treatment. Furthermore, the Drug Information Analysis Department can provide individualized advice by considering the patient's medical history and allergy information. This enables the selection of optimal medications according to the patient's health condition, minimizing the risks associated with side effects and drug interactions. Furthermore, the Drug Information Analysis Department can provide healthcare professionals with the latest information on drug interactions, thereby improving the quality of diagnosis and treatment. This allows the Drug Information Analysis Department to support accurate information exchange between patients and healthcare professionals, leading to safer and more effective treatment.

[0080] The drug information input unit can input information about medications brought by the patient. For example, the drug information input unit can input information such as the name, ingredients, and dosage of the medication brought by the patient. For example, the drug information input unit provides an interface for inputting information about medications brought by the patient, making it easy for the patient to input the information. This makes it possible to analyze drug interactions by inputting information about the medications brought by the patient. Some or all of the above processing in the drug information input unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the drug information input unit can input information about medications brought by the patient into a generating AI, and the generating AI can analyze that information.

[0081] The information provision unit can provide information analyzed by the generating AI. For example, the information provision unit can provide information such as drug components, effects, and side effects analyzed by the generating AI. For example, the information provision unit can provide information analyzed by the generating AI to patients and medical professionals, supporting accurate information sharing. This facilitates information sharing between patients and medical professionals by providing information analyzed by the generating AI. Some or all of the above processing in the information provision unit may be performed using the generating AI or without it. For example, the information provision unit can provide information analyzed by the generating AI through web applications or mobile applications.

[0082] The Emergency Response Unit can support emergency response. For example, the Emergency Response Unit can use generative AI to provide emergency response methods and support a rapid response. For example, the Emergency Response Unit can immediately provide necessary information in an emergency, enabling medical professionals to respond quickly. This enables a rapid response by supporting emergency response. Some or all of the above-described processes in the Emergency Response Unit may be performed using generative AI or not. For example, the Emergency Response Unit may use generative AI to provide emergency response methods, enabling medical professionals to respond quickly.

[0083] The translation unit can estimate the patient's emotions and adjust the translation's expression based on those estimated emotions. For example, if the patient is feeling anxious, the generation AI can use gentle language in the translation. For example, if the patient is relaxed, the generation AI can provide a translation that includes detailed explanations. If the patient is tense, the generation AI can provide a translation that is concise and easy to understand. This allows for more appropriate communication by adjusting the translation's expression according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the translation unit may be performed using or without the generation AI. For example, the translation unit can input the patient's emotions into the generation AI, which can then adjust the translation's expression based on those emotions.

[0084] The translation unit can select the optimal translation method by referring to the patient's past medical history during translation. For example, the translation unit can refer to the patient's past medical records and adjust the frequency of use of technical terms. For example, the translation unit can prioritize the translation of relevant information based on the patient's past medical history. The translation unit can also consider the patient's past treatment history and select appropriate medical terms for translation. In this way, the optimal translation method can be selected by referring to the patient's past medical history. Some or all of the above processing in the translation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the translation unit can input the patient's past medical history into a generation AI, and the generation AI can select the optimal translation method based on that history.

[0085] The translation unit can adjust the level of detail in the translation based on the patient's current health condition. For example, if the patient is in a critical condition, the translation unit will prioritize translating concise and important information. For example, if the patient is in a stable condition, the translation unit can provide a translation that includes detailed explanations. Furthermore, if the patient is in the recovery phase, the translation unit can provide detailed information regarding rehabilitation. This allows for the provision of more appropriate information by adjusting the level of detail in the translation according to the patient's current health condition. Some or all of the above processing in the translation unit may be performed using or without a generative AI. For example, the translation unit can input the patient's current health condition into the generative AI, which can then adjust the level of detail in the translation based on that condition.

[0086] The translation unit can estimate the patient's emotions and determine translation priorities based on the estimated emotions. For example, if the patient is feeling anxious, the generative AI will prioritize translating information that provides reassurance. For example, if the patient is relaxed, the generative AI can prioritize translating detailed medical information. Also, if the patient is stressed, the generative AI can translate important information concisely. This allows for more appropriate information to be provided by determining translation priorities according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using or without the generative AI. For example, the translation unit can input the patient's emotions into the generative AI, which can then determine translation priorities based on those emotions.

[0087] The translation unit can prioritize highly relevant translations by considering the patient's geographical location during the translation process. For example, if the patient is in a specific region, the translation unit will prioritize translating medical information for that region. For example, if the patient is traveling, the translation unit can prioritize translating medical information for the travel destination. Also, if the patient is at home, the translation unit can prioritize translating information about nearby medical facilities. This allows the system to prioritize providing highly relevant information by considering the patient's geographical location. Some or all of the above processing in the translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the translation unit can input the patient's geographical location information into a generative AI, which can then prioritize highly relevant translations based on that information.

[0088] The translation unit can analyze the patient's social media activity during translation and translate relevant information. For example, the translation unit can translate relevant medical information based on health information shared by the patient on social media. For example, the translation unit can prioritize translating information from medical professionals the patient follows on social media. The translation unit can also translate information related to medical topics the patient has shown interest in on social media. This allows the unit to provide relevant information by analyzing the patient's social media activity. Some or all of the above processing in the translation unit may be performed using or without generative AI. For example, the translation unit can input the patient's social media activity into a generative AI, which can then translate relevant information based on that activity.

[0089] The technical term translation unit can estimate the patient's emotions and adjust the translation method of technical terms based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI will translate the technical terms into simple language. For example, if the patient is relaxed, the generating AI can provide a translation that includes detailed explanations. Also, if the patient is tense, the generating AI can translate the technical terms using concise and easy-to-understand expressions. This allows for the provision of more appropriate information by adjusting the translation method of technical terms according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the technical term translation unit may be performed using or without a generating AI. For example, the technical term translation unit can input the patient's emotions into a generating AI, and the generating AI can adjust the translation method of technical terms based on those emotions.

