system

Abstract

The system according to this embodiment aims to facilitate communication between foreign patients and medical professionals. [Solution] The system according to this embodiment comprises a reception unit, a translation unit, a provision unit, a medical reception unit, a medical translation unit, and a medical provision unit. The reception unit receives the patient's voice. The translation unit translates the voice received by the reception unit. The provision unit provides the voice translated by the translation unit to medical personnel. The medical reception unit receives the voice of medical personnel. The medical translation unit translates the voice received by the medical reception unit. The medical provision unit provides the voice translated by the medical translation unit to the patient.

Description

Technical Field

[0004] ,

[0006] , , , , ,

[0005] , , , , ,

[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

[0007] The system according to this embodiment can facilitate communication between foreign patients and medical professionals. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applicable 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 multilingual translation and interpretation system according to an embodiment of the present invention is a platform that utilizes generative AI to facilitate communication between foreign patients and medical professionals in medical settings. This system removes language barriers and enables the provision of appropriate medical services to foreign patients. At the same time, it improves the internationalization capabilities of medical institutions and contributes to the realization of a global medical environment. For example, it provides a real-time voice translation function. The generative AI translates what the patient says in real time and conveys it to the medical professional. Conversely, the generative AI also translates what the medical professional says in real time and conveys it to the patient. This removes language barriers and enables smooth communication. Next, it is equipped with a high-precision translation engine specializing in medical terminology. The generative AI translates medical terms and specialized terms that are difficult for general translation engines to handle with high precision. This reduces the risk of misdiagnosis and treatment delays and enables the provision of appropriate medical services. Furthermore, it is equipped with a multilingual questionnaire and consent form generation system. Patients can fill out questionnaires and consent forms in their own language, and the generative AI translates them into the medical professional's language. This reduces the burden on patients and allows medical professionals to obtain accurate information. Furthermore, the system will also offer integration with remote medical interpretation services. The AI ​​will not only provide real-time translations but will also collaborate with remote medical interpreters as needed to offer more advanced interpretation services. This will reduce the burden on medical institutions and improve their ability to serve foreign patients. This system is urgently needed due to factors such as the increasing number of foreign visitors to Japan, the diversification of foreign residents, the rapid advancements in AI technology, the growing demand associated with the globalization of healthcare, and the spread of telemedicine due to the COVID-19 pandemic. The system aims to provide high-quality medical services that transcend language and cultural barriers, improve the internationalization capabilities of medical institutions, enhance access to medical care and foster a sense of security for foreign patients, and reduce the burden on healthcare professionals while improving operational efficiency. As a result, the multilingual translation and interpretation system will enable smooth communication between foreign patients and healthcare professionals, allowing for the provision of appropriate medical services.

[0029] The multilingual translation and interpretation system according to this embodiment comprises a reception unit, a translation unit, a provision unit, a medical reception unit, a medical translation unit, and a medical provision unit. The reception unit receives the patient's voice. The reception unit, for example, receives the words spoken by the patient using a microphone and stores them as voice data. The reception unit can also convert the voice data into text data using speech recognition technology. For example, the reception unit analyzes the voice using speech recognition software and stores it as text data. The translation unit translates the voice received by the reception unit using a generation AI. The translation unit, for example, uses a generation AI to analyze the voice data and translate it into another language. The translation unit can also translate medical terms and technical terms with high accuracy. For example, the generation AI performs translation while referring to a medical terminology dictionary. The provision unit provides the voice translated by the translation unit to medical personnel. The provision unit, for example, plays back the translated text data as voice using speech synthesis technology. The provision unit can also display the translation results on a display. For example, the delivery department displays the translated text data on a screen for medical professionals to review. The medical reception department receives the voice of medical professionals. For example, the medical reception department receives the words spoken by medical professionals using a microphone and saves them as audio data. The medical reception department can also convert the audio data into text data using speech recognition technology. For example, the medical reception department analyzes the voice using speech recognition software and saves it as text data. The medical translation department translates the voice received by the medical reception department using generative AI. For example, the medical translation department uses generative AI to analyze the audio data and translate it into another language. The medical translation department can also translate medical terms and technical terms with high accuracy. For example, the generative AI performs translations while referring to a medical terminology dictionary. The medical delivery department provides the voice translated by the medical translation department to the patient. For example, the medical delivery department plays back the translated text data as audio using speech synthesis technology. The medical delivery department can also display the translation results on a display. For example, the medical delivery department displays the translated text data on a screen for the patient to review.As a result, the multilingual translation and interpretation system according to this embodiment can translate speech in real time between patients and healthcare professionals, enabling smooth communication.

[0030] The reception area receives patient voices. For example, the reception area receives the patient's spoken words using a microphone and saves them as audio data. Specifically, the reception area uses a high-sensitivity microphone to clearly capture the patient's voice. The audio data is processed using noise reduction technology to remove background noise and improve the accuracy of speech recognition. The speech recognition technology uses a deep learning model to convert the patient's pronunciation and accent differences into text data with high accuracy. For example, the speech recognition software analyzes the patient's voice in real time and saves it as text data. This allows the reception area to quickly and accurately convert the patient's voice into text data and smoothly hand it over to the next processing step. Furthermore, the reception area has a database for storing and managing audio data, and can refer to past audio data. This allows for reviewing the patient's past statements and symptoms, enabling more appropriate responses.

[0031] The translation department uses generative AI to translate audio received by the reception department. Specifically, the generative AI analyzes the audio data and translates it into other languages. The generative AI utilizes natural language processing technology to convert the audio data into text data, and then translates that text data into the target language. For example, the generative AI uses speech recognition technology to convert audio into text data and inputs that text data into a multilingual translation model. The multilingual translation model has been pre-trained on a large amount of medical and technical terms, enabling highly accurate translations. Because the generative AI performs translations while referring to a medical terminology dictionary, it can accurately translate specialized terms and expressions. Furthermore, the generative AI uses contextual analysis technology to understand the context and provide appropriate translations. As a result, the translation department can accurately and naturally translate patients' statements into other languages ​​and provide them to healthcare professionals.

[0032] The service provider delivers the translated audio to healthcare professionals. Specifically, it plays back the translated text data as audio using speech synthesis technology. The speech synthesis technology generates audio with natural pronunciation and intonation, providing it in a format that is easy for healthcare professionals to understand. For example, the service provider inputs the translated text data into a speech synthesis engine and plays the generated audio through a speaker. The service provider can also display the translation results on a screen. The screen displays the translated text data in an easy-to-read font and size, allowing healthcare professionals to quickly review it. Furthermore, the service provider can automatically record the translation results in the electronic medical record system and save them as part of the patient's medical history. This enables the service provider to provide healthcare professionals with timely and accurate information and support smooth communication.

[0033] The medical reception department receives voice messages from medical professionals. Specifically, it captures the words spoken by medical professionals using a microphone and saves them as audio data. The medical reception department can also convert the audio data into text data using speech recognition technology. For example, the medical reception department uses a high-sensitivity microphone to collect the voices of medical professionals and removes background noise using noise reduction technology. The speech recognition technology uses a deep learning model to convert the pronunciation and technical terms of medical professionals into text data with high accuracy. This allows the medical reception department to quickly and accurately convert the voices of medical professionals into text data and smoothly hand it over to the next processing step. Furthermore, the medical reception department has a database for storing and managing audio data, and can refer to past audio data. This makes it possible to check past statements and instructions from medical professionals and respond more appropriately.

[0034] The medical translation department uses generative AI to translate audio received by the medical reception department. Specifically, the generative AI analyzes the audio data and translates it into other languages. The generative AI utilizes natural language processing technology to convert the audio data into text data, and then translates that text data into the target language. For example, the generative AI uses speech recognition technology to convert audio into text data and inputs that text data into a multilingual translation model. The multilingual translation model has been pre-trained on a large amount of medical and technical terms, enabling highly accurate translations. Because the generative AI performs translations while referring to a medical terminology dictionary, it can accurately translate specialized terms and expressions. Furthermore, the generative AI uses contextual analysis technology to understand the context and provide appropriate translations. As a result, the medical translation department can accurately and naturally translate the statements of medical professionals into other languages ​​and provide them to patients.

[0035] The medical service department provides patients with audio translated by the medical translation department. Specifically, the translated text data is played back as audio using speech synthesis technology. Speech synthesis technology generates audio with natural pronunciation and intonation, providing it in a way that is easy for patients to understand. For example, the medical service department inputs the translated text data into a speech synthesis engine and plays the generated audio through a speaker. The medical service department can also display the translation results on a screen. The translated text data is displayed on the screen in an easy-to-read font and size, allowing patients to quickly review it. Furthermore, the medical service department can automatically record the translation results in the electronic medical record system and save them as part of the patient's medical history. This allows the medical service department to provide patients with timely and accurate information and support smooth communication.

[0036] The generation unit can generate medical questionnaires and consent forms. For example, the generation unit uses a generation AI to generate medical questionnaires and consent forms filled out by the patient in their own language. The generation unit uses the generation AI to analyze the patient's input data and generate the medical questionnaires and consent forms in an appropriate format. The generation unit can also use the generation AI to translate medical and technical terms with high accuracy. For example, the generation unit uses the generation AI to perform translations while referring to a medical terminology dictionary. This allows patients to fill out medical questionnaires and consent forms in their own language. Medical questionnaires and consent forms may include, but are not limited to, basic patient information, medical history, allergy information, and current symptoms. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the medical questionnaire and consent form filled out by the patient into the generation AI, which can then generate them in an appropriate format.

[0037] The generation unit can translate questionnaires and consent forms filled out by patients in their own language into the language of healthcare professionals. For example, the generation unit uses a generation AI to analyze the questionnaires and consent forms filled out by patients and translate them into the language of healthcare professionals. The generation unit can also use the generation AI to translate medical and technical terms with high accuracy. For example, the generation unit performs translation while the generation AI refers to a medical terminology dictionary. This allows healthcare professionals to understand the information filled out by patients. The translation includes, but is not limited to, basic patient information, medical history, allergy information, and current symptoms. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input questionnaires and consent forms filled out by patients into a generation AI, which can then translate them into the language of healthcare professionals.

[0038] The generation unit can translate medical terms and technical terms with high accuracy. The generation unit analyzes medical terms and technical terms using, for example, a generation AI and translates them with high accuracy. The generation unit performs translation while the generation AI refers to a medical terminology dictionary. This prevents mistranslation of medical terms and technical terms. Translations include, but are not limited to, diagnoses, treatments, drug names, and test results. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input medical terms and technical terms into a generation AI, which can then translate them with high accuracy.

[0039] The collaboration unit can collaborate with remote medical interpretation services. For example, the collaboration unit can use a generative AI to collaborate with remote medical interpreters and provide interpretation services. The collaboration unit can also use the generative AI to select the most suitable interpreter, taking into account their expertise and experience. For example, the collaboration unit can use the generative AI to select interpreters by referring to their qualifications and past interpretation history. This allows the collaboration with remote medical interpreters to provide more advanced interpretation services. Collaboration includes, but is not limited to, methods such as video calls, voice calls, and chat. Some or all of the processing described above in the collaboration unit may be performed using, for example, a generative AI, or without one. For example, the collaboration unit can input information about remote medical interpreters into the generative AI, which can then select the most suitable interpreter.

[0040] The collaboration unit can provide interpretation services by collaborating with remote medical interpreters as needed. For example, the collaboration unit can use a generative AI to select the most suitable interpreter based on the patient's situation and then collaborate with them. The collaboration unit can also use the generative AI to analyze the patient's symptoms and urgency to select an appropriate interpreter. For example, the collaboration unit can use the generative AI to select an interpreter based on the patient's medical history and current symptoms. This allows the unit to collaborate with remote medical interpreters as needed and provide interpretation services. Collaboration includes, but is not limited to, methods such as video calls, voice calls, and chat. Some or all of the above-described processes in the collaboration unit may be performed using, for example, a generative AI, or without one. For example, the collaboration unit can input patient information into the generative AI, which can then select the most suitable interpreter.

[0041] The reception desk can analyze the patient's past voice data and select the optimal voice reception method. For example, the reception desk can use AI to analyze the patient's past voice data and propose the optimal voice reception method. For example, the reception desk can analyze the voice input methods the patient has used in the past and select the optimal method. The reception desk can also select the method that resulted in the smoothest reception from the patient's past voice data. Furthermore, the reception desk can analyze the quality of the patient's voice data and select the optimal voice reception method. Thus, by analyzing the patient's past voice data, the optimal voice reception method can be selected. The optimal voice reception method includes, but is not limited to, voice recognition technology, voice input devices, and voice input timing. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can input the patient's past voice data into AI, which can then select the optimal voice reception method.

