system

Abstract

The system according to this embodiment aims to support the health management of the elderly using a voice assistant and reduce the burden on healthcare professionals. [Solution] The system according to the embodiment comprises a reception unit, a text conversion unit, an organization unit, a management unit, a reminder unit, a dialogue unit, and a confirmation unit. The reception unit receives voice input. The text conversion unit converts the voice received by the reception unit into text. The organization unit organizes the content converted into text by the text conversion unit as a medical record. The management unit manages the user's medication schedule. The reminder unit provides reminders based on the schedule managed by the management unit. The dialogue unit engages in dialogue with the user. The confirmation unit confirms the user's health status based on the information obtained by the dialogue unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional technologies have problems such as the complexity of drug management, the sense of isolation of the elderly, and the increased burden on medical staff.

[0005] The system according to the embodiment aims to support the health management of the elderly using a voice assistant and reduce the burden on medical staff.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a text conversion unit, an organization unit, a management unit, a reminder unit, a dialogue unit, and a confirmation unit. The reception unit receives voice input. The text conversion unit converts the voice received by the reception unit into text. The organization unit organizes the content converted into text by the text conversion unit as a medical record. The management unit manages the user's medication schedule. The reminder unit provides reminders based on the schedule managed by the management unit. The dialogue unit engages in dialogue with the user. The confirmation unit confirms the user's health status based on the information obtained by the dialogue unit. [Effects of the Invention]

[0007] The system according to this embodiment can support the health management of the elderly using a voice assistant and reduce the burden on healthcare 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 manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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 WellnessNavigator system according to an embodiment of the present invention is a health management and treatment support system for the elderly and users unfamiliar with AI technology, utilizing a voice assistant. The WellnessNavigator system provides a function that transcribes the content of medical examinations in real time and automatically creates and organizes medical records using AI. This reduces the record-keeping work of doctors and nurses and improves work efficiency. For example, the AI ​​transcribes conversations during examinations in real time and automatically creates medical records based on that text. This allows healthcare professionals to concentrate on examinations and reduces the time spent on manual record-keeping. Next, it facilitates health management for the elderly through a medication reminder function and medication management support. For example, the AI ​​understands the user's medication schedule and provides reminders at the appropriate time. Also, if the user is taking multiple medications, it explains the risks of interactions and side effects and provides warnings. This reduces the risk of medication errors and missed doses among the elderly. Furthermore, through a daily dialogue function via voice, it helps people experiencing social isolation and loneliness to receive appropriate support. For example, the AI ​​can monitor users' daily health and mood, and increase opportunities for communication to reduce feelings of social isolation. It can also support medical consultations, reducing the burden on healthcare professionals and allowing them to focus more on patients. Through this, the WellnessNavigator system aims to improve the efficiency of healthcare professionals' work, enhance health management for the elderly, and reduce feelings of isolation, thereby enabling a more secure life, by utilizing a voice assistant to provide automatic creation of medical records, medication reminders, and conversational functions.

[0029] The WellnessNavigator system according to this embodiment comprises a reception unit, a text conversion unit, an organization unit, a management unit, a reminder unit, a dialogue unit, and a confirmation unit. The reception unit receives voice input. The reception unit receives voice input using, for example, a microphone. The reception unit can also receive voice input using a smartphone app. Furthermore, the reception unit can also receive voice input using speech recognition technology. For example, the reception unit converts speech to text using speech recognition technology. The text conversion unit converts the voice received by the reception unit into text. The text conversion unit converts speech to text using, for example, speech recognition technology. Furthermore, the text conversion unit can improve the accuracy of text conversion using a method for correcting misrecognition. Furthermore, the text conversion unit can adjust the text conversion method according to the type of speech recognition technology. For example, the text conversion unit converts speech to text using speech recognition technology and improves the accuracy of text conversion using a method for correcting misrecognition. The organization unit organizes the content converted into text by the text conversion unit as a medical record. The organization unit organizes the text content according to the format of the medical record, for example. The organization unit can also save the text content according to the method of saving the medical record. Furthermore, the organization unit can organize the text content according to the method of organizing the medical record. For example, the organization unit organizes the text content according to the format of the medical record and saves the text content according to the method of saving the medical record. The management unit manages the user's medication schedule. For example, the management unit inputs the user's medication schedule. Furthermore, the management unit can manage the medication schedule according to the method of setting reminders. Furthermore, the management unit can manage the medication schedule according to the method of managing the medication schedule. For example, the management unit inputs the user's medication schedule and manages the medication schedule according to the method of setting reminders. The reminder unit provides reminders based on the schedule managed by the management unit. The reminder unit provides reminders according to the format of the notification, for example. Furthermore, the reminder unit can provide reminders according to the timing of the notification.Furthermore, the reminder unit can provide reminders according to the method of providing reminders. For example, the reminder unit can provide reminders according to the format of the notification and according to the timing of the notification. The dialogue unit interacts with the user. For example, the dialogue unit interacts with the user according to the content of the dialogue. The dialogue unit can also interact with the user according to the frequency of the dialogue. Furthermore, the dialogue unit can also interact with the user according to the method of the dialogue. For example, the dialogue unit interacts with the user according to the content of the dialogue and according to the frequency of the dialogue. The confirmation unit confirms the user's health status based on the information obtained by the dialogue unit. For example, the confirmation unit confirms the user's health status according to the items to be confirmed. The confirmation unit can also confirm the user's health status according to the frequency of confirmation. Furthermore, the confirmation unit can also confirm the user's health status according to the method of confirming the health status. For example, the confirmation unit confirms the user's health status according to the items to be confirmed and according to the frequency of confirmation. As a result, the WellnessNavigator system according to this embodiment can provide automatic creation of medical records, medication reminders, and dialogue functions through voice input, thereby improving the work efficiency of healthcare professionals, enhancing health management for the elderly, and reducing feelings of isolation.

[0030] The reception desk accepts voice input. For example, the reception desk accepts voice input using a microphone. Specifically, the microphone is highly sensitive and features noise cancellation to eliminate ambient noise, allowing users to input clear voice. The reception desk can also accept voice input using a smartphone app. The smartphone app provides an intuitive interface for easy voice input, allowing users to start and stop voice input with a single touch. Furthermore, the reception desk can accept voice input using speech recognition technology. For example, the reception desk converts speech to text using speech recognition technology. The speech recognition technology employs advanced algorithms using deep learning, enabling high-precision recognition of differences in user pronunciation and accent. This allows the reception desk to ensure accurate voice input in any environment, improving the overall reliability of the system.

[0031] The text conversion unit converts the audio received by the reception unit into text. The text conversion unit converts audio to text using, for example, speech recognition technology. Specifically, speech recognition technology analyzes audio data, identifies phoneme and word patterns, and converts them into text. The text conversion unit can also improve the accuracy of the conversion using methods to correct misrecognition. For example, if the user misrecognizes a particular word or phrase, the text conversion unit makes appropriate corrections based on context and past data. Furthermore, the text conversion unit can adjust the conversion method depending on the type of speech recognition technology used. For example, it can combine different speech recognition engines and select the most accurate result. This allows the text conversion unit to handle diverse audio input situations and achieve highly accurate conversion.

[0032] The editing department organizes the content converted into text by the text conversion department as medical records. For example, the editing department organizes the text according to the medical record format. Specifically, the medical record format includes items such as basic patient information, treatment details, prescribed medications, and the next scheduled appointment. The editing department can also save the text according to the medical record storage method. For example, it can automatically save the data to an electronic medical record system, allowing healthcare professionals to access it as needed. Furthermore, the editing department can organize the text according to the medical record organization method. For example, it can organize the text according to the medical record format and save the text according to the medical record storage method. This ensures that the editing department maintains the consistency and accuracy of medical records and allows healthcare professionals to manage information efficiently.

[0033] The administration department manages the user's medication schedule. For example, the administration department inputs the user's medication schedule. Specifically, it inputs information such as the name of the medication the user takes, the time to take it, and the dosage, and saves it in the system. The administration department can also manage the medication schedule according to the reminder setting method. For example, it can set a reminder at a time specified by the user and send a notification. Furthermore, the administration department can manage the medication schedule according to the medication schedule management method. For example, it inputs the user's medication schedule and manages the medication schedule according to the reminder setting method. In this way, the administration department ensures that users take their medication at the appropriate time and supports their health management.