[0090] The specialized terminology translation unit can select the optimal translation method when translating specialized terminology by referring to the medical professional's past medical history. For example, the specialized terminology translation unit can adjust the frequency of use of specialized terminology by referring to the medical professional's past medical records. For example, the specialized terminology translation unit can prioritize the translation of relevant information based on the medical professional's past medical history. Furthermore, the specialized terminology translation unit can select and translate appropriate medical terms by considering the medical professional's past medical history. This allows the unit to select the optimal translation method by referring to the medical professional's past medical history. Some or all of the above processing in the specialized terminology translation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the specialized terminology translation unit can input the medical professional's past medical history into a generation AI, and the generation AI can select the optimal translation method based on that history.

[0091] The specialized terminology translation unit can apply different translation algorithms to each medical field when translating specialized terminology. For example, the specialized terminology translation unit can apply an internal medicine-specific translation algorithm to internal medicine terminology. For example, the specialized terminology translation unit can apply a surgical-specific translation algorithm to surgical terminology. Furthermore, the specialized terminology translation unit can apply a pediatrics-specific translation algorithm to pediatric terminology. By applying different translation algorithms to each medical field, the accuracy of the translation is improved. Some or all of the above processing in the specialized terminology translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the specialized terminology translation unit can input different translation algorithms for each medical field into a generative AI, and the generative AI can translate the specialized terminology based on that algorithm.

[0092] The technical term translation unit can estimate the patient's emotions and determine the priority of technical term translations based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI will prioritize translating technical terms that provide reassurance. For example, if the patient is relaxed, the generating AI can prioritize translating detailed medical information. Also, if the patient is tense, the generating AI can translate important information concisely. This allows for more appropriate information to be provided by determining the priority of technical term translations according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the technical term translation unit may be performed using or without a generating AI. For example, the technical term translation unit can input the patient's emotions into a generating AI, which can then determine the priority of technical term translations based on those emotions.

[0093] The specialized terminology translation unit can prioritize highly relevant translations by considering the geographical location of medical institutions when translating specialized terminology. For example, if a medical institution is located in a specific region, the specialized terminology translation unit can prioritize translating medical information for that region. For example, if a medical institution is located in a travel destination, the specialized terminology translation unit can prioritize translating medical information for that destination. Furthermore, if a medical institution is located near a patient's home, the specialized terminology translation unit can prioritize translating information for nearby medical institutions. In this way, by considering the geographical location of medical institutions, highly relevant information can be provided preferentially. Some or all of the above processing in the specialized terminology translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the specialized terminology translation unit can input the geographical location information of medical institutions into a generative AI, and the generative AI can prioritize highly relevant translations based on that information.

[0094] The specialized terminology translation unit can improve the accuracy of its translations by referring to relevant medical literature when translating specialized terms. For example, the specialized terminology translation unit can improve the accuracy of its translations by referring to the latest medical literature when translating specialized terms. For example, the specialized terminology translation unit can improve the accuracy of its translations by referring to past medical literature. In addition, the specialized terminology translation unit can improve the accuracy of its translations by referring to relevant academic papers. Thus, the accuracy of the translation is improved by referring to relevant medical literature. Some or all of the above processes in the specialized terminology translation unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the specialized terminology translation unit can input relevant medical literature into a generative AI, and the generative AI can translate specialized terms based on that literature.

[0095] The real-time translation unit can estimate the patient's emotions and adjust the speed of real-time translation based on the estimated emotions. For example, if the patient is feeling anxious, the generative AI will translate quickly. For example, if the patient is relaxed, the generative AI can provide a translation that includes detailed explanations. Also, if the patient is tense, the generative AI can provide a translation using concise and easy-to-understand language. By adjusting the speed of real-time translation according to the patient's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the real-time translation unit may be performed using the generative AI or not. For example, the real-time translation unit can input the patient's emotions into the generative AI, and the generative AI can adjust the speed of real-time translation based on those emotions.

[0096] The real-time translation unit can adjust the translation priority according to urgency during real-time translation. For example, if the urgency is high, the generating AI will prioritize translating important information. For example, if the urgency is low, the generating AI can produce a translation that includes detailed explanations. Furthermore, if the urgency is moderate, the generating AI can produce a translation using concise and easy-to-understand language. This allows for a rapid response by adjusting the translation priority according to urgency. Some or all of the above processing in the real-time translation unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the real-time translation unit can input the urgency level into the generating AI, and the generating AI can adjust the translation priority based on that urgency level.

[0097] The real-time translation unit can select the optimal translation method by referring to the medical professional's past medical history during real-time translation. For example, the real-time translation unit can refer to the medical professional's past medical records and adjust the frequency of use of technical terms. For example, the real-time translation unit can prioritize the translation of relevant information based on the medical professional's past medical history. The real-time translation unit can also consider the medical professional's past medical history and select appropriate medical terms for translation. This allows the optimal translation method to be selected by referring to the medical professional's past medical history. Some or all of the above processing in the real-time translation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the real-time translation unit can input the medical professional's past medical history into a generation AI, and the generation AI can select the optimal translation method based on that history.

[0098] The real-time translation unit can estimate the patient's emotions and adjust the display method of the real-time translation based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI can provide a simple and easy-to-read display method. For example, if the patient is relaxed, the generating AI can provide a display method that includes detailed information. Also, if the patient is tense, the generating AI can provide a display method that gets straight to the point. This allows for more appropriate information to be provided by adjusting the display method of the real-time translation according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the real-time translation unit may be performed using the generating AI or not. For example, the real-time translation unit can input the patient's emotions into the generating AI, and the generating AI can adjust the display method of the real-time translation based on those emotions.