[0042] The reception desk can filter voice messages based on the patient's current health status and symptoms. For example, the reception desk can use AI to analyze the patient's health status and symptoms and prioritize receiving important information. For instance, if the patient's health is poor, the AI ​​will filter the voice message and prioritize receiving important information. Similarly, if the patient's symptoms are severe, the AI ​​can filter the voice message and prioritize receiving urgent information. Furthermore, if the patient's health is good, the reception desk can receive normal information. This allows for the prioritization of important information based on the patient's health status and symptoms. Filtering includes, but is not limited to, voice recognition technology, voice analysis algorithms, and health status assessment criteria. Some or all of the above processing in the reception desk may be performed using, for example, AI, or without AI. For example, the reception desk can input patient health data into the AI, which can then filter important information.

[0043] The reception desk can prioritize receiving voice messages that are highly relevant, taking into account the patient's geographical location. For example, the reception desk can use AI to analyze the patient's geographical location and prioritize receiving highly relevant voice messages. For instance, if the patient is near the hospital, the reception desk will prioritize receiving urgent voice messages. If the patient is far away, the reception desk can also prioritize receiving voice messages related to telemedicine. Furthermore, if the patient is in a specific region, the reception desk can prioritize receiving voice messages related to that region. This allows for the prioritization of highly relevant voice messages by considering the patient's geographical location. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the reception desk may be performed using, for example, AI, or without AI. For example, the reception desk can input the patient's geographical information into the AI, which can then prioritize receiving highly relevant voice messages.

[0044] The reception desk can analyze the patient's social media activity when receiving voice messages and receive relevant messages. For example, the reception desk can use AI to analyze the patient's social media activity and prioritize receiving relevant messages. For instance, the reception desk can analyze health-related posts from the patient's social media activity and prioritize receiving relevant messages. The reception desk can also analyze recent activity from the patient's social media activity and prioritize receiving relevant messages. Furthermore, the reception desk can analyze the patient's interests from their social media activity and prioritize receiving relevant messages. This allows for the priority reception of relevant messages by analyzing the patient's social media activity. Social media activity includes, but is not limited to, analysis of post content and methods for evaluating relevance. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the patient's social media data into AI, which can then prioritize receiving relevant messages.

[0045] The translation unit can adjust the level of detail in translations based on the importance of medical terms during the translation process. For example, the translation unit can use generative AI to analyze the importance of medical terms and adjust the level of detail in the translation. For instance, the translation unit can provide detailed translations for important medical terms. It can also provide concise translations for common medical terms. Furthermore, it can provide specialized translations for specialized medical terms. By adjusting the level of detail in translations based on the importance of medical terms, appropriate translations are provided. The evaluation of importance includes, but is not limited to, the frequency of medical terms and the method of evaluating importance. Some or all of the above processing in the translation unit may be performed using, for example, generative AI, or without generative AI. For example, the translation unit can input medical term data into generative AI, which can evaluate importance and adjust the level of detail in the translation.

[0046] The translation unit can apply different translation algorithms during translation depending on the patient's symptoms and medical history. For example, the translation unit can use a generative AI to analyze the patient's symptoms and medical history and select an appropriate translation algorithm. For instance, if the patient's symptoms are severe, the translation unit can apply a detailed translation algorithm. It can also apply a specialized translation algorithm if the patient's medical history is complex. Furthermore, if the patient's symptoms are mild, the translation unit can apply a concise translation algorithm. This ensures that more accurate translations are provided by applying the appropriate translation algorithm according to the patient's symptoms and medical history. Examples of different translation algorithms include, but are not limited to, criteria for selecting an algorithm based on symptoms and medical history. Some or all of the above-described processes in the translation unit may be performed using, for example, a generative AI, or without one. For example, the translation unit can input patient symptom and medical history data into a generative AI, which can then select an appropriate translation algorithm.

[0047] The translation unit can determine translation priorities based on the submission date of the audio during the translation process. For example, the translation unit may use a generative AI to analyze the submission date and determine translation priorities. For instance, the translation unit may prioritize translating recently submitted audio. It may also prioritize translating audio with high urgency. Furthermore, the translation unit may postpone the translation of older audio. This allows for prioritizing the translation of audio with high urgency by determining translation priorities based on the submission date. Prioritization includes, but is not limited to, evaluation criteria for submission date and priority determination algorithms. Some or all of the above-described processes in the translation unit may be performed, for example, using a generative AI, or without a generative AI. For example, the translation unit may input audio data into a generative AI, which may evaluate the submission date and determine translation priorities.

[0048] The translation unit can adjust the order of translations based on the relevance of the audio during the translation process. For example, the translation unit may use a generative AI to analyze the relevance of the audio and adjust the order of translations. For example, the translation unit may prioritize translating audio related to the patient's symptoms. It may also prioritize translating audio related to the medical professional's area of ​​expertise. Furthermore, it may prioritize translating audio of high urgency. This allows important audio to be prioritized for translation by adjusting the order of translations based on the relevance of the audio. The evaluation of relevance includes, but is not limited to, the content of the audio and the method of evaluating relevance. Some or all of the above processing in the translation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the translation unit may input audio data into a generative AI, which may evaluate the relevance and adjust the order of translations.

[0049] The service delivery unit can select the optimal delivery method by referring to the past interaction history of healthcare professionals at the time of delivery. The service delivery unit can, for example, use AI to analyze the past interaction history of healthcare professionals and propose the optimal delivery method. For example, the service delivery unit can refer to delivery methods previously used by healthcare professionals and select the optimal method. The service delivery unit can also select the most effective delivery method from the past interaction history of healthcare professionals. Furthermore, the service delivery unit can analyze the past interaction history of healthcare professionals and select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the past interaction history of healthcare professionals. The optimal delivery method includes, but is not limited to, selection criteria and evaluation methods for delivery methods. Some or all of the above processing in the service delivery unit may be performed using, for example, AI, or not using AI. For example, the service delivery unit can input healthcare professional interaction history data into AI, and the AI ​​can select the optimal delivery method.

[0050] The information delivery unit can customize the means of delivery based on the patient's current health condition at the time of delivery. For example, the information delivery unit can use AI to analyze the patient's health condition and customize the means of delivery. For example, if the patient's health condition is poor, the information delivery unit will prioritize providing important information. The information delivery unit can also provide normal information if the patient's health condition is good. Furthermore, if the patient's health condition is unstable, the information delivery unit can provide urgent information. By customizing the means of delivery according to the patient's health condition, more appropriate information can be provided. Customization includes, but is not limited to, health condition evaluation criteria and customization methods. Some or all of the above processing in the information delivery unit may be performed using, for example, AI, or not using AI. For example, the information delivery unit can input patient health condition data into AI, and the AI ​​can customize the means of delivery.

[0051] The service provider can select the optimal delivery method by considering the patient's geographical location information at the time of delivery. For example, the service provider can use AI to analyze the patient's geographical location information and select the optimal delivery method. For example, if the patient is near a hospital, the service provider can prioritize providing information with high urgency. The service provider can also prioritize providing information related to telemedicine if the patient is far away. Furthermore, if the service provider is in a specific region, the service provider can prioritize providing information relevant to that region. In this way, the optimal delivery method can be selected by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the service provider may be performed using, for example, AI, or without AI. For example, the service provider can input the patient's geographical information into AI, and the AI ​​can select the optimal delivery method.

[0052] The service provider can analyze the patient's social media activity and propose a means of delivery at the time of delivery. For example, the service provider can use AI to analyze the patient's social media activity and prioritize the provision of relevant information. For example, the service provider can analyze health-related posts from the patient's social media activity and prioritize the provision of relevant information. The service provider can also analyze recent activities from the patient's social media activity and prioritize the provision of relevant information. Furthermore, the service provider can analyze interests from the patient's social media activity and prioritize the provision of relevant information. In this way, relevant information can be prioritized by analyzing the patient's social media activity. Social media activity includes, but is not limited to, examples such as analysis of post content and methods for evaluating relevance. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the patient's social media data into AI, and the AI ​​can prioritize the provision of relevant information.

[0053] The medical reception department can analyze the past voice data of medical staff and select the optimal voice reception method. For example, the medical reception department can use AI to analyze the past voice data of medical staff and propose the optimal voice reception method. For example, the medical reception department can analyze the voice input methods previously used by medical staff and select the optimal method. Furthermore, the medical reception department can select the method that resulted in the smoothest reception from the medical staff's past voice data. In addition, the medical reception department can analyze the quality of the medical staff's voice data and select the optimal voice reception method. Thus, by analyzing the medical staff's past voice data, the optimal voice reception method can be selected. The optimal voice reception method includes, but is not limited to, voice recognition technology, voice input devices, and voice input timing. Some or all of the above processing in the medical reception department may be performed using, for example, AI, or not using AI. For example, the medical reception department can input the medical staff's past voice data into AI, and the AI ​​can select the optimal voice reception method.

[0054] The medical reception department can filter voice calls based on the expertise and experience of the medical professionals. For example, the medical reception department can use AI to analyze the expertise and experience of medical professionals and prioritize important voice calls. For instance, the medical reception department can prioritize voice calls related to the medical professional's area of ​​expertise. It can also prioritize important voice calls based on the medical professional's experience. Furthermore, the medical reception department can prioritize urgent voice calls based on the medical professional's expertise and experience. This allows for the prioritization of important voice calls based on the medical professional's expertise and experience. Filtering includes, but is not limited to, evaluation criteria for expertise and experience, and filtering algorithms. Some or all of the above processing in the medical reception department may be performed using, for example, AI, or not. For example, the medical reception department can input data on the medical professionals' areas of expertise and experience into the AI, which can then filter important voice calls.

[0055] The medical reception department can prioritize receiving voice calls by considering the geographical location information of healthcare professionals. For example, the medical reception department can use AI to analyze the geographical location information of healthcare professionals and prioritize receiving relevant voice calls. For instance, if a healthcare professional is within the hospital, the medical reception department will prioritize receiving urgent voice calls. Furthermore, if a healthcare professional is located far away, the medical reception department can prioritize receiving voice calls related to telemedicine. Additionally, if a healthcare professional is in a specific region, the medical reception department can prioritize receiving voice calls related to that region. This allows for the prioritization of highly relevant voice calls by considering the geographical location information of healthcare professionals. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the medical reception department may be performed using, for example, AI, or without AI. For example, the medical reception department can input the geographical information of healthcare professionals into AI, which can then prioritize receiving highly relevant voice calls.

[0056] The medical reception department can analyze the social media activity of healthcare workers when receiving voice calls and receive relevant voice calls. For example, the medical reception department can use AI to analyze the social media activity of healthcare workers and prioritize receiving relevant voice calls. For instance, the medical reception department can analyze posts related to healthcare from the social media activity of healthcare workers and prioritize receiving relevant voice calls. Furthermore, the medical reception department can analyze recent activity from the social media activity of healthcare workers and prioritize receiving relevant voice calls. In addition, the medical reception department can analyze interests from the social media activity of healthcare workers and prioritize receiving relevant voice calls. This allows for the prioritization of relevant voice calls by analyzing the social media activity of healthcare workers. Social media activity includes, but is not limited to, analysis of post content and methods for evaluating relevance. Some or all of the above processing in the medical reception department may be performed using AI, for example, or without AI. For example, the medical reception department can input the social media data of healthcare workers into AI, which can then prioritize receiving relevant voice calls.

[0057] The medical translation department can adjust the level of detail in translations based on the importance of medical terms. For example, the medical translation department might use generative AI to analyze the importance of medical terms and adjust the level of detail. For instance, it might provide detailed translations for important medical terms, concise translations for common terms, and specialized translations for specialized medical terms. This ensures that appropriate translations are provided by adjusting the level of detail based on the importance of medical terms. The evaluation of importance includes, but is not limited to, the frequency of medical terms and methods for evaluating importance. Some or all of the above-described processes in the medical translation department may be performed using, for example, generative AI, or without it. For example, the medical translation department could input medical term data into a generative AI, which could then evaluate importance and adjust the level of detail.

[0058] The medical translation department can apply different translation algorithms during translation depending on the medical professional's area of ​​expertise and experience. For example, the medical translation department can use generative AI to analyze the medical professional's area of ​​expertise and experience and select an appropriate translation algorithm. For instance, if the medical professional specializes in internal medicine, the department will apply a translation algorithm specifically for internal medicine. Similarly, if the medical professional specializes in surgery, the department can apply a translation algorithm specifically for surgery. Furthermore, if the medical professional has extensive experience, the department can apply a more detailed translation algorithm. This ensures that more accurate translations are provided by applying the appropriate translation algorithm according to the medical professional's area of ​​expertise and experience. Examples of different translation algorithms include, but are not limited to, criteria for selecting algorithms based on area of ​​expertise and experience. Some or all of the above-described processes in the medical translation department may be performed using, for example, generative AI, or without generative AI. For example, the medical translation department can input data on the medical professional's area of ​​expertise and experience into a generative AI, which can then select an appropriate translation algorithm.