[0034] The reminder unit provides reminders based on schedules managed by the management unit. The reminder unit provides reminders according to the notification format, for example. Specifically, it sends reminders in the form of smartphone push notifications, email, SMS, etc. The reminder unit can also provide reminders according to the timing of notifications. For example, it can send a notification 30 minutes before or immediately before taking medication to ensure that the user does not forget to take their medication. Furthermore, the reminder unit can provide reminders according to the method of providing reminders. For example, it can provide reminders according to the notification format and reminders according to the timing of notifications. In this way, the reminder unit helps users take their medication at the appropriate time and supports their health management.

[0035] The dialogue unit engages in conversations with the user. For example, the dialogue unit interacts with the user according to the content of the conversation. Specifically, it asks questions about the user's health and daily life and records the user's responses. The dialogue unit can also interact with the user according to the frequency of the conversation. For example, it can interact daily, once a week, or at a frequency specified by the user. Furthermore, the dialogue unit can interact with the user according to the method of interaction. For example, it can interact using methods such as voice conversation, text chat, or video call. This allows the dialogue unit to continuously monitor the user's health and provide necessary support.

[0036] The verification unit checks the user's health status based on the information obtained by the dialogue unit. For example, the verification unit checks the user's health status according to the items to be checked. Specifically, it checks health indicators such as the user's body temperature, blood pressure, heart rate, and weight. The verification unit can also check the user's health status according to the frequency of checks. For example, it can check the health status daily, once a week, or at a frequency specified by the user. Furthermore, the verification unit can check the user's health status according to the method of checking the health status. For example, it can check the user's health status according to the items to be checked and according to the frequency of checks. This allows the verification unit to continuously monitor the user's health status and respond early if an abnormality occurs.

[0037] The reception desk can transcribe conversations during consultations in real time. For example, the reception desk can use speech recognition technology to transcribe conversations during consultations in real time. The reception desk can also set an acceptable delay range for real-time transcription. Furthermore, the reception desk can improve the accuracy of transcription using real-time processing technology. For example, the reception desk can transcribe conversations during consultations in real time using speech recognition technology, set an acceptable delay range, and improve the accuracy of transcription using real-time processing technology. This allows for the rapid and accurate creation of medical records by transcribing conversations during consultations in real time. Some or all of the above processes in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can use an AI model with speech recognition technology to transcribe conversations during consultations in real time and improve the accuracy of transcription.

[0038] The text conversion unit can automatically create medical records based on the transcribed content. For example, the text conversion unit can use templates to automatically create medical records based on the transcribed content. The text conversion unit can also automatically create medical records using an automated data entry method. Furthermore, the text conversion unit can adjust the automated medical record creation method. For example, the text conversion unit can automatically create medical records based on transcribed content using templates, and can also automatically create medical records using an automated data entry method. This reduces the burden on healthcare professionals by automatically creating medical records based on transcribed content. Some or all of the above-described processes in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can use an AI model to automatically create medical records based on the transcribed content and adjust the automated medical record creation method.

[0039] The management department can understand the user's medication schedule and provide reminders at the appropriate time. For example, the management department uses a schedule input method to understand the user's medication schedule. The management department can also set the reminder notification interval. Furthermore, the management department can adjust how reminders are delivered. For example, the management department understands the user's medication schedule using the schedule input method and adjusts how reminders are delivered by setting the reminder notification interval. This reduces the risk of medication errors or missed doses by understanding the user's medication schedule and providing reminders at the appropriate time. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department may use an AI model to understand the user's medication schedule and adjust how reminders are delivered to provide them at the appropriate time.

[0040] The reminder unit can explain and warn about the risks of drug interactions and side effects. For example, the reminder unit uses risk assessment criteria to explain the risks of interactions and side effects. The reminder unit can also set the format of the explanation. Furthermore, the reminder unit can adjust the method of explaining the risks. For example, the reminder unit can explain the risks of interactions and side effects using risk assessment criteria and adjust the method of explaining the risks by setting the format of the explanation. This ensures user safety by explaining and warning about the risks of drug interactions and side effects. Some or all of the above processing in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit can use an AI model to adjust the method of explaining the risks in order to explain and warn about the risks of drug interactions and side effects.

[0041] The dialogue unit can check the user's daily health and mood and increase opportunities for communication. For example, the dialogue unit sets the content of questions to check the user's daily health and mood. The dialogue unit can also set the frequency of checks. Furthermore, the dialogue unit can adjust the method of the conversation. For example, the dialogue unit checks the user's daily health and mood by setting the content of questions and adjusts the method of the conversation by setting the frequency of checks. This reduces feelings of social isolation by checking the user's daily health and mood and increasing opportunities for communication. Some or all of the above processing in the dialogue unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the dialogue unit may use an emotion engine or generative AI and adjust the method of the conversation in order to check the user's daily health and mood and increase opportunities for communication.

[0042] The verification unit can provide support for medical consultations based on the user's health status. For example, the verification unit can set how to record the consultation content in order to provide support for medical consultations. The verification unit can also set how to provide support. Furthermore, the verification unit can adjust the method of providing support for medical consultations. For example, the verification unit can set how to record the consultation content to provide support for medical consultations based on the user's health status, and adjust the method of providing support for medical consultations by setting how to provide support. In this way, appropriate medical support is provided by providing support for medical consultations based on the user's health status. Some or all of the above processing in the verification unit may be performed using AI, for example, or not using AI. For example, the verification unit can use an AI model to adjust the method of providing support for medical consultations based on the user's health status.

[0043] The reception desk can analyze the importance of conversations during consultations and prioritize transcribing important parts. For example, the reception desk can prioritize transcribing important information about the patient's condition from the conversation. It can also prioritize transcribing important information about prescriptions from the conversation. Furthermore, the reception desk can prioritize transcribing important information about the next consultation from the conversation. For example, the reception desk can prioritize transcribing important information about the patient's condition and important information about prescriptions from the conversation. This improves the accuracy of medical records by prioritizing the transcription of important information during consultations. Some or all of the above processing at the reception desk may be performed using AI, for example, or not. For example, the reception desk can use an AI model to analyze the importance of conversations during consultations and prioritize transcribing important parts to improve the accuracy of transcription.

[0044] The reception unit can automatically remove background noise from voice input and obtain clear audio data. For example, the reception unit can automatically remove background noise in a medical examination room and obtain clear audio data. It can also automatically remove background noise in the user's home environment and obtain clear audio data. Furthermore, it can automatically remove background noise in public places and obtain clear audio data. For example, the reception unit can automatically remove background noise in a medical examination room and obtain clear audio data, and it can also automatically remove background noise in the user's home environment and obtain clear audio data. By removing background noise, clear audio data is obtained, improving the accuracy of text transcription. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can use an AI model and apply noise filtering technology to automatically remove background noise from voice input and obtain clear audio data.

[0045] The reception desk can prioritize retrieving highly relevant information by considering the user's geographical location during voice input. For example, if the user is in a hospital, the reception desk will prioritize retrieving information related to consultations within the hospital. Similarly, if the user is at home, the reception desk can prioritize retrieving information related to health management at home. Furthermore, if the user is traveling, the reception desk can prioritize retrieving medical information at their travel destination. For instance, if the user is in a hospital, the reception desk prioritizes retrieving information related to consultations within the hospital; if the user is at home, it prioritizes retrieving information related to health management at home. This allows for the prioritization of highly relevant information by considering the user's geographical location, enabling appropriate responses. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can use an AI model to determine information priorities in order to prioritize retrieving highly relevant information by considering the user's geographical location during voice input.

[0046] The reception desk can prioritize retrieving relevant information by referring to the user's past medical history when voice input is received. For example, the reception desk can prioritize retrieving information related to the current consultation from the user's past consultation history. It can also prioritize retrieving information related to prescribed medications from the user's past consultation history. Furthermore, the reception desk can prioritize retrieving information related to the next consultation from the user's past consultation history. For example, the reception desk prioritizes retrieving information related to the current consultation and information related to prescribed medications from the user's past consultation history. By referring to the user's past consultation history, relevant information is prioritized, improving the accuracy of the consultation. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can use an AI model to determine the priority of information in order to prioritize retrieving relevant information by referring to the user's past consultation history when voice input is received.