[0099] The real-time translation unit can prioritize highly relevant translations by considering the patient's geographical location during real-time translation. For example, if the patient is in a specific region, the real-time translation unit will prioritize translating medical information for that region. For example, if the patient is traveling, the real-time translation unit can prioritize translating medical information for the travel destination. Also, if the patient is at home, the real-time translation unit can prioritize translating information about nearby medical facilities. In this way, by considering the patient's geographical location, highly relevant information can be provided preferentially. Some or all of the above processing in the real-time translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the real-time translation unit can input the patient's geographical location information into a generative AI, and the generative AI can prioritize highly relevant translations based on that information.

[0100] The real-time translation unit can improve translation accuracy by referring to relevant medical literature during real-time translation. For example, the real-time translation unit can improve translation accuracy by referring to the latest medical literature during real-time translation. For example, the real-time translation unit can improve translation accuracy by referring to past medical literature. In addition, the real-time translation unit can improve translation accuracy by referring to relevant academic papers. Thus, the accuracy of translation is improved by referring to relevant medical literature. Some or all of the above processing in the real-time translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the real-time translation unit can input relevant medical literature into a generative AI, and the generative AI can perform translation based on that literature.

[0101] The multilingual support unit can estimate the patient's emotions and determine the priority of multilingual support based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI will prioritize language that provides reassurance. For example, if the patient is relaxed, the generating AI will prioritize language containing detailed medical information. Also, if the patient is tense, the generating AI will prioritize language that is concise and easy to understand. This allows for the provision of more appropriate information by determining the priority of multilingual support according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the multilingual support unit may be performed using the generating AI or not. For example, the multilingual support unit can input the patient's emotions into the generating AI, and the generating AI can determine the priority of multilingual support based on those emotions.

[0102] The multilingual support unit can select the optimal language by referring to the patient's past medical history when providing multilingual support. For example, the multilingual support unit can refer to the patient's past medical records and select the most frequently used language. For example, based on the patient's past medical history, the multilingual support unit can select a language that prioritizes the translation of relevant information. The multilingual support unit can also consider the patient's past treatment history and select a language that includes appropriate medical terminology. In this way, the optimal language can be selected by referring to the patient's past medical history. Some or all of the above processing in the multilingual support unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the multilingual support unit can input the patient's past medical history into a generation AI, and the generation AI can select the optimal language based on that history.

[0103] The multilingual support unit can apply different language support algorithms to each medical field when handling multiple languages. For example, the multilingual support unit can apply a language support algorithm specifically for internal medicine to internal medicine terminology. For example, the multilingual support unit can apply a language support algorithm specifically for surgery to surgical terminology. Furthermore, the multilingual support unit can apply a language support algorithm specifically for pediatrics terminology. By applying different language support algorithms to each medical field, the accuracy of the translation is improved. Some or all of the above processing in the multilingual support unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the multilingual support unit can input different language support algorithms for each medical field into a generative AI, and the generative AI can translate the terminology based on that algorithm.

[0104] The multilingual support unit can estimate the patient's emotions and adjust the multilingual display method based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI can provide a simple and highly visible display method. For example, if the patient is relaxed, the generating AI can provide a display method that includes detailed information. Also, if the patient is tense, the generating AI can provide a display method that gets straight to the point. By adjusting the multilingual display method according to the patient's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the multilingual support unit may be performed using the generating AI or not. For example, the multilingual support unit can input the patient's emotions into the generating AI, and the generating AI can adjust the multilingual display method based on those emotions.

[0105] The multilingual support unit can prioritize the most relevant language when providing multilingual support, taking into account the patient's geographical location. For example, if the patient is in a specific region, the multilingual support unit can prioritize the language of that region. For example, if the patient is traveling, the multilingual support unit can prioritize the language of the travel destination. Furthermore, if the patient is at home, the multilingual support unit can prioritize the language of nearby medical institutions. This allows for the provision of more relevant information by considering the patient's geographical location. Some or all of the above processing in the multilingual support unit may be performed using or without a generative AI. For example, the multilingual support unit can input the patient's geographical location information into a generative AI, which can then prioritize the most relevant language based on that information.

[0106] The multilingual support unit can improve the accuracy of language support by referring to relevant medical literature during multilingual support. For example, the multilingual support unit can improve the accuracy of language support by referring to the latest medical literature during multilingual support. For example, the multilingual support unit can improve the accuracy of language support by referring to past medical literature. In addition, the multilingual support unit can improve the accuracy of language support by referring to relevant academic papers. Thus, the accuracy of language support is improved by referring to relevant medical literature. Some or all of the above processing in the multilingual support unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the multilingual support unit can input relevant medical literature into a generation AI, and the generation AI can perform language support based on that literature.

[0107] The drug information analysis unit can estimate the patient's emotions and determine the priority of drug information analysis based on the estimated emotions. For example, if the patient is feeling anxious, the drug information analysis unit's generating AI will prioritize analyzing drug information that provides a sense of security. For example, if the patient is relaxed, the drug information analysis unit's generating AI can prioritize analyzing detailed drug information. Also, if the patient is tense, the drug information analysis unit's generating AI can analyze important drug information concisely. This allows for the provision of more appropriate information by determining the priority of drug information analysis according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the drug information analysis unit may be performed using the generating AI or not. For example, the drug information analysis unit can input the patient's emotions into the generating AI, and the generating AI can determine the priority of drug information analysis based on those emotions.