[0059] The medical translation department can prioritize translations based on the submission date of the audio. For example, the medical translation department might use a generative AI to analyze the submission date and determine the translation priority. For instance, the medical translation department might prioritize translating recently submitted audio. It could also prioritize translating audio with high urgency. Furthermore, it could postpone the translation of older audio. This allows for prioritizing the translation of audio with high urgency based on the submission date. Prioritization includes, but is not limited to, evaluation criteria for submission date and priority determination algorithms. Some or all of the above-described processes in the medical translation department may be performed, for example, using a generative AI, or without one. For example, the medical translation department could input audio data into a generative AI, which would then evaluate the submission date and determine the translation priority.

[0060] The medical translation department can adjust the order of translations based on the relevance of the audio during the translation process. For example, the medical translation department may use generative AI to analyze the relevance of the audio and adjust the translation order. For instance, the medical translation department may prioritize translating audio related to the patient's symptoms. It may also prioritize translating audio related to the medical professional's area of ​​expertise. Furthermore, it may prioritize translating audio of high urgency. This allows for the prioritization of important audio by adjusting the translation order based on the relevance of the audio. Relevance evaluation includes, but is not limited to, the content of the audio and the method of evaluating relevance. Some or all of the above-described processes in the medical translation department may be performed, for example, using generative AI, or without generative AI. For example, the medical translation department can input audio data into a generative AI, which can then evaluate relevance and adjust the translation order.

[0061] The healthcare delivery department can select the optimal delivery method by referring to the patient's past interaction history at the time of delivery. The healthcare delivery department can, for example, use AI to analyze the patient's past interaction history and propose the optimal delivery method. For example, the healthcare delivery department can refer to the patient's past interaction history and select the optimal method. The healthcare delivery department can also select the most effective delivery method from the patient's past interaction history. Furthermore, the healthcare delivery department can analyze the patient's past interaction history and select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the patient's past interaction history. The optimal delivery method includes, but is not limited to, selection criteria and evaluation methods for the delivery method. Some or all of the above processing in the healthcare delivery department may be performed using, for example, AI, or not using AI. For example, the healthcare delivery department can input patient interaction history data into AI, and the AI ​​can select the optimal delivery method.

[0062] The healthcare delivery department can customize the means of delivery based on the expertise and experience of healthcare professionals at the time of delivery. For example, the healthcare delivery department can use AI to analyze the expertise and experience of healthcare professionals and customize the means of delivery. For example, if a healthcare professional's area of ​​expertise is internal medicine, the healthcare delivery department will customize the means of delivery to be specialized for internal medicine. Furthermore, if a healthcare professional's area of ​​expertise is surgery, the healthcare delivery department can customize the means of delivery to be specialized for surgery. In addition, if a healthcare professional has extensive experience, the healthcare delivery department can customize the means of delivery in more detail. This allows for the provision of more appropriate information by customizing the means of delivery based on the expertise and experience of healthcare professionals. Customization includes, but is not limited to, evaluation criteria for expertise and experience, and methods of customization. Some or all of the above-described processes in the healthcare delivery department may be performed using, for example, AI, or not. For example, the healthcare delivery department can input data on the expertise and experience of healthcare professionals into AI, which can then customize the means of delivery.

[0063] The healthcare delivery department can select the optimal delivery method by considering the geographical location information of healthcare workers at the time of delivery. For example, the healthcare delivery department can use AI to analyze the geographical location information of healthcare workers and select the optimal delivery method. For example, if healthcare workers are in the hospital, the healthcare delivery department can prioritize providing information of high urgency. Also, if healthcare workers are in a remote location, the healthcare delivery department can prioritize providing information related to that region. In addition, if healthcare workers are in a specific region, the healthcare delivery department can prioritize providing information related to that region. In this way, the optimal delivery method can be selected by considering the geographical location information of healthcare workers. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the healthcare delivery department may be performed using, for example, AI, or not using AI. For example, the healthcare delivery department can input the geographical information of healthcare workers into AI, and the AI ​​can select the optimal delivery method.

[0064] The healthcare delivery department can analyze the social media activity of healthcare professionals and propose delivery methods at the time of delivery. For example, the healthcare delivery department can use AI to analyze the social media activity of healthcare professionals and provide relevant information preferentially. For example, the healthcare delivery department can analyze posts related to medicine from the social media activity of healthcare professionals and provide relevant information preferentially. The healthcare delivery department can also analyze recent activity from the social media activity of healthcare professionals and provide relevant information preferentially. Furthermore, the healthcare delivery department can analyze interests from the social media activity of healthcare professionals and provide relevant information preferentially. In this way, relevant information can be provided preferentially by analyzing the social media activity of healthcare professionals. Social media activity includes, but is not limited to, examples such as analysis of post content and methods for evaluating relevance. Some or all of the above processing in the healthcare delivery department may be performed using AI, for example, or without AI. For example, the healthcare delivery department can input the social media data of healthcare professionals into AI, and the AI ​​can provide relevant information preferentially.

[0065] The generation unit can adjust the level of detail of the generated documents based on the importance of the medical terms during the generation process. For example, the generation unit can use a generation AI to analyze the importance of medical terms and adjust the level of detail of the generated documents. For example, the generation unit can generate questionnaires that include detailed explanations for important medical terms. The generation unit can also generate questionnaires that include concise explanations for common medical terms. Furthermore, the generation unit can generate questionnaires that include specialized explanations for specialized medical terms. By adjusting the level of detail of the generated documents based on the importance of the medical terms, appropriate questionnaires and consent forms are generated. The evaluation of importance includes, but is not limited to, the frequency of medical terms and the method of evaluating importance. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input medical term data into a generation AI, which can evaluate importance and adjust the level of detail of the generated documents.

[0066] The generation unit can apply different generation algorithms during generation depending on the patient's symptoms and medical history. For example, the generation unit uses a generation AI to analyze the patient's symptoms and medical history and select an appropriate generation algorithm. For example, if the patient's symptoms are severe, the generation unit applies a detailed generation algorithm. The generation unit can also apply a specialized generation algorithm if the patient's medical history is complex. Furthermore, if the patient's symptoms are mild, the generation unit can apply a concise generation algorithm. By applying an appropriate generation algorithm according to the patient's symptoms and medical history, more accurate questionnaires and consent forms are generated. Different generation algorithms include, but are not limited to, criteria for selecting an algorithm based on symptoms and medical history. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input patient symptom and medical history data into a generation AI, which can then select an appropriate generation algorithm.

[0067] The generation unit can determine the generation priority based on the submission timing of questionnaires and consent forms during the generation process. For example, the generation unit can use a generation AI to analyze the submission timing of questionnaires and consent forms and determine the generation priority. For example, the generation unit can prioritize the generation of questionnaires that have been submitted recently. The generation unit can also prioritize the generation of questionnaires with high urgency. Furthermore, the generation unit can postpone the generation of questionnaires that have been submitted earlier. In this way, by determining the generation priority based on the submission timing of questionnaires and consent forms, it is possible to prioritize the generation of those with high urgency. The determination of priority includes, but is not limited to, evaluation criteria for submission timing and priority determination algorithms. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input questionnaire and consent form data into a generation AI, which can evaluate the submission timing and determine the generation priority.

[0068] The generation unit can adjust the generation order based on the relevance of questionnaires and consent forms during the generation process. For example, the generation unit can use a generation AI to analyze the relevance of questionnaires and consent forms and adjust the generation order. For example, the generation unit can prioritize generating questionnaires related to the patient's symptoms. It can also prioritize generating questionnaires related to the medical professional's area of ​​expertise. Furthermore, it can prioritize generating questionnaires of high urgency. By adjusting the generation order based on the relevance of questionnaires and consent forms, important documents can be generated preferentially. The evaluation of relevance includes, but is not limited to, the content of the questionnaires and consent forms and the method of evaluating relevance. Some or all of the above-described processes in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input data from questionnaires and consent forms into a generation AI, which can evaluate the relevance and adjust the generation order.

[0069] The collaboration department can select the most appropriate collaboration method based on the medical interpreter's area of ​​expertise and experience during the collaboration process. For example, the collaboration department can use AI to analyze the medical interpreter's area of ​​expertise and experience and select the most appropriate collaboration method. For instance, if the medical interpreter's area of ​​expertise is internal medicine, the collaboration department will select a collaboration method specifically for internal medicine. Similarly, if the medical interpreter's area of ​​expertise is surgery, the collaboration department can select a collaboration method specifically for surgery. Furthermore, if the medical interpreter has extensive experience, the collaboration department can select a more detailed collaboration method. This allows for the provision of more appropriate interpretation services by selecting the most appropriate collaboration method based on the medical interpreter's area of ​​expertise and experience. The optimal collaboration method includes, but is not limited to, selection criteria and evaluation methods. Some or all of the above-described processes in the collaboration department may be performed using AI, or not. For example, the collaboration department can input data on the medical interpreter's area of ​​expertise and experience into AI, which can then select the most appropriate collaboration method.

[0070] The collaboration unit can select the optimal collaboration method by considering the patient's geographical location information during collaboration. For example, the collaboration unit can use AI to analyze the patient's geographical location information and select the optimal collaboration method. For example, if the patient is in a hospital, the collaboration unit can prioritize providing urgent interpretation services. The collaboration unit can also prioritize providing telemedicine interpretation services if the patient is in a distant location. Furthermore, if the collaboration unit is in a specific region, it can prioritize providing interpretation services related to that region. In this way, the optimal collaboration method can be selected by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the collaboration unit may be performed using, for example, AI, or not using AI. For example, the collaboration unit can input the patient's geographical information into AI, and the AI ​​can select the optimal collaboration method.

[0071] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0072] The reception desk can analyze the patient's past voice data and select the optimal voice reception method. For example, it can use AI to analyze the patient's past voice data and suggest the optimal voice reception method. It can analyze the voice input methods the patient has used in the past and select the optimal method. It can also select the method that resulted in the smoothest reception from the patient's past voice data. Furthermore, it can analyze the quality of the patient's voice data and select the optimal voice reception method. In this way, the optimal voice reception method can be selected by analyzing the patient's past voice data. The optimal voice reception method includes, but is not limited to, voice recognition technology, voice input devices, and voice input timing. Some or all of the above processing in the reception desk may be performed using AI or not using AI. For example, the reception desk can input the patient's past voice data into AI, and the AI ​​can select the optimal voice reception method.

[0073] The reception desk can filter voice messages based on the patient's current health status and symptoms. For example, it can use AI to analyze the patient's health status and symptoms and prioritize receiving important information. If the patient's health is poor, the AI ​​can filter the voice message and prioritize receiving important information. If the patient's symptoms are severe, the AI ​​can also filter the voice message and prioritize receiving urgent information. Furthermore, if the patient's health is good, it can also receive normal information. This allows for the prioritization of important information based on the patient's health status and symptoms. Filtering includes, but is not limited to, voice recognition technology, voice analysis algorithms, and health status evaluation criteria. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input patient health data into the AI, which can then filter important information.

[0074] The reception desk can prioritize receiving voice messages that are highly relevant, taking into account the patient's geographical location. For example, it can use AI to analyze the patient's geographical location and prioritize receiving highly relevant voice messages. If the patient is near the hospital, it can prioritize receiving urgent voice messages. If the patient is far away, it can prioritize receiving voice messages related to telemedicine. Furthermore, if the patient is in a specific region, it can prioritize receiving voice messages related to that region. In this way, by considering the patient's geographical location, it is possible to prioritize receiving highly relevant voice messages. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the patient's geographical information into the AI, which can then prioritize receiving highly relevant voice messages.

[0075] The translation unit can adjust the level of detail in translations based on the importance of medical terms. For example, it can use a generative AI to analyze the importance of medical terms and adjust the level of detail. For important medical terms, a detailed translation can be provided. For common medical terms, a concise translation can be provided. Furthermore, for specialized medical terms, a specialized translation can be provided. In this way, appropriate translations are provided by adjusting the level of detail in translations based on the importance of medical terms. The evaluation of importance includes, but is not limited to, the frequency of medical terms and the method of evaluating importance. Some or all of the above processing in the translation unit may be performed using a generative AI or not. For example, the translation unit can input medical term data into a generative AI, which can evaluate importance and adjust the level of detail in translation.

[0076] The delivery unit can select the optimal delivery method by referring to the past interaction history of healthcare professionals at the time of delivery. For example, it can use AI to analyze the past interaction history of healthcare professionals and propose the optimal delivery method. It can select the optimal method by referring to delivery methods previously used by healthcare professionals. It can also select the most effective delivery method from the past interaction history of healthcare professionals. Furthermore, it can analyze the past interaction history of healthcare professionals to select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the past interaction history of healthcare professionals. The optimal delivery method includes, but is not limited to, selection criteria and evaluation methods for delivery methods. Some or all of the above processing in the delivery unit may be performed using AI or not using AI. For example, the delivery unit can input healthcare professional interaction history data into AI, and the AI ​​can select the optimal delivery method.

[0077] The following briefly describes the processing flow for example form 1.