[0047] The text conversion unit can adjust the level of detail in the text based on the speed and tone of the speech during the transcription process. For example, if the speech is fast, the text conversion unit will generate concise text. It can also generate detailed text if the speech is slow. Furthermore, if the speech has a high tone, the text conversion unit can generate emphasized text. For example, if the text conversion unit generates concise text when the speech is fast, and detailed text when the speech is slow. This allows for the generation of text with an appropriate amount of information by adjusting the level of detail based on the speed and tone of the speech. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can use an AI model to adjust the level of detail in the text based on the speed and tone of the speech during transcription.

[0048] The text conversion unit can automatically expand technical terms and abbreviations during the text conversion process to generate easily understandable text. For example, the text conversion unit can convert medical terms into common language and then convert them into text. It can also expand abbreviations to their full spellings and then convert them into text. Furthermore, the text conversion unit can generate text that includes explanations of technical terms. For example, the text conversion unit can convert medical terms into common language and then convert them into text, and expand abbreviations to their full spellings. This automatically expands technical terms and abbreviations to generate text that is easy for the user to understand. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or not. For example, the text conversion unit can use an AI model to adjust the method of terminology expansion in order to automatically expand technical terms and abbreviations during the text conversion process and generate easily understandable text.

[0049] The text conversion unit can determine the priority of text based on the recording date of the audio during the text conversion process. For example, the text conversion unit may prioritize the most recent audio recording. The text conversion unit can also refer to past audio recordings and prioritize those that are more relevant. Furthermore, the text conversion unit can prioritize those that are of higher importance based on the recording date of the audio. For example, the text conversion unit may prioritize the most recent audio recording and refer to past audio recordings to prioritize those that are more relevant. This ensures that important information is prioritized by determining the text priority based on the recording date of the audio. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit may use an AI model to determine the priority of text based on the recording date of the audio during the text conversion process.

[0050] The text conversion unit can adjust the order of the text based on the relevance of the audio during the conversion process. For example, if the audio content is related, the text conversion unit will adjust the order before converting it to text. Furthermore, if the audio content is different, the text conversion unit can convert it in order of relevance. Additionally, if the audio content is repetitive, the text conversion unit can omit the duplicated parts during conversion. For example, if the audio content is related, the text conversion unit will adjust the order before converting it to text; if the audio content is different, it will convert it in order of relevance. This process, by adjusting the order of the text based on the relevance of the audio, generates more easily understandable text. Some or all of the above processing in the text conversion unit may be performed using, for example, AI, or not. For example, the text conversion unit can use an AI model to adjust the order of the text based on the relevance of the audio during the conversion process.

[0051] The organization unit can select the optimal organization method by referring to past medical data when organizing medical records. For example, the organization unit can select the optimal organization method based on past medical data. The organization unit can also prioritize organizing highly relevant information from past medical data. Furthermore, the organization unit can analyze past medical data and select an efficient organization method. For example, the organization unit selects the optimal organization method based on past medical data and prioritizes organizing highly relevant information from past medical data. This makes it possible to select the optimal organization method by referring to past medical data and to organize records efficiently. Some or all of the above processes in the organization unit may be performed using AI, for example, or not using AI. For example, the organization unit can use an AI model to select the optimal organization method by referring to past medical data when organizing medical records.

[0052] The organization unit can apply different organization algorithms to each category of medical examination content when organizing medical records. For example, if the medical examination content relates to a medical condition, the organization unit can apply an organization algorithm specialized for medical conditions. Furthermore, if the medical examination content relates to a prescription, the organization unit can apply an organization algorithm specialized for prescriptions. In addition, if the medical examination content relates to a next appointment, the organization unit can apply an organization algorithm specialized for the next appointment. For example, if the medical examination content relates to a medical condition, the organization unit can apply an organization algorithm specialized for medical conditions, and if the medical examination content relates to a prescription, it can apply an organization algorithm specialized for prescriptions. This allows for more appropriate record organization by applying different organization algorithms to each category of medical examination content. Some or all of the above processing in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can use an AI model to apply different organization algorithms to each category of medical examination content when organizing medical records.

[0053] The sorting department can determine the sorting priority based on the date the medical consultation was submitted when sorting medical records. For example, the sorting department can prioritize sorting the most recent medical records. The sorting department can also refer to past medical records and prioritize sorting those with high relevance. Furthermore, the sorting department can prioritize sorting those with high importance based on the date the medical consultation was submitted. For example, the sorting department prioritizes sorting the most recent medical records and refers to past medical records to prioritize sorting those with high relevance. In this way, by determining the sorting priority based on the date the medical consultation was submitted, important records are sorted first. Some or all of the above processes in the sorting department may be performed using AI, for example, or not using AI. For example, the sorting department can use an AI model to determine the sorting priority based on the date the medical consultation was submitted when sorting medical records.

[0054] The organization unit can adjust the order of organization of medical records based on the relevance of the consultations. For example, if the content of the consultations is related, the organization unit will adjust the order of organization. Furthermore, if the content of the consultations is different, the organization unit can also organize them in order of relevance. In addition, if the content of the consultations is duplicated, the organization unit can omit the duplicated parts. For example, if the content of the consultations is related, the organization unit will adjust the order of organization; if the content is different, it will organize them in order of relevance. This provides records that are easier to understand by adjusting the order of organization based on the relevance of the consultations. Some or all of the above processing in the organization unit may be performed using AI, for example, or not. For example, the organization unit can use an AI model to adjust the order of organization based on the relevance of the consultations when organizing medical records.

[0055] The management department can select the optimal management method when managing medication schedules by referring to past medication data. For example, the management department can select the optimal management method based on past medication data. The management department can also prioritize the management of highly relevant information from past medication data. Furthermore, the management department can analyze past medication data and select an efficient management method. For example, the management department can select the optimal management method based on past medication data and prioritize the management of highly relevant information from past medication data. This makes it possible to select the optimal management method by referring to past medication data and to manage medication efficiently. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can use an AI model to select the optimal management method when managing medication schedules by referring to past medication data.

[0056] The management unit can apply different management algorithms for each type of medication when managing medication schedules. For example, if the medications are of different types, the management unit can apply a specialized management algorithm to each. Alternatively, if the medications are of the same type, the management unit can apply a common management algorithm. Furthermore, the management unit can select the optimal management algorithm depending on the type of medication. For example, if the medications are of different types, the management unit can apply a specialized management algorithm to each type, and if the medications are of the same type, it can apply a common management algorithm. This allows for more appropriate medication management by applying different management algorithms for each type of medication. Some or all of the above processes in the management unit may be performed using AI, for example, or not. For example, the management unit can use an AI model to apply different management algorithms for each type of medication when managing medication schedules.

[0057] The management department can prioritize highly relevant schedules when managing medication schedules, taking into account the user's geographical location. For example, if the user is in a hospital, the management department will prioritize medication schedules within the hospital. Similarly, if the user is at home, the management department can prioritize medication schedules at home. Furthermore, if the user is traveling, the management department can prioritize medication schedules at their travel destination. For instance, if the user is in a hospital, the management department prioritizes medication schedules within the hospital; if the user is at home, it prioritizes medication schedules at home. This allows for appropriate medication management by prioritizing highly relevant schedules while considering the user's geographical location. Some or all of the above processing in the management department may be performed using AI, or not. For example, the management department can use an AI model to determine schedule priorities in order to prioritize highly relevant schedules while considering the user's geographical location when managing medication schedules.

[0058] The management department can analyze users' social media activity and manage related schedules when managing medication schedules. For example, the management department can prioritize information related to medication schedules from users' social media activity. The management department can also analyze users' social media activity and propose an optimal medication schedule. Furthermore, the management department can determine the priority of medication schedules based on users' social media activity. For example, the management department prioritizes information related to medication schedules from users' social media activity and proposes an optimal medication schedule by analyzing users' social media activity. This enables appropriate medication management by analyzing users' social media activity and managing related schedules. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, the management department can use an AI model to analyze users' social media activity and manage related schedules when managing medication schedules, and to determine the priority of schedules.