[0108] The drug information analysis unit can select the optimal analysis method by referring to the patient's past drug use history during drug information analysis. For example, the drug information analysis unit can refer to the patient's past drug use history and prioritize the analysis of the most frequently used drugs. For example, the drug information analysis unit can prioritize the analysis of relevant drug information based on the patient's past drug use history. Furthermore, the drug information analysis unit can select and analyze appropriate drug information considering the patient's past drug use history. In this way, the optimal analysis method can be selected by referring to the patient's past drug use history. Some or all of the above processing in the drug information analysis unit may be performed using a generating AI, or it may be performed without using a generating AI. For example, the drug information analysis unit can input the patient's past drug use history into a generating AI, and the generating AI can select the optimal analysis method based on that history.

[0109] The drug information analysis unit can apply different analysis algorithms to each drug component during drug information analysis. For example, the drug information analysis unit can apply an analysis algorithm specifically for antibiotics to the components of antibiotics. For example, the drug information analysis unit can apply an analysis algorithm specifically for analgesics to the components of analgesics. Furthermore, the drug information analysis unit can apply an analysis algorithm specifically for antiviral drugs to the components of antiviral drugs. By applying different analysis algorithms to each drug component, the accuracy of the analysis is improved. Some or all of the above processing in the drug information analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the drug information analysis unit can input different analysis algorithms for each drug component into the generation AI, and the generation AI can analyze the drug information based on that algorithm.

[0110] The drug information analysis unit can estimate the patient's emotions and adjust the display method of the drug information analysis based on the estimated emotions. For example, if the patient is feeling anxious, the drug information analysis unit's generating AI can provide a simple and highly visible display method. For example, if the patient is relaxed, the drug information analysis unit's generating AI can provide a display method that includes detailed information. Furthermore, if the patient is tense, the drug information analysis unit's generating AI can provide a display method that gets straight to the point. By adjusting the display method of the drug information analysis according to the patient's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the drug information analysis unit may be performed using the generating AI or not. For example, the drug information analysis unit can input the patient's emotions into the generating AI, and the generating AI can adjust the display method of the drug information analysis based on those emotions.

[0111] The drug information analysis unit can prioritize the analysis of highly relevant drug information by considering the patient's geographical location during drug information analysis. For example, if the patient is in a specific region, the drug information analysis unit will prioritize the analysis of drug information for that region. For example, if the patient is traveling, the drug information analysis unit can prioritize the analysis of drug information for the travel destination. Furthermore, if the patient is at home, the drug information analysis unit can prioritize the analysis of drug information for nearby medical institutions. In this way, by considering the patient's geographical location, highly relevant information can be provided preferentially. Some or all of the above processing in the drug information analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the drug information analysis unit can input the patient's geographical location information into a generating AI, and the generating AI can prioritize the analysis of highly relevant drug information based on that information.

[0112] The drug information analysis unit can improve the accuracy of its analysis by referring to relevant medical literature during drug information analysis. For example, the drug information analysis unit can improve the accuracy of its analysis by referring to the latest medical literature during drug information analysis. For example, the drug information analysis unit can improve the accuracy of its analysis by referring to past medical literature. In addition, the drug information analysis unit can improve the accuracy of its analysis by referring to relevant academic papers. Thus, the accuracy of the analysis is improved by referring to relevant medical literature. Some or all of the above processing in the drug information analysis unit may be performed using a generating AI, or it may be performed without using a generating AI. For example, the drug information analysis unit can input relevant medical literature into a generating AI, and the generating AI can analyze drug information based on that literature.

[0113] The drug information input unit can estimate the patient's emotions and adjust the method of inputting drug information based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI can provide a simple interface and minimize the input steps. For example, if the patient is relaxed, the generating AI can provide detailed input options and suggest a customizable input method. Also, if the patient is in a hurry, the generating AI can prioritize voice input to allow for quick drug information input. This allows for more appropriate information to be provided by adjusting the drug information input method according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the drug information input unit may be performed using or without a generating AI. For example, the drug information input unit can input the patient's emotions into the generating AI, and the generating AI can adjust the method of inputting drug information based on those emotions.

[0114] The drug information input unit can select the optimal input method by referring to the patient's past drug use history when inputting drug information. For example, the drug information input unit can refer to the patient's past drug use history and automatically display the most frequently used drug as a candidate. For example, the drug information input unit can prioritize inputting relevant drug information based on the patient's past drug use history. Furthermore, the drug information input unit can select and input appropriate drug information considering the patient's past drug use history. In this way, the optimal input method can be selected by referring to the patient's past drug use history. Some or all of the above processing in the drug information input unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the drug information input unit can input the patient's past drug use history into a generation AI, and the generation AI can select the optimal input method based on that history.

[0115] The drug information input unit can estimate the patient's emotions and determine the priority of drug information input based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI will prioritize inputting drug information that provides a sense of security. For example, if the patient is relaxed, the generating AI will prioritize inputting detailed drug information. Also, if the patient is tense, the generating AI will input important drug information concisely. This allows for the provision of more appropriate information by determining the priority of drug information input according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the drug information input unit may be performed using a generating AI or not. For example, the drug information input unit can input the patient's emotions into a generating AI, and the generating AI can determine the priority of drug information input based on those emotions.

[0116] The drug information input unit can prioritize inputting highly relevant drug information by considering the patient's geographical location when inputting drug information. For example, if the patient is in a specific region, the drug information input unit will prioritize inputting drug information for that region. For example, if the patient is traveling, the drug information input unit can prioritize inputting drug information for the travel destination. Also, if the patient is at home, the drug information input unit can prioritize inputting drug information for nearby medical institutions. In this way, highly relevant information can be prioritized by considering the patient's geographical location. Some or all of the above processing in the drug information input unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the drug information input unit can input the patient's geographical location information into a generation AI, and the generation AI can prioritize inputting highly relevant drug information based on that information.