[0078] Step 1: The reception desk receives the patient's voice. For example, it receives the patient's spoken words with a microphone and saves them as audio data. The reception desk can also use speech recognition technology to convert the audio data into text data. Step 2: The translation unit uses generative AI to translate the audio received by the reception unit. For example, the generative AI analyzes the audio data and translates it into another language. The translation unit can also translate medical terms and technical terms with high accuracy. Step 3: The delivery unit provides the translated audio to healthcare professionals. For example, the translated text data is played back as audio using speech synthesis technology. The delivery unit can also display the translation results on a screen. Step 4: The medical reception desk receives the voice of the medical staff. For example, it receives what the medical staff says using a microphone and saves it as audio data. The medical reception desk can also use speech recognition technology to convert the audio data into text data. Step 5: The medical translation department uses generative AI to translate the audio received by the medical reception department. For example, the generative AI analyzes the audio data and translates it into another language. The medical translation department can also translate medical terms and technical terms with high accuracy. Step 6: The medical service department provides the patient with the audio translated by the medical translation department. For example, the translated text data is played back as audio using speech synthesis technology. The medical service department can also display the translation results on a screen.

[0079] (Example of form 2) The multilingual translation and interpretation system according to an embodiment of the present invention is a platform that utilizes generative AI to facilitate communication between foreign patients and medical professionals in medical settings. This system removes language barriers and enables the provision of appropriate medical services to foreign patients. At the same time, it improves the internationalization capabilities of medical institutions and contributes to the realization of a global medical environment. For example, it provides a real-time voice translation function. The generative AI translates what the patient says in real time and conveys it to the medical professional. Conversely, the generative AI also translates what the medical professional says in real time and conveys it to the patient. This removes language barriers and enables smooth communication. Next, it is equipped with a high-precision translation engine specializing in medical terminology. The generative AI translates medical terms and specialized terms that are difficult for general translation engines to handle with high precision. This reduces the risk of misdiagnosis and treatment delays and enables the provision of appropriate medical services. Furthermore, it is equipped with a multilingual questionnaire and consent form generation system. Patients can fill out questionnaires and consent forms in their own language, and the generative AI translates them into the medical professional's language. This reduces the burden on patients and allows medical professionals to obtain accurate information. Furthermore, the system will also offer integration with remote medical interpretation services. The AI ​​will not only provide real-time translations but will also collaborate with remote medical interpreters as needed to offer more advanced interpretation services. This will reduce the burden on medical institutions and improve their ability to serve foreign patients. This system is urgently needed due to factors such as the increasing number of foreign visitors to Japan, the diversification of foreign residents, the rapid advancements in AI technology, the growing demand associated with the globalization of healthcare, and the spread of telemedicine due to the COVID-19 pandemic. The system aims to provide high-quality medical services that transcend language and cultural barriers, improve the internationalization capabilities of medical institutions, enhance access to medical care and foster a sense of security for foreign patients, and reduce the burden on healthcare professionals while improving operational efficiency. As a result, the multilingual translation and interpretation system will enable smooth communication between foreign patients and healthcare professionals, allowing for the provision of appropriate medical services.

[0080] The multilingual translation and interpretation system according to this embodiment comprises a reception unit, a translation unit, a provision unit, a medical reception unit, a medical translation unit, and a medical provision unit. The reception unit receives the patient's voice. The reception unit, for example, receives the words spoken by the patient using a microphone and stores them as voice data. The reception unit can also convert the voice data into text data using speech recognition technology. For example, the reception unit analyzes the voice using speech recognition software and stores it as text data. The translation unit translates the voice received by the reception unit using a generation AI. The translation unit, for example, uses a generation AI to analyze the voice data and translate it into another language. The translation unit can also translate medical terms and technical terms with high accuracy. For example, the generation AI performs translation while referring to a medical terminology dictionary. The provision unit provides the voice translated by the translation unit to medical personnel. The provision unit, for example, plays back the translated text data as voice using speech synthesis technology. The provision unit can also display the translation results on a display. For example, the delivery department displays the translated text data on a screen for medical professionals to review. The medical reception department receives the voice of medical professionals. For example, the medical reception department receives the words spoken by medical professionals using a microphone and saves them as audio data. The medical reception department can also convert the audio data into text data using speech recognition technology. For example, the medical reception department analyzes the voice using speech recognition software and saves it as text data. The medical translation department translates the voice received by the medical reception department using generative AI. For example, the medical translation department uses generative AI to analyze the audio data and translate it into another language. The medical translation department can also translate medical terms and technical terms with high accuracy. For example, the generative AI performs translations while referring to a medical terminology dictionary. The medical delivery department provides the voice translated by the medical translation department to the patient. For example, the medical delivery department plays back the translated text data as audio using speech synthesis technology. The medical delivery department can also display the translation results on a display. For example, the medical delivery department displays the translated text data on a screen for the patient to review.As a result, the multilingual translation and interpretation system according to this embodiment can translate speech in real time between patients and healthcare professionals, enabling smooth communication.

[0081] The reception area receives patient voices. For example, the reception area receives the patient's spoken words using a microphone and saves them as audio data. Specifically, the reception area uses a high-sensitivity microphone to clearly capture the patient's voice. The audio data is processed using noise reduction technology to remove background noise and improve the accuracy of speech recognition. The speech recognition technology uses a deep learning model to convert the patient's pronunciation and accent differences into text data with high accuracy. For example, the speech recognition software analyzes the patient's voice in real time and saves it as text data. This allows the reception area to quickly and accurately convert the patient's voice into text data and smoothly hand it over to the next processing step. Furthermore, the reception area has a database for storing and managing audio data, and can refer to past audio data. This allows for reviewing the patient's past statements and symptoms, enabling more appropriate responses.

[0082] The translation department uses generative AI to translate audio received by the reception department. Specifically, the generative AI analyzes the audio data and translates it into other languages. The generative AI utilizes natural language processing technology to convert the audio data into text data, and then translates that text data into the target language. For example, the generative AI uses speech recognition technology to convert audio into text data and inputs that text data into a multilingual translation model. The multilingual translation model has been pre-trained on a large amount of medical and technical terms, enabling highly accurate translations. Because the generative AI performs translations while referring to a medical terminology dictionary, it can accurately translate specialized terms and expressions. Furthermore, the generative AI uses contextual analysis technology to understand the context and provide appropriate translations. As a result, the translation department can accurately and naturally translate patients' statements into other languages ​​and provide them to healthcare professionals.

[0083] The service provider delivers the translated audio to healthcare professionals. Specifically, it plays back the translated text data as audio using speech synthesis technology. The speech synthesis technology generates audio with natural pronunciation and intonation, providing it in a format that is easy for healthcare professionals to understand. For example, the service provider inputs the translated text data into a speech synthesis engine and plays the generated audio through a speaker. The service provider can also display the translation results on a screen. The screen displays the translated text data in an easy-to-read font and size, allowing healthcare professionals to quickly review it. Furthermore, the service provider can automatically record the translation results in the electronic medical record system and save them as part of the patient's medical history. This enables the service provider to provide healthcare professionals with timely and accurate information and support smooth communication.

[0084] The medical reception department receives voice messages from medical professionals. Specifically, it captures the words spoken by medical professionals using a microphone and saves them as audio data. The medical reception department can also convert the audio data into text data using speech recognition technology. For example, the medical reception department uses a high-sensitivity microphone to collect the voices of medical professionals and removes background noise using noise reduction technology. The speech recognition technology uses a deep learning model to convert the pronunciation and technical terms of medical professionals into text data with high accuracy. This allows the medical reception department to quickly and accurately convert the voices of medical professionals into text data and smoothly hand it over to the next processing step. Furthermore, the medical reception department has a database for storing and managing audio data, and can refer to past audio data. This makes it possible to check past statements and instructions from medical professionals and respond more appropriately.

[0085] The medical translation department uses generative AI to translate audio received by the medical reception department. Specifically, the generative AI analyzes the audio data and translates it into other languages. The generative AI utilizes natural language processing technology to convert the audio data into text data, and then translates that text data into the target language. For example, the generative AI uses speech recognition technology to convert audio into text data and inputs that text data into a multilingual translation model. The multilingual translation model has been pre-trained on a large amount of medical and technical terms, enabling highly accurate translations. Because the generative AI performs translations while referring to a medical terminology dictionary, it can accurately translate specialized terms and expressions. Furthermore, the generative AI uses contextual analysis technology to understand the context and provide appropriate translations. As a result, the medical translation department can accurately and naturally translate the statements of medical professionals into other languages ​​and provide them to patients.

[0086] The medical service department provides patients with audio translated by the medical translation department. Specifically, the translated text data is played back as audio using speech synthesis technology. Speech synthesis technology generates audio with natural pronunciation and intonation, providing it in a way that is easy for patients to understand. For example, the medical service department inputs the translated text data into a speech synthesis engine and plays the generated audio through a speaker. The medical service department can also display the translation results on a screen. The translated text data is displayed on the screen in an easy-to-read font and size, allowing patients to quickly review it. Furthermore, the medical service department can automatically record the translation results in the electronic medical record system and save them as part of the patient's medical history. This allows the medical service department to provide patients with timely and accurate information and support smooth communication.

[0087] The generation unit can generate medical questionnaires and consent forms. For example, the generation unit uses a generation AI to generate medical questionnaires and consent forms filled out by the patient in their own language. The generation unit uses the generation AI to analyze the patient's input data and generate the medical questionnaires and consent forms in an appropriate format. The generation unit can also use the generation AI to translate medical and technical terms with high accuracy. For example, the generation unit uses the generation AI to perform translations while referring to a medical terminology dictionary. This allows patients to fill out medical questionnaires and consent forms in their own language. Medical questionnaires and consent forms may include, but are not limited to, basic patient information, medical history, allergy information, and current symptoms. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the medical questionnaire and consent form filled out by the patient into the generation AI, which can then generate them in an appropriate format.

[0088] The generation unit can translate questionnaires and consent forms filled out by patients in their own language into the language of healthcare professionals. For example, the generation unit uses a generation AI to analyze the questionnaires and consent forms filled out by patients and translate them into the language of healthcare professionals. The generation unit can also use the generation AI to translate medical and technical terms with high accuracy. For example, the generation unit performs translation while the generation AI refers to a medical terminology dictionary. This allows healthcare professionals to understand the information filled out by patients. The translation includes, but is not limited to, basic patient information, medical history, allergy information, and current symptoms. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input questionnaires and consent forms filled out by patients into a generation AI, which can then translate them into the language of healthcare professionals.

[0089] The generation unit can translate medical terms and technical terms with high accuracy. The generation unit analyzes medical terms and technical terms using, for example, a generation AI and translates them with high accuracy. The generation unit performs translation while the generation AI refers to a medical terminology dictionary. This prevents mistranslation of medical terms and technical terms. Translations include, but are not limited to, diagnoses, treatments, drug names, and test results. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input medical terms and technical terms into a generation AI, which can then translate them with high accuracy.

[0090] The collaboration unit can collaborate with remote medical interpretation services. For example, the collaboration unit can use a generative AI to collaborate with remote medical interpreters and provide interpretation services. The collaboration unit can also use the generative AI to select the most suitable interpreter, taking into account their expertise and experience. For example, the collaboration unit can use the generative AI to select interpreters by referring to their qualifications and past interpretation history. This allows the collaboration with remote medical interpreters to provide more advanced interpretation services. Collaboration includes, but is not limited to, methods such as video calls, voice calls, and chat. Some or all of the processing described above in the collaboration unit may be performed using, for example, a generative AI, or without one. For example, the collaboration unit can input information about remote medical interpreters into the generative AI, which can then select the most suitable interpreter.

[0091] The collaboration unit can provide interpretation services by collaborating with remote medical interpreters as needed. For example, the collaboration unit can use a generative AI to select the most suitable interpreter based on the patient's situation and then collaborate with them. The collaboration unit can also use the generative AI to analyze the patient's symptoms and urgency to select an appropriate interpreter. For example, the collaboration unit can use the generative AI to select an interpreter based on the patient's medical history and current symptoms. This allows the unit to collaborate with remote medical interpreters as needed and provide interpretation services. Collaboration includes, but is not limited to, methods such as video calls, voice calls, and chat. Some or all of the above-described processes in the collaboration unit may be performed using, for example, a generative AI, or without one. For example, the collaboration unit can input patient information into the generative AI, which can then select the most suitable interpreter.

[0092] The reception desk can estimate the patient's emotions and adjust the timing of voice reception based on the estimated emotions. The reception desk can estimate emotions from the patient's facial expressions and voice, for example, using an emotion estimation algorithm. For example, if the reception desk is tense, it can delay voice reception until the patient relaxes. Conversely, if the patient is anxious, it can quickly receive voice reception. Furthermore, if the patient is calm, it can receive voice reception at the normal timing. This allows for more appropriate responses by adjusting the timing of voice reception according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. 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 reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the patient's facial expression data into a generative AI, which can then estimate emotions.