[0059] The reminder unit can adjust the level of detail in reminders based on the importance of the drug when providing them. For example, the reminder unit can provide detailed reminders for important drugs, and concise reminders for less important drugs. Furthermore, the reminder unit can adjust the level of detail in reminders according to the importance of the drug. For example, the reminder unit can provide detailed reminders for important drugs and concise reminders for less important drugs. By adjusting the level of detail in reminders based on the importance of the drug, the system can provide reminders with an appropriate amount of information. Some or all of the above processing in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit can use an AI model to adjust the level of detail in reminders based on the importance of the drug when providing them.

[0060] The reminder unit can apply different reminder algorithms depending on the drug category when providing reminders. For example, if the drug categories are different, the reminder unit can apply a specialized reminder algorithm to each. Alternatively, if the drug categories are the same, the reminder unit can apply a common reminder algorithm. Furthermore, the reminder unit can select the optimal reminder algorithm depending on the drug category. For example, if the drug categories are different, the reminder unit can apply a specialized reminder algorithm to each, and if the drug categories are the same, it can apply a common reminder algorithm. This allows for the provision of more appropriate reminders by applying different reminder algorithms depending on the drug category. Some or all of the above processing in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit can use an AI model to apply different reminder algorithms depending on the drug category when providing reminders.

[0061] The reminder unit can prioritize reminders based on the timing of drug submission when providing reminders. For example, the reminder unit may prioritize providing reminders for the most recent medication. The reminder unit can also refer to past medication reminders and prioritize those that are most relevant. Furthermore, the reminder unit can prioritize those of high importance based on the timing of drug submission. For example, the reminder unit prioritizes providing reminders for the most recent medication and refers to past medication reminders to prioritize those that are most relevant. This ensures that important reminders are prioritized by determining the priority of reminders based on the timing of drug submission. Some or all of the above processing in the reminder unit may be performed using AI, for example, or not using AI. For example, the reminder unit may use an AI model to determine the priority of reminders based on the timing of drug submission when providing reminders.

[0062] The reminder unit can adjust the order of reminders based on the relevance of the drugs when providing them. For example, if the contents of the drugs are related, the reminder unit will adjust the order in which it provides reminders. The reminder unit can also provide reminders in order of relevance if the contents of the drugs are different. Furthermore, if the contents of the drugs overlap, the reminder unit can provide reminders while omitting the overlapping parts. For example, if the contents of the drugs are related, the reminder unit will adjust the order in which it provides reminders, and if the contents of the drugs are different, it will provide reminders in order of relevance. By adjusting the order of reminders based on the relevance of the drugs, the reminder unit can provide more easily understood reminders. Some or all of the above processing in the reminder unit may be performed using AI, for example, or not using AI. For example, the reminder unit can use an AI model to adjust the order of reminders based on the relevance of the drugs when providing them.

[0063] The dialogue unit can select the optimal dialogue method by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can prioritize the use of highly relevant information from the user's past dialogue history. The dialogue unit can also analyze the user's past dialogue history to select an efficient dialogue method. Furthermore, the dialogue unit can propose an optimal dialogue method based on the user's past dialogue history. For example, the dialogue unit prioritizes the use of highly relevant information from the user's past dialogue history and analyzes the user's past dialogue history to select an efficient dialogue method. In this way, by referring to the user's past dialogue history, the dialogue unit selects the optimal dialogue method and provides an effective conversation. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit may use an AI model to select the optimal dialogue method by referring to the user's past dialogue history during a conversation.

[0064] The dialogue unit can customize the content of the conversation based on the user's current living situation. For example, the dialogue unit can consider the user's current living situation and provide highly relevant dialogue content. The dialogue unit can also analyze the user's current living situation and suggest the most appropriate dialogue content. Furthermore, the dialogue unit can customize the dialogue content based on the user's current living situation. For example, the dialogue unit considers the user's current living situation, provides highly relevant dialogue content, and analyzes the user's current living situation to suggest the most appropriate dialogue content. By customizing the dialogue content based on the user's current living situation, it provides a more relevant conversation. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can use an AI model to customize the dialogue content based on the user's current living situation during a conversation.

[0065] The dialogue unit can select the optimal dialogue method during a conversation, taking into account the user's geographical location. For example, if the user is in a hospital, the dialogue unit will prioritize a dialogue method within the hospital. Similarly, if the user is at home, the dialogue unit can prioritize a dialogue method suitable for home use. Furthermore, if the user is traveling, the dialogue unit can prioritize a dialogue method suitable for their travel destination. For instance, if the user is in a hospital, the dialogue unit will prioritize a dialogue method within the hospital; if the user is at home, it will prioritize a dialogue method suitable for home use. This allows for the selection of the optimal dialogue method and appropriate responses by considering the user's geographical location. Some or all of the above processing in the dialogue unit may be performed using AI, or not. For example, the dialogue unit may use an AI model to select the optimal dialogue method during a conversation, taking into account the user's geographical location.

[0066] The dialogue unit can analyze the user's social media activity during a conversation and suggest conversation content. For example, the dialogue unit can suggest highly relevant conversation content based on the user's social media activity. Furthermore, the dialogue unit can analyze the user's social media activity and suggest the most appropriate conversation content. In addition, the dialogue unit can customize conversation content based on the user's social media activity. For example, the dialogue unit suggests highly relevant conversation content based on the user's social media activity and then analyzes the user's social media activity to suggest the most appropriate conversation content. This allows the dialogue unit to suggest highly relevant conversation content and provide an effective conversation by analyzing the user's social media activity. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can use an AI model to analyze the user's social media activity during a conversation and suggest conversation content.

[0067] The verification unit can select the optimal verification method by referring to past health data when checking a person's health status. For example, the verification unit selects the optimal verification method based on past health data. The verification unit can also prioritize checking highly relevant information from past health data. Furthermore, the verification unit can analyze past health data and select an efficient verification method. For example, the verification unit selects the optimal verification method based on past health data and prioritizes checking highly relevant information from past health data. This makes it possible to select the optimal verification method by referring to past health data and to perform an efficient health check. Some or all of the above processing in the verification unit may be performed using AI, for example, or without using AI. For example, the verification unit may use an AI model to select the optimal verification method by referring to past health data when checking a person's health status.

[0068] The verification unit can customize the verification methods based on the user's current living situation when verifying health status. For example, the verification unit considers the user's current living situation and provides highly relevant verification methods. The verification unit can also analyze the user's current living situation and propose the optimal verification method. Furthermore, the verification unit can customize the verification methods based on the user's current living situation. For example, the verification unit considers the user's current living situation, provides highly relevant verification methods, and analyzes the user's current living situation to propose the optimal verification method. By customizing the verification methods based on the user's current living situation, more relevant verification becomes possible. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can use an AI model to customize the verification methods based on the user's current living situation when verifying health status.

[0069] The verification unit can select the optimal verification method when checking the user's health status, taking into account the user's geographical location information. For example, if the user is in a hospital, the verification unit will prioritize selecting a verification method within the hospital. Similarly, if the user is at home, the verification unit can prioritize selecting a verification method at their home. Furthermore, if the user is traveling, the verification unit can prioritize selecting a verification method at their travel destination. For example, if the user is in a hospital, the verification unit will prioritize selecting a verification method within the hospital; if the user is at home, it will prioritize selecting a verification method at their home. This allows for the selection of the optimal verification method and appropriate action by considering the user's geographical location information. Some or all of the above processing in the verification unit may be performed using AI, or not. For example, the verification unit may use an AI model to select the optimal verification method when checking the user's health status, taking into account the user's geographical location information.

[0070] The verification unit can analyze the user's social media activity and propose verification methods when checking the user's health status. For example, the verification unit can propose highly relevant verification methods based on the user's social media activity. The verification unit can also analyze the user's social media activity and propose the most suitable verification method. Furthermore, the verification unit can customize the verification methods based on the user's social media activity. For example, the verification unit can propose highly relevant verification methods based on the user's social media activity and propose the most suitable verification method by analyzing the user's social media activity. This enables effective health checks by proposing highly relevant verification methods through analysis of the user's social media activity. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can use an AI model to propose verification methods by analyzing the user's social media activity when checking the user's health status.

[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 WellnessNavigator system can also acquire user exercise data and use it to help with health management. For example, the management department can record users' steps and exercise volume to understand their daily exercise habits. The management department can also provide appropriate exercise advice based on the exercise data. Furthermore, the management department can evaluate the user's health status based on the exercise data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' exercise habits and using that information for health management.