[0117] The information provision unit can estimate the patient's emotions and adjust the method of information provision based on the estimated emotions. For example, if the patient is feeling anxious, the information provision unit's generating AI can prioritize providing reassuring information. For example, if the patient is relaxed, the information provision unit's generating AI can prioritize providing detailed medical information. Also, if the patient is tense, the information provision unit's generating AI can provide important information concisely. This allows for more appropriate information provision by adjusting the method of information provision according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information provision unit may be performed using a generating AI or not. For example, the information provision unit can input the patient's emotions into a generating AI, and the generating AI can adjust the method of information provision based on those emotions.

[0118] The information provision unit can select the optimal method of information provision by referring to the patient's past medical history when providing information. For example, the information provision unit can refer to the patient's past medical records and prioritize providing the most frequently used information. For example, the information provision unit can prioritize providing relevant information based on the patient's past medical history. The information provision unit can also consider the patient's past treatment history and select and provide appropriate medical information. In this way, the optimal method of information provision can be selected by referring to the patient's past medical history. Some or all of the above processing in the information provision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the information provision unit can input the patient's past medical history into a generating AI, and the generating AI can select the optimal method of information provision based on that history.

[0119] The information provision unit can estimate the patient's emotions and determine the priority of information provision based on the estimated emotions. For example, if the patient is feeling anxious, the information provision unit's generative AI will prioritize providing information that provides reassurance. For example, if the patient is relaxed, the information provision unit's generative AI can prioritize providing detailed medical information. Also, if the patient is tense, the information provision unit's generative AI can provide important information concisely. This allows for more appropriate information provision by determining the priority of information provision according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information provision unit may be performed using the generative AI or not. For example, the information provision unit can input the patient's emotions into the generative AI, and the generative AI can determine the priority of information provision based on those emotions.

[0120] The information provision unit can prioritize providing highly relevant information by considering the patient's geographical location when providing information. For example, if the patient is in a specific region, the information provision unit can prioritize providing medical information for that region. For example, if the patient is traveling, the information provision unit can prioritize providing medical information for the travel destination. Also, if the patient is at home, the information provision unit can prioritize providing information on nearby medical institutions. In this way, highly relevant information can be prioritized by considering the patient's geographical location. Some or all of the above processing in the information provision unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the information provision unit can input the patient's geographical location information into a generating AI, and the generating AI can prioritize providing highly relevant information based on that information.

[0121] The emergency response unit can estimate the patient's emotions and adjust the emergency response method based on the estimated emotions. For example, if the patient is feeling anxious, the generating AI can provide a reassuring emergency response method. For example, if the patient is relaxed, the generating AI can provide a detailed emergency response method. Also, if the patient is tense, the generating AI can provide a concise and easy-to-understand emergency response method. This allows for a more appropriate response by adjusting the emergency response method according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emergency response unit may be performed using the generating AI or not. For example, the emergency response unit can input the patient's emotions into the generating AI, and the generating AI can adjust the emergency response method based on those emotions.

[0122] The emergency response unit can select the optimal response method by referring to the patient's past medical history during an emergency. For example, the emergency response unit can refer to the patient's past medical records to select the most appropriate emergency response method. For example, the emergency response unit can select relevant emergency response methods based on the patient's past medical history. The emergency response unit can also consider the patient's past treatment history to select an appropriate emergency response method. In this way, the optimal response method can be selected by referring to the patient's past medical history. Some or all of the above processing in the emergency response unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the emergency response unit can input the patient's past medical history into a generation AI, and the generation AI can select the optimal response method based on that history.

[0123] The emergency response unit can estimate the patient's emotions and determine the priority of emergency responses based on those emotions. For example, if the patient is feeling anxious, the generation AI will prioritize emergency responses that provide reassurance. For example, if the patient is relaxed, the generation AI will prioritize detailed emergency responses. If the patient is tense, the generation AI will perform important emergency responses concisely. This allows for more appropriate responses by determining the priority of emergency responses according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emergency response unit may be performed using or without the generation AI. For example, the emergency response unit can input the patient's emotions into the generation AI, which can then determine the priority of emergency responses based on those emotions.

[0124] The emergency response unit can prioritize highly relevant responses during an emergency by considering the patient's geographical location. For example, if the patient is in a specific region, the emergency response unit can prioritize emergency response methods for that region. For example, if the patient is traveling, the emergency response unit can prioritize emergency response methods for the travel destination. Also, if the patient is at home, the emergency response unit can prioritize emergency response methods for nearby medical facilities. In this way, by considering the patient's geographical location, highly relevant responses can be prioritized. Some or all of the above processing in the emergency response unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emergency response unit can input the patient's geographical location information into a generative AI, and the generative AI can prioritize highly relevant responses based on that information.

[0125] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0126] The medical translation system can also include a health monitoring unit to monitor the patient's health status. This unit can collect the patient's vital signs and health data in real time and provide it to medical professionals. For example, it can collect data such as the patient's heart rate, blood pressure, and body temperature, and send alerts to medical professionals if abnormalities are detected. Furthermore, the health monitoring unit can record the patient's health data over the long term and track changes in their health status. This allows medical professionals to more accurately understand the patient's health status and provide appropriate treatment. In addition, the health monitoring unit can analyze the patient's health data and provide preventative advice. For example, based on the patient's data, it can provide advice on improving lifestyle habits and maintaining health.