[0093] The reception desk can analyze the patient's past voice data and select the optimal voice reception method. For example, the reception desk can use AI to analyze the patient's past voice data and propose the optimal voice reception method. For example, the reception desk can analyze the voice input methods the patient has used in the past and select the optimal method. The reception desk can also select the method that resulted in the smoothest reception from the patient's past voice data. Furthermore, the reception desk can analyze the quality of the patient's voice data and select the optimal voice reception method. Thus, by analyzing the patient's past voice data, the optimal voice reception method can be selected. The optimal voice reception method includes, but is not limited to, voice recognition technology, voice input devices, and voice input timing. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can input the patient's past voice data into AI, which can then select the optimal voice reception method.

[0094] The reception desk can filter voice messages based on the patient's current health status and symptoms. For example, the reception desk can use AI to analyze the patient's health status and symptoms and prioritize receiving important information. For instance, if the patient's health is poor, the AI ​​will filter the voice message and prioritize receiving important information. Similarly, if the patient's symptoms are severe, the AI ​​can filter the voice message and prioritize receiving urgent information. Furthermore, if the patient's health is good, the reception desk can receive normal information. This allows for the prioritization of important information based on the patient's health status and symptoms. Filtering includes, but is not limited to, voice recognition technology, voice analysis algorithms, and health status assessment criteria. Some or all of the above processing in the reception desk may be performed using, for example, AI, or without AI. For example, the reception desk can input patient health data into the AI, which can then filter important information.

[0095] The reception desk can estimate the patient's emotions and determine the priority of the voice messages to receive based on the estimated emotions. The reception desk can estimate emotions from the patient's facial expressions and voice, for example, using an emotion estimation algorithm. For example, if the patient is feeling anxious, the reception desk will prioritize receiving reassuring voice messages. Similarly, if the patient is angry, the reception desk can prioritize receiving calming voice messages. Furthermore, if the patient is sad, the reception desk can prioritize receiving comforting voice messages. This allows for more appropriate responses by prioritizing voice messages according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. 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 reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the patient's facial expression data into a generative AI, which can then estimate the emotions.

[0096] The reception desk can prioritize receiving voice messages that are highly relevant, taking into account the patient's geographical location. For example, the reception desk can use AI to analyze the patient's geographical location and prioritize receiving highly relevant voice messages. For instance, if the patient is near the hospital, the reception desk will prioritize receiving urgent voice messages. If the patient is far away, the reception desk can also prioritize receiving voice messages related to telemedicine. Furthermore, if the patient is in a specific region, the reception desk can prioritize receiving voice messages related to that region. This allows for the prioritization of highly relevant voice messages by considering the patient's geographical location. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the reception desk may be performed using, for example, AI, or without AI. For example, the reception desk can input the patient's geographical information into the AI, which can then prioritize receiving highly relevant voice messages.

[0097] The reception desk can analyze the patient's social media activity when receiving voice messages and receive relevant messages. For example, the reception desk can use AI to analyze the patient's social media activity and prioritize receiving relevant messages. For instance, the reception desk can analyze health-related posts from the patient's social media activity and prioritize receiving relevant messages. The reception desk can also analyze recent activity from the patient's social media activity and prioritize receiving relevant messages. Furthermore, the reception desk can analyze the patient's interests from their social media activity and prioritize receiving relevant messages. This allows for the priority reception of relevant messages by analyzing the patient's social media activity. Social media activity includes, but is not limited to, analysis of post content and methods for evaluating relevance. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the patient's social media data into AI, which can then prioritize receiving relevant messages.

[0098] The translation unit can estimate the patient's emotions and adjust the translation's expression based on the estimated emotions. For example, the translation unit might use an emotion estimation algorithm to estimate emotions from the patient's facial expressions and voice. For instance, if the patient is anxious, the translation unit might use gentle, reassuring language. Similarly, if the patient is angry, it might use calming language. Furthermore, if the patient is sad, it might use comforting language. This allows for more appropriate translations 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 generative AI. Generative AI may include, 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, for example, a generative AI, or not. For example, the translation unit could input patient facial data into a generative AI, which could then estimate emotions and adjust the translation's expression.

[0099] The translation unit can adjust the level of detail in translations based on the importance of medical terms during the translation process. For example, the translation unit can use generative AI to analyze the importance of medical terms and adjust the level of detail in the translation. For instance, the translation unit can provide detailed translations for important medical terms. It can also provide concise translations for common medical terms. Furthermore, it can provide specialized translations for specialized medical terms. By adjusting the level of detail in translations based on the importance of medical terms, appropriate translations are provided. The evaluation of importance includes, but is not limited to, the frequency of medical terms and the method of evaluating importance. Some or all of the above processing in the translation unit may be performed using, for example, generative AI, or without generative AI. For example, the translation unit can input medical term data into generative AI, which can evaluate importance and adjust the level of detail in the translation.

[0100] The translation unit can apply different translation algorithms during translation depending on the patient's symptoms and medical history. For example, the translation unit can use a generative AI to analyze the patient's symptoms and medical history and select an appropriate translation algorithm. For instance, if the patient's symptoms are severe, the translation unit can apply a detailed translation algorithm. It can also apply a specialized translation algorithm if the patient's medical history is complex. Furthermore, if the patient's symptoms are mild, the translation unit can apply a concise translation algorithm. This ensures that more accurate translations are provided by applying the appropriate translation algorithm according to the patient's symptoms and medical history. Examples of different translation algorithms include, but are not limited to, criteria for selecting an algorithm based on symptoms and medical history. Some or all of the above-described processes in the translation unit may be performed using, for example, a generative AI, or without one. For example, the translation unit can input patient symptom and medical history data into a generative AI, which can then select an appropriate translation algorithm.

[0101] The translation unit can estimate the patient's emotions and adjust the length of the translation based on the estimated emotions. For example, the translation unit can estimate emotions from the patient's facial expressions and voice using an emotion estimation algorithm. For instance, if the patient is in a hurry, the translation unit can provide a short, concise translation. It can also provide a detailed translation if the patient is relaxed. Furthermore, if the patient is agitated, the translation unit can provide a visually stimulating translation. This allows for more appropriate translations by adjusting the length of the translation according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, 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, for example, a generative AI, or not. For example, the translation unit can input patient facial expression data into a generative AI, which can estimate emotions and adjust the length of the translation.

[0102] The translation unit can determine translation priorities based on the submission date of the audio during the translation process. For example, the translation unit may use a generative AI to analyze the submission date and determine translation priorities. For instance, the translation unit may prioritize translating recently submitted audio. It may also prioritize translating audio with high urgency. Furthermore, the translation unit may postpone the translation of older audio. This allows for prioritizing the translation of audio with high urgency by determining translation priorities based on the submission date. Prioritization includes, but is not limited to, evaluation criteria for submission date and priority determination algorithms. Some or all of the above-described processes in the translation unit may be performed, for example, using a generative AI, or without a generative AI. For example, the translation unit may input audio data into a generative AI, which may evaluate the submission date and determine translation priorities.

[0103] The translation unit can adjust the order of translations based on the relevance of the audio during the translation process. For example, the translation unit may use a generative AI to analyze the relevance of the audio and adjust the order of translations. For example, the translation unit may prioritize translating audio related to the patient's symptoms. It may also prioritize translating audio related to the medical professional's area of ​​expertise. Furthermore, it may prioritize translating audio of high urgency. This allows important audio to be prioritized for translation by adjusting the order of translations based on the relevance of the audio. The evaluation of relevance includes, but is not limited to, the content of the audio and the method of evaluating relevance. Some or all of the above processing in the translation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the translation unit may input audio data into a generative AI, which may evaluate the relevance and adjust the order of translations.

[0104] The service provider can estimate the patient's emotions and adjust the method of providing the translation results based on the estimated emotions. For example, the service provider can estimate emotions from the patient's facial expressions and voice using an emotion estimation algorithm. For example, if the patient is feeling anxious, the service provider can provide the translation results in a gentle voice to reassure them. If the patient is angry, the service provider can also provide the translation results in a calm voice to calm them down. Furthermore, if the patient is sad, the service provider can provide the translation results in a warm voice to comfort them. This allows for a more appropriate response by adjusting the method of providing the translation results according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 service provider may be performed using AI, for example, or without AI. For example, the service provider can input the patient's facial expression data into the generative AI, which can estimate emotions and adjust the method of providing the translation results.

[0105] The service delivery unit can select the optimal delivery method by referring to the past interaction history of healthcare professionals at the time of delivery. The service delivery unit can, for example, use AI to analyze the past interaction history of healthcare professionals and propose the optimal delivery method. For example, the service delivery unit can refer to delivery methods previously used by healthcare professionals and select the optimal method. The service delivery unit can also select the most effective delivery method from the past interaction history of healthcare professionals. Furthermore, the service delivery unit can analyze the past interaction history of healthcare professionals and select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the past interaction history of healthcare professionals. The optimal delivery method includes, but is not limited to, selection criteria and evaluation methods for delivery methods. Some or all of the above processing in the service delivery unit may be performed using, for example, AI, or not using AI. For example, the service delivery unit can input healthcare professional interaction history data into AI, and the AI ​​can select the optimal delivery method.

[0106] The information delivery unit can customize the means of delivery based on the patient's current health condition at the time of delivery. For example, the information delivery unit can use AI to analyze the patient's health condition and customize the means of delivery. For example, if the patient's health condition is poor, the information delivery unit will prioritize providing important information. The information delivery unit can also provide normal information if the patient's health condition is good. Furthermore, if the patient's health condition is unstable, the information delivery unit can provide urgent information. By customizing the means of delivery according to the patient's health condition, more appropriate information can be provided. Customization includes, but is not limited to, health condition evaluation criteria and customization methods. Some or all of the above processing in the information delivery unit may be performed using, for example, AI, or not using AI. For example, the information delivery unit can input patient health condition data into AI, and the AI ​​can customize the means of delivery.

[0107] The service provider can estimate the patient's emotions and determine the priority of translation results based on the estimated emotions. For example, the service provider can estimate emotions from the patient's facial expressions and voice using an emotion estimation algorithm. For example, if the patient is feeling anxious, the service provider can prioritize providing reassuring translation results. If the patient is angry, the service provider can also prioritize providing calming translation results. Furthermore, if the patient is sad, the service provider can prioritize providing comforting translation results. This allows for more appropriate responses by prioritizing translation results according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 service provider may be performed using AI, or not using AI. For example, the service provider can input patient facial expression data into a generative AI, which can estimate emotions and determine the priority of translation results.

[0108] The service provider can select the optimal delivery method by considering the patient's geographical location information at the time of delivery. For example, the service provider can use AI to analyze the patient's geographical location information and select the optimal delivery method. For example, if the patient is near a hospital, the service provider can prioritize providing information with high urgency. The service provider can also prioritize providing information related to telemedicine if the patient is far away. Furthermore, if the service provider is in a specific region, the service provider can prioritize providing information relevant to that region. In this way, the optimal delivery method can be selected by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the service provider may be performed using, for example, AI, or without AI. For example, the service provider can input the patient's geographical information into AI, and the AI ​​can select the optimal delivery method.

[0109] The service provider can analyze the patient's social media activity and propose a means of delivery at the time of delivery. For example, the service provider can use AI to analyze the patient's social media activity and prioritize the provision of relevant information. For example, the service provider can analyze health-related posts from the patient's social media activity and prioritize the provision of relevant information. The service provider can also analyze recent activities from the patient's social media activity and prioritize the provision of relevant information. Furthermore, the service provider can analyze interests from the patient's social media activity and prioritize the provision of relevant information. In this way, relevant information can be prioritized by analyzing the patient's social media activity. Social media activity includes, but is not limited to, examples such as analysis of post content and methods for evaluating relevance. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the patient's social media data into AI, and the AI ​​can prioritize the provision of relevant information.

[0110] The medical reception desk can estimate the emotions of medical professionals and adjust the timing of voice reception based on the estimated emotions. The medical reception desk can estimate emotions from the facial expressions and voice of medical professionals, for example, using an emotion estimation algorithm. For example, if a medical professional is tired, the medical reception desk can accept voice calls after a break. Also, if a medical professional is busy, the medical reception desk can accept voice calls quickly. Furthermore, if a medical professional is relaxed, the medical reception desk can accept voice calls at the normal timing. This allows for more appropriate responses by adjusting the timing of voice reception according to the emotions of medical professionals. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 medical reception desk may be performed using AI, for example, or without AI. For example, the medical reception department can input facial expression data of medical staff into a generating AI, which can then estimate emotions and adjust the timing of voice reception.