[0073] The WellnessNavigator system can also acquire users' dietary data and use it to support their health management. For example, the management department can record the user's meals and evaluate their nutritional balance. The management department can also provide appropriate dietary advice based on this data. Furthermore, the management department can assess the user's health status based on the dietary data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' eating habits and utilizing that information for health management.

[0074] The WellnessNavigator system can also acquire user sleep data and use it for health management. For example, the management department can record the user's sleep duration and quality to understand their sleep patterns. The management department can also provide appropriate sleep advice based on the sleep data. Furthermore, the management department can evaluate the user's health status based on the sleep data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding the user's sleep habits and using that information for health management.

[0075] The WellnessNavigator system can further monitor users' stress levels and utilize this information for health management. For example, the management department can record users' heart rate and skin electrical activity to assess their stress levels. Based on this stress data, the management department can also provide appropriate relaxation advice. Furthermore, based on the stress data, the management department can evaluate the user's health status and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' stress levels and utilizing this information for health management.

[0076] The WellnessNavigator system can further monitor users' fluid intake and utilize this information for health management. For example, the management department can record users' fluid intake and encourage appropriate hydration. The management department can also provide appropriate hydration advice based on the fluid intake data. Furthermore, the management department can evaluate users' health status based on the fluid intake data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' fluid intake habits and utilizing this information for health management.

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

[0078] Step 1: The reception desk accepts voice input. For example, voice input can be accepted using a microphone or a smartphone app. Alternatively, voice recognition technology can be used to accept voice input. Step 2: The text conversion unit converts the audio received by the reception unit into text. For example, it uses speech recognition technology to convert the audio into text and improves the accuracy of the text conversion using a method to correct misrecognition. Step 3: The organization unit organizes the content converted into text by the text conversion unit as a medical record. For example, it organizes the content converted into text according to the medical record format and saves the content converted into text according to the medical record saving method. Step 4: The administration department manages the user's medication schedule. For example, they input the user's medication schedule and manage it according to the reminder settings. Step 5: The reminder department provides reminders based on the schedule managed by the management department. For example, it provides reminders according to the format and timing of the notifications. Step 6: The dialogue unit interacts with the user. For example, it interacts with the user according to the content and frequency of the conversation. Step 7: The verification unit checks the user's health status based on the information obtained by the dialogue unit. For example, it checks the user's health status according to the items and frequency to be checked.

[0079] (Example of form 2) The WellnessNavigator system according to an embodiment of the present invention is a health management and treatment support system for the elderly and users unfamiliar with AI technology, utilizing a voice assistant. The WellnessNavigator system provides a function that transcribes the content of medical examinations in real time and automatically creates and organizes medical records using AI. This reduces the record-keeping work of doctors and nurses and improves work efficiency. For example, the AI ​​transcribes conversations during examinations in real time and automatically creates medical records based on that text. This allows healthcare professionals to concentrate on examinations and reduces the time spent on manual record-keeping. Next, it facilitates health management for the elderly through a medication reminder function and medication management support. For example, the AI ​​understands the user's medication schedule and provides reminders at the appropriate time. Also, if the user is taking multiple medications, it explains the risks of interactions and side effects and provides warnings. This reduces the risk of medication errors and missed doses among the elderly. Furthermore, through a daily dialogue function via voice, it helps people experiencing social isolation and loneliness to receive appropriate support. For example, the AI ​​can monitor users' daily health and mood, and increase opportunities for communication to reduce feelings of social isolation. It can also support medical consultations, reducing the burden on healthcare professionals and allowing them to focus more on patients. Through this, the WellnessNavigator system aims to improve the efficiency of healthcare professionals' work, enhance health management for the elderly, and reduce feelings of isolation, thereby enabling a more secure life, by utilizing a voice assistant to provide automatic creation of medical records, medication reminders, and conversational functions.

[0080] The WellnessNavigator system according to this embodiment comprises a reception unit, a text conversion unit, an organization unit, a management unit, a reminder unit, a dialogue unit, and a confirmation unit. The reception unit receives voice input. The reception unit receives voice input using, for example, a microphone. The reception unit can also receive voice input using a smartphone app. Furthermore, the reception unit can also receive voice input using speech recognition technology. For example, the reception unit converts speech to text using speech recognition technology. The text conversion unit converts the voice received by the reception unit into text. The text conversion unit converts speech to text using, for example, speech recognition technology. Furthermore, the text conversion unit can improve the accuracy of text conversion using a method for correcting misrecognition. Furthermore, the text conversion unit can adjust the text conversion method according to the type of speech recognition technology. For example, the text conversion unit converts speech to text using speech recognition technology and improves the accuracy of text conversion using a method for correcting misrecognition. The organization unit organizes the content converted into text by the text conversion unit as a medical record. The organization unit organizes the text content according to the format of the medical record, for example. The organization unit can also save the text content according to the method of saving the medical record. Furthermore, the organization unit can organize the text content according to the method of organizing the medical record. For example, the organization unit organizes the text content according to the format of the medical record and saves the text content according to the method of saving the medical record. The management unit manages the user's medication schedule. For example, the management unit inputs the user's medication schedule. Furthermore, the management unit can manage the medication schedule according to the method of setting reminders. Furthermore, the management unit can manage the medication schedule according to the method of managing the medication schedule. For example, the management unit inputs the user's medication schedule and manages the medication schedule according to the method of setting reminders. The reminder unit provides reminders based on the schedule managed by the management unit. The reminder unit provides reminders according to the format of the notification, for example. Furthermore, the reminder unit can provide reminders according to the timing of the notification.Furthermore, the reminder unit can provide reminders according to the method of providing reminders. For example, the reminder unit can provide reminders according to the format of the notification and according to the timing of the notification. The dialogue unit interacts with the user. For example, the dialogue unit interacts with the user according to the content of the dialogue. The dialogue unit can also interact with the user according to the frequency of the dialogue. Furthermore, the dialogue unit can also interact with the user according to the method of the dialogue. For example, the dialogue unit interacts with the user according to the content of the dialogue and according to the frequency of the dialogue. The confirmation unit confirms the user's health status based on the information obtained by the dialogue unit. For example, the confirmation unit confirms the user's health status according to the items to be confirmed. The confirmation unit can also confirm the user's health status according to the frequency of confirmation. Furthermore, the confirmation unit can also confirm the user's health status according to the method of confirming the health status. For example, the confirmation unit confirms the user's health status according to the items to be confirmed and according to the frequency of confirmation. As a result, the WellnessNavigator system according to this embodiment can provide automatic creation of medical records, medication reminders, and dialogue functions through voice input, thereby improving the work efficiency of healthcare professionals, enhancing health management for the elderly, and reducing feelings of isolation.

[0081] The reception desk accepts voice input. For example, the reception desk accepts voice input using a microphone. Specifically, the microphone is highly sensitive and features noise cancellation to eliminate ambient noise, allowing users to input clear voice. The reception desk can also accept voice input using a smartphone app. The smartphone app provides an intuitive interface for easy voice input, allowing users to start and stop voice input with a single touch. Furthermore, the reception desk can accept voice input using speech recognition technology. For example, the reception desk converts speech to text using speech recognition technology. The speech recognition technology employs advanced algorithms using deep learning, enabling high-precision recognition of differences in user pronunciation and accent. This allows the reception desk to ensure accurate voice input in any environment, improving the overall reliability of the system.

[0082] The text conversion unit converts the audio received by the reception unit into text. The text conversion unit converts audio to text using, for example, speech recognition technology. Specifically, speech recognition technology analyzes audio data, identifies phoneme and word patterns, and converts them into text. The text conversion unit can also improve the accuracy of the conversion using methods to correct misrecognition. For example, if the user misrecognizes a particular word or phrase, the text conversion unit makes appropriate corrections based on context and past data. Furthermore, the text conversion unit can adjust the conversion method depending on the type of speech recognition technology used. For example, it can combine different speech recognition engines and select the most accurate result. This allows the text conversion unit to handle diverse audio input situations and achieve highly accurate conversion.