[0127] The medical translation system can also include a medical history management unit that manages the patient's medical history. This unit can centrally manage the patient's past medical records and treatment history and provide it to medical professionals. For example, it can refer to the patient's past medical records and provide information related to their current symptoms and treatment. Furthermore, the medical history management unit can analyze the patient's treatment history and propose the most suitable treatment method. This allows medical professionals to provide more appropriate treatment, taking into account the patient's past treatment history. Additionally, the medical history management unit can share the patient's medical history with other medical institutions. For example, it can quickly provide past medical records when a patient seeks treatment at another medical institution.

[0128] The medical translation system can also include a lifestyle management unit to manage patients' lifestyle habits. This unit can collect data on patients' lifestyle habits, such as diet, exercise, and sleep, and provide this data to medical professionals. For example, it can collect data on patients' diet, exercise levels, and sleep duration to identify factors that affect their health. Furthermore, the lifestyle management unit can provide advice to improve patients' lifestyle habits. This allows patients to maintain healthy lifestyles and contribute to disease prevention and health maintenance. Additionally, the lifestyle management unit can record patients' lifestyle data over the long term and track changes in their health. This allows medical professionals to understand changes in patients' lifestyles and provide appropriate advice.

[0129] The medical translation system may also include a psychological assessment unit to evaluate the patient's psychological state. This unit can assess the patient's psychological state and provide this information to medical professionals. For example, it can assess the patient's stress levels, anxiety, and depressive states, and notify medical professionals if psychological support is needed. Furthermore, the unit can provide advice on relaxation and stress management based on the patient's psychological state. This allows patients to maintain their psychological health and reduce stress and anxiety. Additionally, the unit can record the patient's psychological state over the long term and track psychological changes. This allows medical professionals to understand changes in the patient's psychological state and provide appropriate support.

[0130] The medical translation system may also include a nutrition assessment unit that evaluates the patient's nutritional status. This unit can assess the patient's nutritional status and provide this information to healthcare professionals. For example, it can evaluate the patient's diet and nutrient intake to ensure nutritional balance. Furthermore, based on the patient's nutritional status, the unit can provide advice for nutritional supplementation and dietary improvements. This allows patients to receive appropriate nutrition and maintain their health. Additionally, the nutrition assessment unit can record the patient's nutritional status over the long term and track changes. This allows healthcare professionals to understand changes in the patient's nutritional status and provide appropriate advice.

[0131] The medical translation system may also include an exercise assessment unit that evaluates the patient's exercise status. This unit can assess the patient's exercise status and provide this information to medical professionals. For example, it can evaluate the patient's exercise volume and habits to confirm whether appropriate exercise is being performed. Furthermore, based on the patient's exercise status, the unit can provide suggestions for exercise programs and advice for improving exercise habits. This allows patients to exercise appropriately and maintain their health. Additionally, the exercise assessment unit can record the patient's exercise status over the long term and track changes in their exercise status. This allows medical professionals to understand changes in the patient's exercise status and provide appropriate advice.

[0132] The medical translation system may also include a sleep assessment unit that evaluates the patient's sleep state. This unit can assess the patient's sleep state and provide this information to medical professionals. For example, it can evaluate the patient's sleep duration and quality to confirm whether they are getting adequate sleep. Furthermore, the sleep assessment unit can provide advice for improving sleep based on the patient's sleep state. This allows the patient to get adequate sleep and maintain their health. Additionally, the sleep assessment unit can record the patient's sleep state over the long term and track changes in sleep patterns. This allows medical professionals to understand changes in the patient's sleep state and provide appropriate advice.

[0133] Medical translation systems can further estimate a patient's emotions and adjust the way medical information is delivered based on those estimated emotions. For example, if a patient is feeling anxious, the generative AI can prioritize providing reassuring information. If the patient is relaxed, the generative AI can provide detailed medical information. Furthermore, if the patient is stressed, the generative AI can provide concise and easy-to-understand information. This enables information delivery tailored to the patient's emotions, leading to more appropriate communication. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0134] Medical translation systems can further estimate a patient's emotions and adjust the translation method of medical terminology based on those estimated emotions. For example, if a patient is feeling anxious, the generative AI can translate medical terminology into simple language. If the patient is relaxed, the generative AI can provide translations that include detailed explanations. Furthermore, if the patient is tense, the generative AI can translate medical terminology using concise and easy-to-understand expressions. This enables the translation of medical terminology according to the patient's emotions, resulting in the provision of more appropriate information. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0135] Medical translation systems can further estimate a patient's emotions and prioritize medical information based on those emotions. For example, if a patient is feeling anxious, the generative AI can prioritize providing reassuring information. If a patient is relaxed, the generative AI can prioritize providing detailed medical information. Furthermore, if a patient is stressed, the generative AI can provide important information concisely. This allows for the prioritization of medical information according to the patient's emotions, resulting in more appropriate information delivery. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0136] The following briefly describes the processing flow for example form 2.

[0137] Step 1: The translation department is responsible for facilitating communication between patients and medical professionals. For example, it can use generative AI to translate patients' statements in real time and convey them to medical professionals. When a patient describes their symptoms, the generative AI can instantly translate what they say and convey it to the medical professional. Step 2: The Specialized Terminology Translation Department is responsible for accurately translating medical terminology translated by the Translation Department. For example, it can use generative AI to accurately translate medical terminology and communicate it to medical professionals. By accurately translating medical terminology, it facilitates smoother communication in medical settings. Step 3: The Real-Time Translation Department is responsible for providing content translated by the Specialized Terminology Translation Department in real time. For example, it instantly provides content translated using generative AI to support emergency communication. When a patient describes their symptoms in an emergency, the generative AI can instantly translate that content and convey it to medical professionals. Step 4: The Multilingual Support Department is responsible for translating the content provided by the Real-Time Translation Department into multiple languages. For example, it uses generative AI to support multiple languages ​​and facilitate communication between patients and medical professionals who speak different languages. By supporting multiple languages ​​such as English, Chinese, and Spanish, it can serve patients from various countries. Step 5: The Drug Information Analysis Department is responsible for analyzing drug interactions based on information provided by the Multilingual Support Department. For example, it uses a generating AI to analyze the ingredients, effects, and side effects of medications brought in by patients and provides advice on drug interactions with other medications. When information on medications brought in by patients is entered, the generating AI analyzes the ingredients, effects, and side effects of those medications and provides advice on drug interactions with other medications.