[0111] The medical reception department can analyze the past voice data of medical staff and select the optimal voice reception method. For example, the medical reception department can use AI to analyze the past voice data of medical staff and propose the optimal voice reception method. For example, the medical reception department can analyze the voice input methods previously used by medical staff and select the optimal method. Furthermore, the medical reception department can select the method that resulted in the smoothest reception from the medical staff's past voice data. In addition, the medical reception department can analyze the quality of the medical staff's voice data and select the optimal voice reception method. Thus, by analyzing the medical staff's past voice data, the optimal voice reception method can be selected. The optimal voice reception method includes, but is not limited to, voice recognition technology, voice input devices, and voice input timing. Some or all of the above processing in the medical reception department may be performed using, for example, AI, or not using AI. For example, the medical reception department can input the medical staff's past voice data into AI, and the AI ​​can select the optimal voice reception method.

[0112] The medical reception department can filter voice calls based on the expertise and experience of the medical professionals. For example, the medical reception department can use AI to analyze the expertise and experience of medical professionals and prioritize important voice calls. For instance, the medical reception department can prioritize voice calls related to the medical professional's area of ​​expertise. It can also prioritize important voice calls based on the medical professional's experience. Furthermore, the medical reception department can prioritize urgent voice calls based on the medical professional's expertise and experience. This allows for the prioritization of important voice calls based on the medical professional's expertise and experience. Filtering includes, but is not limited to, evaluation criteria for expertise and experience, and filtering algorithms. Some or all of the above processing in the medical reception department may be performed using, for example, AI, or not. For example, the medical reception department can input data on the medical professionals' areas of expertise and experience into the AI, which can then filter important voice calls.

[0113] The medical reception desk can estimate the emotions of medical professionals and determine the priority of incoming calls based on the estimated emotions. For example, the medical reception desk might use an emotion estimation algorithm to estimate emotions from the medical professional's facial expressions and voice. For instance, if a medical professional is tired, the reception desk might prioritize important calls. Similarly, if a medical professional is busy, it might prioritize urgent calls. Furthermore, if a medical professional is relaxed, it might accept normal calls. This allows for more appropriate responses by prioritizing calls according to the medical professional's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, 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 medical reception desk may be performed using AI, or not. For example, the medical reception department can input facial expression data of medical staff into a generating AI, which can then estimate emotions and determine the priority of voice messages.

[0114] The medical reception department can prioritize receiving voice calls by considering the geographical location information of healthcare professionals. For example, the medical reception department can use AI to analyze the geographical location information of healthcare professionals and prioritize receiving relevant voice calls. For instance, if a healthcare professional is within the hospital, the medical reception department will prioritize receiving urgent voice calls. Furthermore, if a healthcare professional is located far away, the medical reception department can prioritize receiving voice calls related to telemedicine. Additionally, if a healthcare professional is in a specific region, the medical reception department can prioritize receiving voice calls related to that region. This allows for the prioritization of highly relevant voice calls by considering the geographical location information of healthcare professionals. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the medical reception department may be performed using, for example, AI, or without AI. For example, the medical reception department can input the geographical information of healthcare professionals into AI, which can then prioritize receiving highly relevant voice calls.

[0115] The medical reception department can analyze the social media activity of healthcare workers when receiving voice calls and receive relevant voice calls. For example, the medical reception department can use AI to analyze the social media activity of healthcare workers and prioritize receiving relevant voice calls. For instance, the medical reception department can analyze posts related to healthcare from the social media activity of healthcare workers and prioritize receiving relevant voice calls. Furthermore, the medical reception department can analyze recent activity from the social media activity of healthcare workers and prioritize receiving relevant voice calls. In addition, the medical reception department can analyze interests from the social media activity of healthcare workers and prioritize receiving relevant voice calls. This allows for the prioritization of relevant voice calls by analyzing the social media activity of healthcare workers. Social media activity includes, but is not limited to, analysis of post content and methods for evaluating relevance. Some or all of the above processing in the medical reception department may be performed using AI, for example, or without AI. For example, the medical reception department can input the social media data of healthcare workers into AI, which can then prioritize receiving relevant voice calls.

[0116] The medical translation department can estimate the emotions of healthcare workers and adjust the translation's expression based on the estimated emotions. For example, the medical translation department might use an emotion estimation algorithm to estimate emotions from the healthcare worker's facial expressions and voice. For instance, if the healthcare worker is tired, the medical translation department might use concise language. If the healthcare worker is busy, it might use language that can be quickly understood. Furthermore, if the healthcare worker is relaxed, it might use detailed language. This allows for more appropriate translations by adjusting the translation's expression according to the healthcare worker's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, 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 medical translation department may be performed using, for example, generative AI, or without generative AI. For example, the medical translation department can input facial expression data of medical professionals into a generating AI, which can then estimate emotions and adjust the translation's expression accordingly.

[0117] The medical translation department can adjust the level of detail in translations based on the importance of medical terms. For example, the medical translation department might use generative AI to analyze the importance of medical terms and adjust the level of detail. For instance, it might provide detailed translations for important medical terms, concise translations for common terms, and specialized translations for specialized medical terms. This ensures that appropriate translations are provided by adjusting the level of detail based on the importance of medical terms. The evaluation of importance includes, but is not limited to, the frequency of medical terms and methods for evaluating importance. Some or all of the above-described processes in the medical translation department may be performed using, for example, generative AI, or without it. For example, the medical translation department could input medical term data into a generative AI, which could then evaluate importance and adjust the level of detail.

[0118] The medical translation department can apply different translation algorithms during translation depending on the medical professional's area of ​​expertise and experience. For example, the medical translation department can use generative AI to analyze the medical professional's area of ​​expertise and experience and select an appropriate translation algorithm. For instance, if the medical professional specializes in internal medicine, the department will apply a translation algorithm specifically for internal medicine. Similarly, if the medical professional specializes in surgery, the department can apply a translation algorithm specifically for surgery. Furthermore, if the medical professional has extensive experience, the department can apply a more detailed translation algorithm. This ensures that more accurate translations are provided by applying the appropriate translation algorithm according to the medical professional's area of ​​expertise and experience. Examples of different translation algorithms include, but are not limited to, criteria for selecting algorithms based on area of ​​expertise and experience. Some or all of the above-described processes in the medical translation department may be performed using, for example, generative AI, or without generative AI. For example, the medical translation department can input data on the medical professional's area of ​​expertise and experience into a generative AI, which can then select an appropriate translation algorithm.

[0119] The medical translation department can estimate the emotions of healthcare workers and adjust the length of the translation based on the estimated emotions. For example, the medical translation department uses an emotion estimation algorithm to estimate emotions from the healthcare worker's facial expressions and voice. For instance, if the healthcare worker is in a hurry, the medical translation department can provide a short, concise translation. If the healthcare worker is relaxed, it can provide a detailed translation. Furthermore, if the healthcare worker is agitated, it can provide a visually stimulating translation. By adjusting the length of the translation according to the healthcare worker's emotions, a more appropriate translation can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, 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 medical translation department may be performed using, for example, generative AI, or without generative AI. For example, the medical translation department can input facial expression data of medical professionals into a generating AI, which can then estimate emotions and adjust the length of the translation.

[0120] The medical translation department can prioritize translations based on the submission date of the audio. For example, the medical translation department might use a generative AI to analyze the submission date and determine the translation priority. For instance, the medical translation department might prioritize translating recently submitted audio. It could also prioritize translating audio with high urgency. Furthermore, it could postpone the translation of older audio. This allows for prioritizing the translation of audio with high urgency based on the submission date. Prioritization includes, but is not limited to, evaluation criteria for submission date and priority determination algorithms. Some or all of the above-described processes in the medical translation department may be performed, for example, using a generative AI, or without one. For example, the medical translation department could input audio data into a generative AI, which would then evaluate the submission date and determine the translation priority.

[0121] The medical translation department can adjust the order of translations based on the relevance of the audio during the translation process. For example, the medical translation department may use generative AI to analyze the relevance of the audio and adjust the translation order. For instance, the medical translation department may prioritize translating audio related to the patient's symptoms. It may also prioritize translating audio related to the medical professional's area of ​​expertise. Furthermore, it may prioritize translating audio of high urgency. This allows for the prioritization of important audio by adjusting the translation order based on the relevance of the audio. Relevance evaluation includes, but is not limited to, the content of the audio and the method of evaluating relevance. Some or all of the above-described processes in the medical translation department may be performed, for example, using generative AI, or without generative AI. For example, the medical translation department can input audio data into a generative AI, which can then evaluate relevance and adjust the translation order.

[0122] The healthcare delivery unit can estimate the emotions of healthcare workers and adjust the method of providing translation results based on the estimated emotions of the healthcare workers. For example, the healthcare delivery unit can estimate emotions from the facial expressions and voice of healthcare workers using an emotion estimation algorithm. For example, if a healthcare worker is tired, the healthcare delivery unit can provide a concise translation result. Also, if a healthcare worker is busy, the healthcare delivery unit can provide a translation result that can be quickly understood. Furthermore, if a healthcare worker is relaxed, the healthcare delivery unit can provide a detailed translation result. This allows for more appropriate responses by adjusting the method of providing translation results according to the emotions of the healthcare workers. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 healthcare delivery unit may be performed using AI, for example, or not using AI. For example, the medical service department can input facial expression data of medical professionals into a generating AI, which can then estimate emotions and adjust the method of providing the translation results.

[0123] The healthcare delivery department can select the optimal delivery method by referring to the patient's past interaction history at the time of delivery. The healthcare delivery department can, for example, use AI to analyze the patient's past interaction history and propose the optimal delivery method. For example, the healthcare delivery department can refer to the patient's past interaction history and select the optimal method. The healthcare delivery department can also select the most effective delivery method from the patient's past interaction history. Furthermore, the healthcare delivery department can analyze the patient's past interaction history and select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the patient's past interaction history. The optimal delivery method includes, but is not limited to, selection criteria and evaluation methods for the delivery method. Some or all of the above processing in the healthcare delivery department may be performed using, for example, AI, or not using AI. For example, the healthcare delivery department can input patient interaction history data into AI, and the AI ​​can select the optimal delivery method.

[0124] The healthcare delivery department can customize the means of delivery based on the expertise and experience of healthcare professionals at the time of delivery. For example, the healthcare delivery department can use AI to analyze the expertise and experience of healthcare professionals and customize the means of delivery. For example, if a healthcare professional's area of ​​expertise is internal medicine, the healthcare delivery department will customize the means of delivery to be specialized for internal medicine. Furthermore, if a healthcare professional's area of ​​expertise is surgery, the healthcare delivery department can customize the means of delivery to be specialized for surgery. In addition, if a healthcare professional has extensive experience, the healthcare delivery department can customize the means of delivery in more detail. This allows for the provision of more appropriate information by customizing the means of delivery based on the expertise and experience of healthcare professionals. Customization includes, but is not limited to, evaluation criteria for expertise and experience, and methods of customization. Some or all of the above-described processes in the healthcare delivery department may be performed using, for example, AI, or not. For example, the healthcare delivery department can input data on the expertise and experience of healthcare professionals into AI, which can then customize the means of delivery.

[0125] The healthcare delivery unit can estimate the emotions of healthcare workers and prioritize translation results based on the estimated emotions. For example, the healthcare delivery unit might use an emotion estimation algorithm to estimate emotions from the healthcare worker's facial expressions and voice. For instance, if a healthcare worker is tired, the unit might prioritize important translation results. Similarly, if a healthcare worker is busy, the unit might prioritize urgent translation results. Furthermore, if a healthcare worker is relaxed, the unit might provide standard translation results. This allows for more appropriate responses by prioritizing translation results according to the healthcare worker's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the healthcare delivery unit may be performed using AI, or not. For example, the medical service department can input facial expression data of medical professionals into a generating AI, which can then estimate emotions and determine the priority of translation results.

[0126] The healthcare delivery department can select the optimal delivery method by considering the geographical location information of healthcare workers at the time of delivery. For example, the healthcare delivery department can use AI to analyze the geographical location information of healthcare workers and select the optimal delivery method. For example, if healthcare workers are in the hospital, the healthcare delivery department can prioritize providing information of high urgency. Also, if healthcare workers are in a remote location, the healthcare delivery department can prioritize providing information related to that region. In addition, if healthcare workers are in a specific region, the healthcare delivery department can prioritize providing information related to that region. In this way, the optimal delivery method can be selected by considering the geographical location information of healthcare workers. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the healthcare delivery department may be performed using, for example, AI, or not using AI. For example, the healthcare delivery department can input the geographical information of healthcare workers into AI, and the AI ​​can select the optimal delivery method.

[0127] The healthcare delivery department can analyze the social media activity of healthcare professionals and propose delivery methods at the time of delivery. For example, the healthcare delivery department can use AI to analyze the social media activity of healthcare professionals and provide relevant information preferentially. For example, the healthcare delivery department can analyze posts related to medicine from the social media activity of healthcare professionals and provide relevant information preferentially. The healthcare delivery department can also analyze recent activity from the social media activity of healthcare professionals and provide relevant information preferentially. Furthermore, the healthcare delivery department can analyze interests from the social media activity of healthcare professionals and provide relevant information preferentially. In this way, relevant information can be provided preferentially by analyzing the social media activity of healthcare professionals. Social media activity includes, but is not limited to, examples such as analysis of post content and methods for evaluating relevance. Some or all of the above processing in the healthcare delivery department may be performed using AI, for example, or without AI. For example, the healthcare delivery department can input the social media data of healthcare professionals into AI, and the AI ​​can provide relevant information preferentially.