[0083] The editing department organizes the content converted into text by the text conversion department as medical records. For example, the editing department organizes the text according to the medical record format. Specifically, the medical record format includes items such as basic patient information, treatment details, prescribed medications, and the next scheduled appointment. The editing department can also save the text according to the medical record storage method. For example, it can automatically save the data to an electronic medical record system, allowing healthcare professionals to access it as needed. Furthermore, the editing department can organize the text according to the medical record organization method. For example, it can organize the text according to the medical record format and save the text according to the medical record storage method. This ensures that the editing department maintains the consistency and accuracy of medical records and allows healthcare professionals to manage information efficiently.

[0084] The administration department manages the user's medication schedule. For example, the administration department inputs the user's medication schedule. Specifically, it inputs information such as the name of the medication the user takes, the time to take it, and the dosage, and saves it in the system. The administration department can also manage the medication schedule according to the reminder setting method. For example, it can set a reminder at a time specified by the user and send a notification. Furthermore, the administration department can manage the medication schedule according to the medication schedule management method. For example, it inputs the user's medication schedule and manages the medication schedule according to the reminder setting method. In this way, the administration department ensures that users take their medication at the appropriate time and supports their health management.

[0085] The reminder unit provides reminders based on schedules managed by the management unit. The reminder unit provides reminders according to the notification format, for example. Specifically, it sends reminders in the form of smartphone push notifications, email, SMS, etc. The reminder unit can also provide reminders according to the timing of notifications. For example, it can send a notification 30 minutes before or immediately before taking medication to ensure that the user does not forget to take their medication. Furthermore, the reminder unit can provide reminders according to the method of providing reminders. For example, it can provide reminders according to the notification format and reminders according to the timing of notifications. In this way, the reminder unit helps users take their medication at the appropriate time and supports their health management.

[0086] The dialogue unit engages in conversations with the user. For example, the dialogue unit interacts with the user according to the content of the conversation. Specifically, it asks questions about the user's health and daily life and records the user's responses. The dialogue unit can also interact with the user according to the frequency of the conversation. For example, it can interact daily, once a week, or at a frequency specified by the user. Furthermore, the dialogue unit can interact with the user according to the method of interaction. For example, it can interact using methods such as voice conversation, text chat, or video call. This allows the dialogue unit to continuously monitor the user's health and provide necessary support.

[0087] The verification unit checks the user's health status based on the information obtained by the dialogue unit. For example, the verification unit checks the user's health status according to the items to be checked. Specifically, it checks health indicators such as the user's body temperature, blood pressure, heart rate, and weight. The verification unit can also check the user's health status according to the frequency of checks. For example, it can check the health status daily, once a week, or at a frequency specified by the user. Furthermore, the verification unit can check the user's health status according to the method of checking the health status. For example, it can check the user's health status according to the items to be checked and according to the frequency of checks. This allows the verification unit to continuously monitor the user's health status and respond early if an abnormality occurs.

[0088] The reception desk can transcribe conversations during consultations in real time. For example, the reception desk can use speech recognition technology to transcribe conversations during consultations in real time. The reception desk can also set an acceptable delay range for real-time transcription. Furthermore, the reception desk can improve the accuracy of transcription using real-time processing technology. For example, the reception desk can transcribe conversations during consultations in real time using speech recognition technology, set an acceptable delay range, and improve the accuracy of transcription using real-time processing technology. This allows for the rapid and accurate creation of medical records by transcribing conversations during consultations in real time. Some or all of the above processes in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can use an AI model with speech recognition technology to transcribe conversations during consultations in real time and improve the accuracy of transcription.

[0089] The text conversion unit can automatically create medical records based on the transcribed content. For example, the text conversion unit can use templates to automatically create medical records based on the transcribed content. The text conversion unit can also automatically create medical records using an automated data entry method. Furthermore, the text conversion unit can adjust the automated medical record creation method. For example, the text conversion unit can automatically create medical records based on transcribed content using templates, and can also automatically create medical records using an automated data entry method. This reduces the burden on healthcare professionals by automatically creating medical records based on transcribed content. Some or all of the above-described processes in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can use an AI model to automatically create medical records based on the transcribed content and adjust the automated medical record creation method.

[0090] The management department can understand the user's medication schedule and provide reminders at the appropriate time. For example, the management department uses a schedule input method to understand the user's medication schedule. The management department can also set the reminder notification interval. Furthermore, the management department can adjust how reminders are delivered. For example, the management department understands the user's medication schedule using the schedule input method and adjusts how reminders are delivered by setting the reminder notification interval. This reduces the risk of medication errors or missed doses by understanding the user's medication schedule and providing reminders at the appropriate time. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department may use an AI model to understand the user's medication schedule and adjust how reminders are delivered to provide them at the appropriate time.

[0091] The reminder unit can explain and warn about the risks of drug interactions and side effects. For example, the reminder unit uses risk assessment criteria to explain the risks of interactions and side effects. The reminder unit can also set the format of the explanation. Furthermore, the reminder unit can adjust the method of explaining the risks. For example, the reminder unit can explain the risks of interactions and side effects using risk assessment criteria and adjust the method of explaining the risks by setting the format of the explanation. This ensures user safety by explaining and warning about the risks of drug interactions and side effects. Some or all of the above processing in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit can use an AI model to adjust the method of explaining the risks in order to explain and warn about the risks of drug interactions and side effects.

[0092] The dialogue unit can check the user's daily health and mood and increase opportunities for communication. For example, the dialogue unit sets the content of questions to check the user's daily health and mood. The dialogue unit can also set the frequency of checks. Furthermore, the dialogue unit can adjust the method of the conversation. For example, the dialogue unit checks the user's daily health and mood by setting the content of questions and adjusts the method of the conversation by setting the frequency of checks. This reduces feelings of social isolation by checking the user's daily health and mood and increasing opportunities for communication. Some or all of the above processing in the dialogue unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the dialogue unit may use an emotion engine or generative AI and adjust the method of the conversation in order to check the user's daily health and mood and increase opportunities for communication.

[0093] The verification unit can provide support for medical consultations based on the user's health status. For example, the verification unit can set how to record the consultation content in order to provide support for medical consultations. The verification unit can also set how to provide support. Furthermore, the verification unit can adjust the method of providing support for medical consultations. For example, the verification unit can set how to record the consultation content to provide support for medical consultations based on the user's health status, and adjust the method of providing support for medical consultations by setting how to provide support. In this way, appropriate medical support is provided by providing support for medical consultations based on the user's health status. Some or all of the above processing in the verification unit may be performed using AI, for example, or not using AI. For example, the verification unit can use an AI model to adjust the method of providing support for medical consultations based on the user's health status.

[0094] The reception unit can estimate the user's emotions and adjust the timing of voice input reception based on the estimated emotions. For example, if the user is stressed, the reception unit can delay the timing of voice input reception to allow them to relax. Conversely, if the user is relaxed, the reception unit can speed up the timing of voice input reception to facilitate smoother conversation. Furthermore, if the user is in a hurry, the reception unit can make the timing of voice input reception immediate to enable a quick response. For example, if the reception unit is stressed, it can delay the timing of voice input reception to allow the user to relax, and if the user is relaxed, it can speed up the timing of voice input reception to facilitate smoother conversation. This allows for smoother conversation by adjusting the timing of voice input reception according to the user'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 unit may be performed using AI, for example, or without AI. For example, the reception desk can use an emotion engine or generative AI to estimate the user's emotions and adjust the timing of voice input reception based on the estimated user emotions.

[0095] The reception desk can analyze the importance of conversations during consultations and prioritize transcribing important parts. For example, the reception desk can prioritize transcribing important information about the patient's condition from the conversation. It can also prioritize transcribing important information about prescriptions from the conversation. Furthermore, the reception desk can prioritize transcribing important information about the next consultation from the conversation. For example, the reception desk can prioritize transcribing important information about the patient's condition and important information about prescriptions from the conversation. This improves the accuracy of medical records by prioritizing the transcription of important information during consultations. Some or all of the above processing at the reception desk may be performed using AI, for example, or not. For example, the reception desk can use an AI model to analyze the importance of conversations during consultations and prioritize transcribing important parts to improve the accuracy of transcription.