[0138] 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.

[0139] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0140] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements described above, including the translation unit, specialized terminology translation unit, real-time translation unit, multilingual support unit, drug information analysis unit, drug information input unit, information provision unit, and emergency response unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the translation unit is implemented by the control unit 46A of the smart device 14 and can translate the patient's statements in real time and convey them to medical professionals. The specialized terminology translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and accurately translates medical terminology. The real-time translation unit is implemented by the control unit 46A of the smart device 14 and immediately provides the translated content. The multilingual support unit is implemented by the control unit 46A of the smart device 14 and supports multiple languages. The drug information analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the drug's components, effects, side effects, etc. The drug information input unit is implemented by the control unit 46A of the smart device 14 and inputs information about the medication brought by the patient. The information provision unit is implemented by the control unit 46A of the smart device 14 and provides the analyzed information. The emergency response unit is implemented by the control unit 46A of the smart device 14 and provides emergency response methods. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0142] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0143] 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.

[0144] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0145] 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.

[0146] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0147] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] 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.

[0149] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0150] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0151] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0152] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0154] 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.

[0155] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0156] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements described above, including the translation unit, specialized terminology translation unit, real-time translation unit, multilingual support unit, drug information analysis unit, drug information input unit, information provision unit, and emergency response unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the translation unit is implemented by the control unit 46A of the smart glasses 214 and can translate the patient's statements in real time and convey them to medical professionals. The specialized terminology translation unit is implemented by the identification processing unit 290 of the data processing unit 12 and accurately translates medical terminology. The real-time translation unit is implemented by the control unit 46A of the smart glasses 214 and provides the translated content immediately. The multilingual support unit is implemented by the control unit 46A of the smart glasses 214 and supports multiple languages. The drug information analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the drug's components, effects, side effects, etc. The drug information input unit is implemented by the control unit 46A of the smart glasses 214 and inputs information about the medication brought by the patient. The information provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the analyzed information. The emergency response unit is implemented by the control unit 46A of the smart glasses 214 and provides emergency response methods. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0158] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0159] 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.

[0160] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0161] 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.

[0162] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0163] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0164] 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.

[0165] 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.

[0166] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0167] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0168] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] 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.

[0171] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the translation unit, specialized terminology translation unit, real-time translation unit, multilingual support unit, drug information analysis unit, drug information input unit, information provision unit, and emergency response unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the translation unit is implemented by the control unit 46A of the headset terminal 314 and can translate the patient's statements in real time and convey them to medical professionals. The specialized terminology translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and accurately translates medical terminology. The real-time translation unit is implemented by the control unit 46A of the headset terminal 314 and immediately provides the translated content. The multilingual support unit is implemented by the control unit 46A of the headset terminal 314 and supports multiple languages. The drug information analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the drug's components, effects, side effects, etc. The drug information input unit is implemented by the control unit 46A of the headset terminal 314 and inputs information about the medication brought by the patient. The information provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the analyzed information. The emergency response unit is implemented by the control unit 46A of the headset terminal 314 and provides emergency response methods. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0174] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0175] 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.

[0176] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0177] 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.

[0178] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0179] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0180] 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.

[0181] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0182] 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.

[0183] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0184] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0185] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0186] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0187] 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.

[0188] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0189] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0190] Each of the multiple elements described above, including the translation unit, specialized terminology translation unit, real-time translation unit, multilingual support unit, drug information analysis unit, drug information input unit, information provision unit, and emergency response unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the translation unit is implemented by the control unit 46A of the robot 414 and can translate the patient's statements in real time and convey them to medical professionals. The specialized terminology translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and accurately translates medical terminology. The real-time translation unit is implemented by the control unit 46A of the robot 414 and immediately provides the translated content. The multilingual support unit is implemented by the control unit 46A of the robot 414 and supports multiple languages. The drug information analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the drug's components, effects, side effects, etc. The drug information input unit is implemented by the control unit 46A of the robot 414 and inputs information about the medication brought by the patient. The information provision unit is implemented by the control unit 46A of the robot 414 and provides the analyzed information. The emergency response unit is implemented by the control unit 46A of the robot 414 and provides emergency response methods. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0191] 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.

[0192] Figure 9 shows the 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.

[0193] 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.

[0194] 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.

[0195] 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, and motorcycles, 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 based, for example, 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.

[0196] 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."

[0197] 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.

[0198] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0207] 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 other things 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.

[0208] 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.