[0128] The generation unit can estimate the patient's emotions and adjust the generation method of questionnaires and consent forms based on the estimated emotions. For example, the generation unit estimates emotions from the patient's facial expressions and voice using an emotion estimation algorithm. For example, if the patient is feeling anxious, the generation unit can generate a concise and easy-to-understand questionnaire. If the patient is relaxed, the generation unit can also generate a detailed questionnaire. Furthermore, if the patient is in a hurry, the generation unit can generate a questionnaire that can be completed in a short time. This allows for more appropriate responses by adjusting the generation method of questionnaires and consent forms according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 generation unit may be performed using a generation AI, or not. For example, the generation unit can input patient facial expression data into a generation AI, which can estimate emotions and adjust the generation method of questionnaires and consent forms.

[0129] The generation unit can adjust the level of detail of the generated documents based on the importance of the medical terms during the generation process. For example, the generation unit can use a generation AI to analyze the importance of medical terms and adjust the level of detail of the generated documents. For example, the generation unit can generate questionnaires that include detailed explanations for important medical terms. The generation unit can also generate questionnaires that include concise explanations for common medical terms. Furthermore, the generation unit can generate questionnaires that include specialized explanations for specialized medical terms. By adjusting the level of detail of the generated documents based on the importance of the medical terms, appropriate questionnaires and consent forms are generated. The evaluation of importance includes, but is not limited to, the frequency of medical terms and the method of evaluating importance. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input medical term data into a generation AI, which can evaluate importance and adjust the level of detail of the generated documents.

[0130] The generation unit can apply different generation algorithms during generation depending on the patient's symptoms and medical history. For example, the generation unit uses a generation AI to analyze the patient's symptoms and medical history and select an appropriate generation algorithm. For example, if the patient's symptoms are severe, the generation unit applies a detailed generation algorithm. The generation unit can also apply a specialized generation algorithm if the patient's medical history is complex. Furthermore, if the patient's symptoms are mild, the generation unit can apply a concise generation algorithm. By applying an appropriate generation algorithm according to the patient's symptoms and medical history, more accurate questionnaires and consent forms are generated. Different generation algorithms include, but are not limited to, criteria for selecting an algorithm based on symptoms and medical history. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input patient symptom and medical history data into a generation AI, which can then select an appropriate generation algorithm.

[0131] The generation unit can estimate the patient's emotions and adjust the length of questionnaires and consent forms based on the estimated emotions. For example, the generation unit estimates emotions from the patient's facial expressions and voice using an emotion estimation algorithm. For instance, if the patient is in a hurry, the generation unit generates a short, concise questionnaire. If the patient is relaxed, it can generate a detailed questionnaire. Furthermore, if the patient is agitated, it can generate a visually stimulating questionnaire. This allows for more appropriate responses by adjusting the length of questionnaires and consent forms according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a 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 generation unit may be performed using a generation AI, or not. For example, the generation unit can input patient facial expression data into a generation AI, which can estimate emotions and adjust the length of questionnaires and consent forms.

[0132] The generation unit can determine the generation priority based on the submission timing of questionnaires and consent forms during the generation process. For example, the generation unit can use a generation AI to analyze the submission timing of questionnaires and consent forms and determine the generation priority. For example, the generation unit can prioritize the generation of questionnaires that have been submitted recently. The generation unit can also prioritize the generation of questionnaires with high urgency. Furthermore, the generation unit can postpone the generation of questionnaires that have been submitted earlier. In this way, by determining the generation priority based on the submission timing of questionnaires and consent forms, it is possible to prioritize the generation of those with high urgency. The determination of priority includes, but is not limited to, evaluation criteria for submission timing and priority determination algorithms. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input questionnaire and consent form data into a generation AI, which can evaluate the submission timing and determine the generation priority.

[0133] The generation unit can adjust the generation order based on the relevance of questionnaires and consent forms during the generation process. For example, the generation unit can use a generation AI to analyze the relevance of questionnaires and consent forms and adjust the generation order. For example, the generation unit can prioritize generating questionnaires related to the patient's symptoms. It can also prioritize generating questionnaires related to the medical professional's area of ​​expertise. Furthermore, it can prioritize generating questionnaires of high urgency. By adjusting the generation order based on the relevance of questionnaires and consent forms, important documents can be generated preferentially. The evaluation of relevance includes, but is not limited to, the content of the questionnaires and consent forms and the method of evaluating relevance. Some or all of the above-described processes in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input data from questionnaires and consent forms into a generation AI, which can evaluate the relevance and adjust the generation order.

[0134] The collaboration unit can estimate the patient's emotions and adjust the collaboration method for the telemedicine interpretation service based on the estimated emotions. For example, the collaboration unit estimates emotions from the patient's facial expressions and voice using an emotion estimation algorithm. For example, if the patient is feeling anxious, the collaboration unit can provide interpretation services in a gentle voice to reassure them. If the patient is angry, the collaboration unit can also provide interpretation services in a calm voice to help them calm down. Furthermore, if the patient is sad, the collaboration unit can provide interpretation services in a warm voice to comfort them. This allows for a more appropriate response by adjusting the collaboration method for the telemedicine interpretation service according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 collaboration unit may be performed using AI, for example, or not using AI. For example, the collaboration unit can input patient facial expression data into the generative AI, which can estimate emotions and adjust the collaboration method for the telemedicine interpretation service.

[0135] The collaboration department can select the most appropriate collaboration method based on the medical interpreter's area of ​​expertise and experience during the collaboration process. For example, the collaboration department can use AI to analyze the medical interpreter's area of ​​expertise and experience and select the most appropriate collaboration method. For instance, if the medical interpreter's area of ​​expertise is internal medicine, the collaboration department will select a collaboration method specifically for internal medicine. Similarly, if the medical interpreter's area of ​​expertise is surgery, the collaboration department can select a collaboration method specifically for surgery. Furthermore, if the medical interpreter has extensive experience, the collaboration department can select a more detailed collaboration method. This allows for the provision of more appropriate interpretation services by selecting the most appropriate collaboration method based on the medical interpreter's area of ​​expertise and experience. The optimal collaboration method includes, but is not limited to, selection criteria and evaluation methods. Some or all of the above-described processes in the collaboration department may be performed using AI, or not. For example, the collaboration department can input data on the medical interpreter's area of ​​expertise and experience into AI, which can then select the most appropriate collaboration method.

[0136] The collaboration unit can estimate the patient's emotions and prioritize remote medical interpretation services based on the estimated emotions. For example, the collaboration unit uses an emotion estimation algorithm to estimate emotions from the patient's facial expressions and voice. For instance, if the patient is feeling anxious, the collaboration unit prioritizes providing reassuring interpretation services. Similarly, if the patient is angry, it can prioritize providing calming interpretation services. Furthermore, if the patient is sad, it can prioritize providing comforting interpretation services. This allows for more appropriate responses by prioritizing remote medical interpretation services according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collaboration unit may be performed using AI, or not. For example, the collaboration unit can input patient facial expression data into a generative AI, which then estimates the emotions and determines the priority of remote medical interpretation services.

[0137] The collaboration unit can select the optimal collaboration method by considering the patient's geographical location information during collaboration. For example, the collaboration unit can use AI to analyze the patient's geographical location information and select the optimal collaboration method. For example, if the patient is in a hospital, the collaboration unit can prioritize providing urgent interpretation services. The collaboration unit can also prioritize providing telemedicine interpretation services if the patient is in a distant location. Furthermore, if the collaboration unit is in a specific region, it can prioritize providing interpretation services related to that region. In this way, the optimal collaboration method can be selected by considering the patient's geographical location information. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the collaboration unit may be performed using, for example, AI, or not using AI. For example, the collaboration unit can input the patient's geographical information into AI, and the AI ​​can select the optimal collaboration method.

[0138] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0139] The reception desk can estimate the patient's emotions and adjust the timing of voice reception based on the estimated emotions. For example, an emotion estimation algorithm can be used to estimate emotions from the patient's facial expressions and voice. If the patient is tense, voice reception can be delayed until they relax. If the patient is anxious, voice reception can be done quickly. Furthermore, if the patient is calm, voice reception can be done at the normal timing. This allows for more appropriate responses by adjusting the timing of voice reception according to the patient's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input patient facial expression data into a generative AI, which can then estimate emotions.

[0140] The reception desk can analyze the patient's past voice data and select the optimal voice reception method. For example, it can use AI to analyze the patient's past voice data and suggest the optimal voice reception method. It can analyze the voice input methods the patient has used in the past and select the optimal method. It can also select the method that resulted in the smoothest reception from the patient's past voice data. Furthermore, it can analyze the quality of the patient's voice data and select the optimal voice reception method. In this way, the optimal voice reception method can be selected by analyzing the patient's past voice data. The optimal voice reception method includes, but is not limited to, voice recognition technology, voice input devices, and voice input timing. Some or all of the above processing in the reception desk may be performed using AI or not using AI. For example, the reception desk can input the patient's past voice data into AI, and the AI ​​can select the optimal voice reception method.

[0141] The reception desk can filter voice messages based on the patient's current health status and symptoms. For example, it can use AI to analyze the patient's health status and symptoms and prioritize receiving important information. If the patient's health is poor, the AI ​​can filter the voice message and prioritize receiving important information. If the patient's symptoms are severe, the AI ​​can also filter the voice message and prioritize receiving urgent information. Furthermore, if the patient's health is good, it can also receive normal information. This allows for the prioritization of important information based on the patient's health status and symptoms. Filtering includes, but is not limited to, voice recognition technology, voice analysis algorithms, and health status evaluation criteria. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input patient health data into the AI, which can then filter important information.

[0142] The reception desk can estimate the patient's emotions and determine the priority of the voice messages to be received based on the estimated emotions. For example, an emotion estimation algorithm can be used to estimate emotions from the patient's facial expressions and voice. If the patient is feeling anxious, reassuring voice messages can be prioritized. If the patient is angry, calming voice messages can be prioritized. Furthermore, if the patient is sad, comforting voice messages can be prioritized. This allows for more appropriate responses by prioritizing voice messages according to the patient's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the patient's facial expression data into a generative AI, which can then estimate the emotions.

[0143] The reception desk can prioritize receiving voice messages that are highly relevant, taking into account the patient's geographical location. For example, it can use AI to analyze the patient's geographical location and prioritize receiving highly relevant voice messages. If the patient is near the hospital, it can prioritize receiving urgent voice messages. If the patient is far away, it can prioritize receiving voice messages related to telemedicine. Furthermore, if the patient is in a specific region, it can prioritize receiving voice messages related to that region. In this way, by considering the patient's geographical location, it is possible to prioritize receiving highly relevant voice messages. Geographical location information includes, but is not limited to, GPS data and methods for analyzing location information. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the patient's geographical information into the AI, which can then prioritize receiving highly relevant voice messages.

[0144] The translation unit can estimate the patient's emotions and adjust the translation's expression based on those estimated emotions. For example, an emotion estimation algorithm can be used to estimate emotions from the patient's facial expressions and voice. If the patient is feeling anxious, gentle expressions can be used to reassure them. If the patient is angry, calm expressions can be used to calm them down. Furthermore, if the patient is sad, warm expressions can be used to comfort them. By adjusting the translation's expression according to the patient's emotions, a more appropriate translation can be provided. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using generative AI or not. For example, the translation unit can input the patient's facial expression data into a generative AI, which can estimate emotions and adjust the translation's expression.

[0145] The translation unit can adjust the level of detail in translations based on the importance of medical terms. For example, it can use a generative AI to analyze the importance of medical terms and adjust the level of detail. For important medical terms, a detailed translation can be provided. For common medical terms, a concise translation can be provided. Furthermore, for specialized medical terms, a specialized translation can be provided. In this way, appropriate translations are provided by adjusting the level of detail in translations based on the importance of medical terms. The evaluation of importance includes, but is not limited to, the frequency of medical terms and the method of evaluating importance. Some or all of the above processing in the translation unit may be performed using a generative AI or not. For example, the translation unit can input medical term data into a generative AI, which can evaluate importance and adjust the level of detail in translation.

[0146] The translation unit can estimate the patient's emotions and adjust the translation length based on the estimated emotions. For example, it can use an emotion estimation algorithm to estimate emotions from the patient's facial expressions and voice. If the patient is in a hurry, it can provide a short, to-the-point translation. If the patient is relaxed, it can provide a detailed translation. Furthermore, if the patient is agitated, it can provide a visually stimulating translation. By adjusting the translation length according to the patient's emotions, a more appropriate translation can be provided. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using generative AI or not. For example, the translation unit can input patient facial expression data into a generative AI, which can estimate emotions and adjust the translation length.