[0096] The reception unit can automatically remove background noise from voice input and obtain clear audio data. For example, the reception unit can automatically remove background noise in a medical examination room and obtain clear audio data. It can also automatically remove background noise in the user's home environment and obtain clear audio data. Furthermore, it can automatically remove background noise in public places and obtain clear audio data. For example, the reception unit can automatically remove background noise in a medical examination room and obtain clear audio data, and it can also automatically remove background noise in the user's home environment and obtain clear audio data. By removing background noise, clear audio data is obtained, improving the accuracy of text transcription. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can use an AI model and apply noise filtering technology to automatically remove background noise from voice input and obtain clear audio data.

[0097] The reception desk can estimate the user's emotions and determine the priority of voice input based on the estimated emotions. For example, if the user is nervous, the reception desk can set a high priority for voice input and respond quickly. Conversely, if the user is relaxed, the reception desk can set a low priority for voice input and respond slowly. Furthermore, if the user is in a hurry, the reception desk can set the highest priority for voice input and respond immediately. For example, if the reception desk is nervous, it can set a high priority for voice input and respond quickly, and if the user is relaxed, it can set a low priority for voice input and respond slowly. This allows for a quick and appropriate response by determining the priority of voice input according to the user'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 reception desk may be performed using AI, for example, or without AI. For example, the reception desk can use an emotion engine or generative AI to estimate the user's emotions and determine the priority of voice input based on those estimated emotions.

[0098] The reception desk can prioritize retrieving highly relevant information by considering the user's geographical location during voice input. For example, if the user is in a hospital, the reception desk will prioritize retrieving information related to consultations within the hospital. Similarly, if the user is at home, the reception desk can prioritize retrieving information related to health management at home. Furthermore, if the user is traveling, the reception desk can prioritize retrieving medical information at their travel destination. For instance, if the user is in a hospital, the reception desk prioritizes retrieving information related to consultations within the hospital; if the user is at home, it prioritizes retrieving information related to health management at home. This allows for the prioritization of highly relevant information by considering the user's geographical location, enabling appropriate responses. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can use an AI model to determine information priorities in order to prioritize retrieving highly relevant information by considering the user's geographical location during voice input.

[0099] The reception desk can prioritize retrieving relevant information by referring to the user's past medical history when voice input is received. For example, the reception desk can prioritize retrieving information related to the current consultation from the user's past consultation history. It can also prioritize retrieving information related to prescribed medications from the user's past consultation history. Furthermore, the reception desk can prioritize retrieving information related to the next consultation from the user's past consultation history. For example, the reception desk prioritizes retrieving information related to the current consultation and information related to prescribed medications from the user's past consultation history. By referring to the user's past consultation history, relevant information is prioritized, improving the accuracy of the consultation. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can use an AI model to determine the priority of information in order to prioritize retrieving relevant information by referring to the user's past consultation history when voice input is received.

[0100] The text generation unit can estimate the user's emotions and adjust the textual expression based on the estimated emotions. For example, if the user is nervous, the text generation unit will use a concise and easy-to-understand expression. If the user is relaxed, the text generation unit may also use an expression that includes detailed explanations. Furthermore, if the user is in a hurry, the text generation unit may also use an expression that gets straight to the point. For example, if the user is nervous, the text generation unit will use a concise and easy-to-understand expression, and if the user is relaxed, it will use an expression that includes detailed explanations. By adjusting the textual expression according to the user's emotions, it generates more easily understandable text. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the above processing in the text generation unit may be performed using AI, for example, or without AI. For example, the text generation unit can estimate the user's emotions and adjust the text representation based on the estimated emotions, using an emotion engine or generative AI.

[0101] The text conversion unit can adjust the level of detail in the text based on the speed and tone of the speech during the transcription process. For example, if the speech is fast, the text conversion unit will generate concise text. It can also generate detailed text if the speech is slow. Furthermore, if the speech has a high tone, the text conversion unit can generate emphasized text. For example, if the text conversion unit generates concise text when the speech is fast, and detailed text when the speech is slow. This allows for the generation of text with an appropriate amount of information by adjusting the level of detail based on the speed and tone of the speech. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can use an AI model to adjust the level of detail in the text based on the speed and tone of the speech during transcription.

[0102] The text conversion unit can automatically expand technical terms and abbreviations during the text conversion process to generate easily understandable text. For example, the text conversion unit can convert medical terms into common language and then convert them into text. It can also expand abbreviations to their full spellings and then convert them into text. Furthermore, the text conversion unit can generate text that includes explanations of technical terms. For example, the text conversion unit can convert medical terms into common language and then convert them into text, and expand abbreviations to their full spellings. This automatically expands technical terms and abbreviations to generate text that is easy for the user to understand. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or not. For example, the text conversion unit can use an AI model to adjust the method of terminology expansion in order to automatically expand technical terms and abbreviations during the text conversion process and generate easily understandable text.

[0103] The text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is in a hurry, the text generation unit will generate short, concise text. If the user is relaxed, the text generation unit can also generate longer text with detailed explanations. Furthermore, if the user is excited, the text generation unit can generate text with visually stimulating effects. For example, if the text generation unit is in a hurry, it will generate short, concise text, and if the user is relaxed, it will generate longer text with detailed explanations. By adjusting the length of the text according to the user's emotions, the text can generate an appropriate amount of information. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generative AI, but is not limited to these examples. Some or all of the above processing in the text generation unit may be performed using AI, for example, or without AI. For example, the text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions, using an emotion engine or generative AI.

[0104] The text conversion unit can determine the priority of text based on the recording date of the audio during the text conversion process. For example, the text conversion unit may prioritize the most recent audio recording. The text conversion unit can also refer to past audio recordings and prioritize those that are more relevant. Furthermore, the text conversion unit can prioritize those that are of higher importance based on the recording date of the audio. For example, the text conversion unit may prioritize the most recent audio recording and refer to past audio recordings to prioritize those that are more relevant. This ensures that important information is prioritized by determining the text priority based on the recording date of the audio. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit may use an AI model to determine the priority of text based on the recording date of the audio during the text conversion process.

[0105] The text conversion unit can adjust the order of the text based on the relevance of the audio during the conversion process. For example, if the audio content is related, the text conversion unit will adjust the order before converting it to text. Furthermore, if the audio content is different, the text conversion unit can convert it in order of relevance. Additionally, if the audio content is repetitive, the text conversion unit can omit the duplicated parts during conversion. For example, if the audio content is related, the text conversion unit will adjust the order before converting it to text; if the audio content is different, it will convert it in order of relevance. This process, by adjusting the order of the text based on the relevance of the audio, generates more easily understandable text. Some or all of the above processing in the text conversion unit may be performed using, for example, AI, or not. For example, the text conversion unit can use an AI model to adjust the order of the text based on the relevance of the audio during the conversion process.

[0106] The organization unit can estimate the user's emotions and adjust the organization method of medical records based on the estimated emotions. For example, if the user is nervous, the organization unit will use a concise and easy-to-understand organization method. If the user is relaxed, the organization unit may also use an organization method that includes detailed explanations. Furthermore, if the user is in a hurry, the organization unit may also use a concise and easy-to-understand organization method. For example, if the user is nervous, the organization unit will use a concise and easy-to-understand organization method, and if the user is relaxed, it will use an organization method that includes detailed explanations. By adjusting the organization method of medical records according to the user's emotions, it provides records that are easier to understand. 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 organization unit may be performed using AI, for example, or not using AI. For example, the organization unit can use an emotion engine or generative AI to estimate the user's emotions and adjust the organization method of medical records based on the estimated emotions.

[0107] The organization unit can select the optimal organization method by referring to past medical data when organizing medical records. For example, the organization unit can select the optimal organization method based on past medical data. The organization unit can also prioritize organizing highly relevant information from past medical data. Furthermore, the organization unit can analyze past medical data and select an efficient organization method. For example, the organization unit selects the optimal organization method based on past medical data and prioritizes organizing highly relevant information from past medical data. This makes it possible to select the optimal organization method by referring to past medical data and to organize records efficiently. Some or all of the above processes in the organization unit may be performed using AI, for example, or not using AI. For example, the organization unit can use an AI model to select the optimal organization method by referring to past medical data when organizing medical records.