[0209] (Note 1) A translation department to facilitate communication between patients and medical professionals, The Specialized Terminology Translation Department accurately translates the medical terminology translated by the aforementioned Translation Department, The Real-Time Translation Unit provides the content translated by the aforementioned Specialized Terminology Translation Unit in real time, The content provided by the aforementioned real-time translation unit is handled by a multilingual support unit that supports multiple languages, The system includes a drug information analysis unit that analyzes drug interactions based on the information provided by the aforementioned multilingual support unit. A system characterized by the following features. (Note 2) It is equipped with a medication information input section for entering information about medications brought in by the patient. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an information provision unit that provides information analyzed by the generating AI. The system described in Appendix 1, characterized by the features described herein. (Note 4) It has an emergency response unit to support emergency response. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned translation department, The system estimates the patient's emotions and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned translation department, During translation, the patient's past medical history is referenced to select the most appropriate translation method. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned translation department, During translation, adjust the level of detail based on the patient's current health status. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned translation department, The system estimates the patient's emotions and determines translation priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned translation department, During translation, the system prioritizes highly relevant translations by considering the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned translation department, During translation, the system analyzes the patient's social media activity and translates relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned specialized terminology translation department, The system estimates the patient's emotions and adjusts the translation method of technical terms based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned specialized terminology translation department, When translating specialized terminology, the most appropriate translation method is selected by referring to the medical professional's past treatment history. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned specialized terminology translation department, When translating specialized terminology, different translation algorithms are applied depending on the medical field. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned specialized terminology translation department, The system estimates the patient's emotions and prioritizes the translation of technical terms based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned specialized terminology translation department, When translating technical terms, we prioritize highly relevant translations by considering the geographical location of medical institutions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned specialized terminology translation department, When translating technical terms, referencing relevant medical literature improves the accuracy of the translation. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned real-time translation unit, It estimates the patient's emotions and adjusts the real-time translation speed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned real-time translation unit, During real-time translation, the translation priority is adjusted according to urgency. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned real-time translation unit, During real-time translation, the system selects the optimal translation method by referring to the medical professional's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned real-time translation unit, It estimates the patient's emotions and adjusts how real-time translations are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned real-time translation unit, During real-time translation, the system prioritizes highly relevant translations by considering the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned real-time translation unit, During real-time translation, we improve translation accuracy by referencing relevant medical literature. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned multilingual support unit is The system estimates the patient's emotions and determines the priority of multilingual support based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned multilingual support unit is When providing multilingual support, the system selects the most appropriate language by referring to the patient's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned multilingual support unit is When providing multilingual support, different language support algorithms are applied for each medical field. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned multilingual support unit is The system estimates the patient's emotions and adjusts the multilingual display method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned multilingual support unit is When providing multilingual support, the system prioritizes the most relevant language, taking into account the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned multilingual support unit is When providing multilingual support, we improve the accuracy of language support by referring to relevant medical literature. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned drug information analysis unit is The system estimates the patient's emotions and prioritizes drug information analysis based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned drug information analysis unit is When analyzing drug information, the optimal analysis method is selected by referring to the patient's past drug use history. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned drug information analysis unit is When analyzing drug information, different analysis algorithms are applied to each drug component. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned drug information analysis unit is The system estimates the patient's emotions and adjusts the display method of drug information analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned drug information analysis unit is When analyzing drug information, the system prioritizes analyzing highly relevant drug information by considering the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned drug information analysis unit is When analyzing drug information, we improve the accuracy of the analysis by referring to relevant medical literature. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned drug information input unit is The system estimates the patient's emotions and adjusts the method of inputting medication information based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned drug information input unit is When entering medication information, the system selects the optimal input method by referring to the patient's past medication usage history. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned drug information input unit is The system estimates the patient's emotions and prioritizes the input of medication information based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned drug information input unit is When entering medication information, the system prioritizes the entry of highly relevant medication information, taking into account the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned information provision unit, Estimate the patient's emotions and adjust the method of information delivery based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned information provision unit, When providing information, the most appropriate method of information provision is selected by referring to the patient's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned information provision unit, The system estimates the patient's emotions and prioritizes information provision based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned information provision unit, When providing information, we prioritize providing highly relevant information, taking into account the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned emergency response unit, The system estimates the patient's emotions and adjusts emergency response methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned emergency response unit, During emergency situations, the optimal course of action is selected by referring to the patient's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned emergency response unit, The system estimates the patient's emotions and determines the priority of emergency response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 46) The aforementioned emergency response unit, During emergency response, prioritize highly relevant responses by considering the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0210] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A translation department to facilitate communication between patients and medical professionals, The Specialized Terminology Translation Department accurately translates the medical terminology translated by the aforementioned Translation Department, The Real-Time Translation Unit provides the content translated by the aforementioned Specialized Terminology Translation Unit in real time, The content provided by the aforementioned real-time translation unit is handled by a multilingual support unit that supports multiple languages, The system includes a drug information analysis unit that analyzes drug interactions based on the information provided by the aforementioned multilingual support unit. A system characterized by the following features.

2. It is equipped with a medication information input section for entering information about medications brought in by the patient. The system according to feature 1.

3. It includes an information provision unit that provides information analyzed by the generating AI. The system according to feature 1.

4. It has an emergency response unit to support emergency response. The system according to feature 1.

5. The aforementioned translation department, The system estimates the patient's emotions and adjusts the translation's expression based on those estimated emotions. The system according to feature 1.

6. The aforementioned translation department, During translation, the patient's past medical history is referenced to select the most appropriate translation method. The system according to feature 1.

7. The aforementioned translation department, During translation, adjust the level of detail based on the patient's current health status. The system according to feature 1.

8. The aforementioned translation department, The system estimates the patient's emotions and determines translation priorities based on those estimated emotions. The system according to feature 1.

9. The aforementioned translation department, During translation, the system prioritizes highly relevant translations by considering the patient's geographical location. The system according to feature 1.

10. The aforementioned translation department, During translation, the system analyzes the patient's social media activity and translates relevant information. The system according to feature 1.

Images