[0147] The service provider can estimate the patient's emotions and adjust the method of providing the translation results based on the estimated emotions. For example, it can use an emotion estimation algorithm to estimate emotions from the patient's facial expressions and voice. If the patient is feeling anxious, it can provide the translation results in a gentle voice to reassure them. If the patient is angry, it can provide the translation results in a calm voice to calm them down. Furthermore, if the patient is sad, it can provide the translation results in a warm voice to comfort them. By adjusting the method of providing the translation results according to the patient's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the patient's facial expression data into a generative AI, which can estimate emotions and adjust the method of providing the translation results.

[0148] The delivery unit can select the optimal delivery method by referring to the past interaction history of healthcare professionals at the time of delivery. For example, it can use AI to analyze the past interaction history of healthcare professionals and propose the optimal delivery method. It can select the optimal method by referring to delivery methods previously used by healthcare professionals. It can also select the most effective delivery method from the past interaction history of healthcare professionals. Furthermore, it can analyze the past interaction history of healthcare professionals to select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the past interaction history of healthcare professionals. The optimal delivery method includes, but is not limited to, selection criteria and evaluation methods for delivery methods. Some or all of the above processing in the delivery unit may be performed using AI or not using AI. For example, the delivery unit can input healthcare professional interaction history data into AI, and the AI ​​can select the optimal delivery method.

[0149] The following briefly describes the processing flow for example form 2.

[0150] Step 1: The reception desk receives the patient's voice. For example, it receives the patient's spoken words with a microphone and saves them as audio data. The reception desk can also use speech recognition technology to convert the audio data into text data. Step 2: The translation unit uses generative AI to translate the audio received by the reception unit. For example, the generative AI analyzes the audio data and translates it into another language. The translation unit can also translate medical terms and technical terms with high accuracy. Step 3: The delivery unit provides the translated audio to healthcare professionals. For example, the translated text data is played back as audio using speech synthesis technology. The delivery unit can also display the translation results on a screen. Step 4: The medical reception desk receives the voice of the medical staff. For example, it receives what the medical staff says using a microphone and saves it as audio data. The medical reception desk can also use speech recognition technology to convert the audio data into text data. Step 5: The medical translation department uses generative AI to translate the audio received by the medical reception department. For example, the generative AI analyzes the audio data and translates it into another language. The medical translation department can also translate medical terms and technical terms with high accuracy. Step 6: The medical service department provides the patient with the audio translated by the medical translation department. For example, the translated text data is played back as audio using speech synthesis technology. The medical service department can also display the translation results on a screen.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] Each of the multiple elements described above, including the reception unit, translation unit, provision unit, medical reception unit, medical translation unit, medical provision unit, generation unit, and collaboration unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives the patient's voice using the microphone 38B of the smart device 14 and converts the voice data into text data by the control unit 46A. The translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The provision unit provides the translated voice to medical personnel using the speaker 40B of the smart device 14. The medical reception unit receives the voice of medical personnel using the microphone 38B of the smart device 14 and converts the voice data into text data by the control unit 46A. The medical translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The medical provision unit provides the translated voice to the patient using the speaker 40B of the smart device 14. The generation unit generates questionnaires and consent forms using the generation AI via the specific processing unit 290 of the data processing device 12. The collaboration unit uses the generation AI via the specific processing unit 290 of the data processing device 12 to collaborate with medical interpreters in remote locations. 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.

[0155] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] Each of the multiple elements described above, including the reception unit, translation unit, provision unit, medical reception unit, medical translation unit, medical provision unit, generation unit, and coordination unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives the patient's voice using the microphone 238 of the smart glasses 214 and converts the voice data into text data by the control unit 46A. The translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The provision unit provides the translated voice to medical personnel using the speaker 240 of the smart glasses 214. The medical reception unit receives the voice of medical personnel using the microphone 238 of the smart glasses 214 and converts the voice data into text data by the control unit 46A. The medical translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The medical provision unit provides the translated voice to the patient using the speaker 240 of the smart glasses 214. The generation unit generates questionnaires and consent forms using the generation AI via the specific processing unit 290 of the data processing device 12. The collaboration unit uses the generation AI via the specific processing unit 290 of the data processing device 12 to collaborate with medical interpreters in remote locations. 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.

[0171] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.).

[0183] 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.

[0184] 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.

[0185] 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.

[0186] Each of the multiple elements described above, including the reception unit, translation unit, provision unit, medical reception unit, medical translation unit, medical provision unit, generation unit, and coordination unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives the patient's voice using the microphone 238 of the headset terminal 314 and converts the voice data into text data by the control unit 46A. The translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The provision unit provides the translated voice to medical personnel using the speaker 240 of the headset terminal 314. The medical reception unit receives the voice of medical personnel using the microphone 238 of the headset terminal 314 and converts the voice data into text data by the control unit 46A. The medical translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The medical provision unit provides the translated voice to the patient using the speaker 240 of the headset terminal 314. The generation unit generates questionnaires and consent forms using the generation AI via the specific processing unit 290 of the data processing device 12. The collaboration unit uses the generation AI via the specific processing unit 290 of the data processing device 12 to collaborate with medical interpreters in remote locations. 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.

[0187] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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).

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] Each of the multiple elements described above, including the reception unit, translation unit, provision unit, medical reception unit, medical translation unit, medical provision unit, generation unit, and coordination unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives the patient's voice using the microphone 238 of the robot 414 and converts the voice data into text data using the control unit 46A. The translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The provision unit provides the translated voice to medical personnel using the speaker 240 of the robot 414. The medical reception unit receives the voice of medical personnel using the microphone 238 of the robot 414 and converts the voice data into text data using the control unit 46A. The medical translation unit translates the voice data using the generation AI by the specific processing unit 290 of the data processing unit 12. The medical provision unit provides the translated voice to the patient using the speaker 240 of the robot 414. The generation unit generates questionnaires and consent forms using the generation AI via the specific processing unit 290 of the data processing device 12. The collaboration unit uses the generation AI via the specific processing unit 290 of the data processing device 12 to collaborate with medical interpreters in remote locations. 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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."

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] (Note 1) The reception area receives patient voice messages, A translation unit that translates the audio received by the reception unit, A provisioning unit that provides the audio translated by the aforementioned translation unit to medical professionals, A medical reception desk that receives voice messages from medical professionals, A medical translation department that translates audio received by the aforementioned medical reception department, The medical service unit provides the patient with audio translated by the medical translation unit. A system characterized by the following features. (Note 2) It is equipped with a generation unit that generates medical questionnaires and consent forms. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Translate patient questionnaires and consent forms, written in the patient's own language, into the language of the healthcare professional. The system described in Appendix 2, characterized by the features described herein. (Note 4) The generating unit is Translate medical and technical terms with high accuracy. The system described in Appendix 2, characterized by the features described herein. (Note 5) It has a liaison department that works in conjunction with remote medical interpretation services. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned linkage unit is, We provide interpretation services by coordinating with remote medical interpreters as needed. The system described in Appendix 3, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the patient's emotions and adjusts the timing of voice reception based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the patient's past voice data to select the optimal voice reception method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving a voice call, filtering is performed based on the patient's current health status and symptoms. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the patient's emotions and determines the priority of incoming calls based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving voice messages, the system prioritizes receiving messages that are highly relevant, taking into account the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving audio recordings, the system analyzes the patient's social media activity and receives relevant recordings. The system described in Appendix 1, characterized by the features described herein. (Note 13) 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 14) The aforementioned translation department, During translation, adjust the level of detail based on the importance of medical terms. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned translation department, During translation, different translation algorithms are applied depending on the patient's symptoms and medical history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned translation department, The system estimates the patient's emotions and adjusts the translation length based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned translation department, During translation, translation priorities are determined based on the timing of audio submission. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned translation department, During translation, the order of translations is adjusted based on the relevance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, The system estimates the patient's emotions and adjusts the method of providing translation results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing the service, the optimal delivery method is selected by referring to the healthcare professional's past response history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, At the time of delivery, the delivery method will be customized based on the patient's current health condition. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates the patient's emotions and prioritizes translation results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing the service, the optimal delivery method will be selected, taking into account the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing the service, we analyze the patient's social media activity and propose a method of delivery. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned medical reception department is The system estimates the emotions of healthcare workers and adjusts the timing of voice reception based on the estimated emotions of the healthcare workers. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned medical reception department is We analyze past voice data of healthcare professionals to select the optimal voice reception method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned medical reception department is When receiving voice messages, filtering is performed based on the medical professional's area of ​​expertise and experience. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned medical reception department is The system estimates the emotions of healthcare workers and prioritizes incoming calls based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned medical reception department is When receiving voice messages, the system prioritizes receiving messages that are highly relevant, taking into account the geographical location of the healthcare professional. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned medical reception department is When receiving audio, the system analyzes the social media activity of healthcare professionals and receives relevant audio. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned medical translation department, The system estimates the emotions of healthcare workers and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned medical translation department, During translation, adjust the level of detail based on the importance of medical terms. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned medical translation department, During translation, different translation algorithms are applied depending on the medical professional's area of ​​expertise and experience. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned medical translation department, The system estimates the emotions of healthcare workers and adjusts the translation length based on the estimated emotions of those healthcare workers. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned medical translation department, During translation, translation priorities are determined based on the timing of audio submission. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned medical translation department, During translation, the order of translations is adjusted based on the relevance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned medical care provision department, We estimate the emotions of healthcare workers and adjust the way translation results are delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned medical care provision department, When providing the service, the optimal delivery method is selected by referring to the patient's past treatment history. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned medical care provision department, When providing services, the delivery method will be customized based on the expertise and experience of the healthcare professional. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned medical care provision department, The system estimates the emotions of healthcare workers and prioritizes translation results based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned medical care provision department, When providing, select the optimal provision method considering the geographical location information of medical staff The system according to appended note 1, characterized by this. (Appended note 42) The medical provision department When providing, analyze the social media activities of medical staff and propose means of provision The system according to appended note 1, characterized by this. (Appended note 43) The generation department Estimate the emotions of patients and adjust the generation method of questionnaires and consent forms based on the estimated emotions of patients The system according to appended note 2, characterized by this. (Appended note 44) The generation department When generating, adjust the generation details based on the importance of medical terms The system according to appended note 2, characterized by this. (Appended note 45) The generation department When generating, apply different generation algorithms according to the symptoms and medical histories of patients The system according to appended note 2, characterized by this. (Appended note 46) The generation department Estimate the emotions of patients and adjust the length of questionnaires and consent forms based on the estimated emotions of patients The system according to appended note 2, characterized by this. (Appended note 47) The generation department When generating, determine the generation priority based on the submission time of questionnaires and consent forms The system according to appended note 2, characterized by this. (Appended note 48) The generation department When generating, adjust the generation order based on the relevance of questionnaires and consent forms The system according to appended note 2, characterized by this. (Appended note 49) The cooperation department The system estimates the patient's emotions and adjusts the method of coordinating remote medical interpretation services based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 50) The aforementioned linkage unit is, When collaborating, the most suitable method of collaboration will be selected based on the medical interpreter's area of ​​expertise and experience. The system described in Appendix 3, characterized by the features described herein. (Note 51) The aforementioned linkage unit is, The system estimates the patient's emotions and prioritizes telemedicine interpretation services based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 52) The aforementioned linkage unit is, When collaborating, the optimal collaboration method will be selected considering the patient's geographical location. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0223] 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. The reception area receives patient voice messages, A translation unit that translates the audio received by the reception unit, A provisioning unit that provides the audio translated by the aforementioned translation unit to medical professionals, A medical reception desk that receives voice messages from medical professionals, A medical translation department that translates audio received by the aforementioned medical reception department, The medical service unit provides the patient with audio translated by the medical translation unit. A system characterized by the following features.

2. It is equipped with a generation unit that generates medical questionnaires and consent forms. The system according to feature 1.

3. The generating unit is Translate patient questionnaires and consent forms, written in the patient's own language, into the language of the healthcare professional. The system according to feature 2.

4. The generating unit is Translate medical and technical terms with high accuracy. The system according to feature 2.

5. It has a liaison department that works in conjunction with remote medical interpretation services. The system according to feature 1.

6. The aforementioned linkage unit is, We provide interpretation services by coordinating with remote medical interpreters as needed. The system according to claim 5, characterized in that it is the same as described in claim 5.

7. The aforementioned reception unit is The system estimates the patient's emotions and adjusts the timing of voice reception based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze the patient's past voice data to select the optimal voice reception method. The system according to feature 1.

9. The aforementioned reception unit is When receiving a voice call, filtering is performed based on the patient's current health status and symptoms. The system according to feature 1.

10. The aforementioned reception unit is The system estimates the patient's emotions and determines the priority of incoming calls based on those emotions. The system according to feature 1.

Images