[0108] The organization unit can apply different organization algorithms to each category of medical examination content when organizing medical records. For example, if the medical examination content relates to a medical condition, the organization unit can apply an organization algorithm specialized for medical conditions. Furthermore, if the medical examination content relates to a prescription, the organization unit can apply an organization algorithm specialized for prescriptions. In addition, if the medical examination content relates to a next appointment, the organization unit can apply an organization algorithm specialized for the next appointment. For example, if the medical examination content relates to a medical condition, the organization unit can apply an organization algorithm specialized for medical conditions, and if the medical examination content relates to a prescription, it can apply an organization algorithm specialized for prescriptions. This allows for more appropriate record organization by applying different organization algorithms to each category of medical examination content. Some or all of the above processing in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can use an AI model to apply different organization algorithms to each category of medical examination content when organizing medical records.

[0109] The sorting unit can estimate the user's emotions and determine the priority of medical records based on the estimated emotions. For example, if the user is nervous, the sorting unit can set a high priority for the medical records and sort them quickly. Conversely, if the user is relaxed, the sorting unit can set a low priority for the medical records and sort them slowly. Furthermore, if the user is in a hurry, the sorting unit can set the highest priority for the medical records and sort them immediately. For example, if the sorting unit is nervous, it sets a high priority for the medical records and sorts them quickly, and if the user is relaxed, it sets a low priority for the medical records and sorts them slowly. This enables quick and appropriate record sorting by determining the priority of medical records according to the user'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 sorting unit may be performed using AI, for example, or without AI. For example, the sorting unit can use an emotion engine or generative AI to estimate the user's emotions and determine the priority of medical records based on those estimated emotions.

[0110] The sorting department can determine the sorting priority based on the date the medical consultation was submitted when sorting medical records. For example, the sorting department can prioritize sorting the most recent medical records. The sorting department can also refer to past medical records and prioritize sorting those with high relevance. Furthermore, the sorting department can prioritize sorting those with high importance based on the date the medical consultation was submitted. For example, the sorting department prioritizes sorting the most recent medical records and refers to past medical records to prioritize sorting those with high relevance. In this way, by determining the sorting priority based on the date the medical consultation was submitted, important records are sorted first. Some or all of the above processes in the sorting department may be performed using AI, for example, or not using AI. For example, the sorting department can use an AI model to determine the sorting priority based on the date the medical consultation was submitted when sorting medical records.

[0111] The organization unit can adjust the order of organization of medical records based on the relevance of the consultations. For example, if the content of the consultations is related, the organization unit will adjust the order of organization. Furthermore, if the content of the consultations is different, the organization unit can also organize them in order of relevance. In addition, if the content of the consultations is duplicated, the organization unit can omit the duplicated parts. For example, if the content of the consultations is related, the organization unit will adjust the order of organization; if the content is different, it will organize them in order of relevance. This provides records that are easier to understand by adjusting the order of organization based on the relevance of the consultations. Some or all of the above processing in the organization unit may be performed using AI, for example, or not. For example, the organization unit can use an AI model to adjust the order of organization based on the relevance of the consultations when organizing medical records.

[0112] The management unit can estimate the user's emotions and adjust the medication schedule management method based on the estimated emotions. For example, if the user is anxious, the management unit will use a concise and easy-to-understand management method. If the user is relaxed, the management unit may also use a management method that includes detailed explanations. Furthermore, if the user is in a hurry, the management unit may use a concise and easy-to-understand management method. For example, if the user is anxious, the management unit will use a concise and easy-to-understand management method, and if the user is relaxed, it will use a management method that includes detailed explanations. This allows for more appropriate medication management by adjusting the medication schedule management method according to the user'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 management unit may be performed using AI, for example, or not using AI. For example, the management department can use an emotion engine or generative AI to estimate the user's emotions and adjust the medication schedule management method based on the estimated user emotions.

[0113] The management department can select the optimal management method when managing medication schedules by referring to past medication data. For example, the management department can select the optimal management method based on past medication data. The management department can also prioritize the management of highly relevant information from past medication data. Furthermore, the management department can analyze past medication data and select an efficient management method. For example, the management department can select the optimal management method based on past medication data and prioritize the management of highly relevant information from past medication data. This makes it possible to select the optimal management method by referring to past medication data and to manage medication efficiently. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can use an AI model to select the optimal management method when managing medication schedules by referring to past medication data.

[0114] The management unit can apply different management algorithms for each type of medication when managing medication schedules. For example, if the medications are of different types, the management unit can apply a specialized management algorithm to each. Alternatively, if the medications are of the same type, the management unit can apply a common management algorithm. Furthermore, the management unit can select the optimal management algorithm depending on the type of medication. For example, if the medications are of different types, the management unit can apply a specialized management algorithm to each type, and if the medications are of the same type, it can apply a common management algorithm. This allows for more appropriate medication management by applying different management algorithms for each type of medication. Some or all of the above processes in the management unit may be performed using AI, for example, or not. For example, the management unit can use an AI model to apply different management algorithms for each type of medication when managing medication schedules.

[0115] The management unit can estimate the user's emotions and determine the priority of the medication schedule based on the estimated emotions. For example, if the user is stressed, the management unit can set a high priority for the medication schedule and manage it quickly. Conversely, if the user is relaxed, the management unit can set a low priority for the medication schedule and manage it slowly. Furthermore, if the user is in a hurry, the management unit can set the highest priority for the medication schedule and manage it immediately. For example, if the management unit is stressed, it can set a high priority for the medication schedule and manage it quickly, and if the user is relaxed, it can set a low priority for the medication schedule and manage it slowly. This enables quick and appropriate medication management by determining the priority of the medication schedule according to the user'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 management unit may be performed using AI, for example, or without AI. For example, the management department can use an emotion engine or generative AI to estimate the user's emotions and determine the priority of medication schedules based on those estimated emotions.

[0116] The management department can prioritize highly relevant schedules when managing medication schedules, taking into account the user's geographical location. For example, if the user is in a hospital, the management department will prioritize medication schedules within the hospital. Similarly, if the user is at home, the management department can prioritize medication schedules at home. Furthermore, if the user is traveling, the management department can prioritize medication schedules at their travel destination. For instance, if the user is in a hospital, the management department prioritizes medication schedules within the hospital; if the user is at home, it prioritizes medication schedules at home. This allows for appropriate medication management by prioritizing highly relevant schedules while considering the user's geographical location. Some or all of the above processing in the management department may be performed using AI, or not. For example, the management department can use an AI model to determine schedule priorities in order to prioritize highly relevant schedules while considering the user's geographical location when managing medication schedules.

[0117] The management department can analyze users' social media activity and manage related schedules when managing medication schedules. For example, the management department can prioritize information related to medication schedules from users' social media activity. The management department can also analyze users' social media activity and propose an optimal medication schedule. Furthermore, the management department can determine the priority of medication schedules based on users' social media activity. For example, the management department prioritizes information related to medication schedules from users' social media activity and proposes an optimal medication schedule by analyzing users' social media activity. This enables appropriate medication management by analyzing users' social media activity and managing related schedules. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, the management department can use an AI model to analyze users' social media activity and manage related schedules when managing medication schedules, and to determine the priority of schedules.

[0118] The reminder unit can estimate the user's emotions and adjust the way the reminder is presented based on the estimated emotions. For example, if the user is nervous, the reminder unit can provide a reminder in a calm voice. It can also provide a reminder in a cheerful voice if the user is relaxed. Furthermore, if the user is in a hurry, the reminder unit can provide a quick and concise reminder. For example, if the reminder unit is nervous, it can provide a reminder in a calm voice; if the user is relaxed, it can provide a reminder in a cheerful voice. This allows for more effective reminders by adjusting the way the reminder is presented according to the user'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 reminder unit may be performed using AI, or not. For example, the reminder unit can estimate the user's emotions and adjust the way the reminder is presented based on those emotions using an emotion engine or generative AI.

[0119] The reminder unit can adjust the level of detail in reminders based on the importance of the drug when providing them. For example, the reminder unit can provide detailed reminders for important drugs, and concise reminders for less important drugs. Furthermore, the reminder unit can adjust the level of detail in reminders according to the importance of the drug. For example, the reminder unit can provide detailed reminders for important drugs and concise reminders for less important drugs. By adjusting the level of detail in reminders based on the importance of the drug, the system can provide reminders with an appropriate amount of information. Some or all of the above processing in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit can use an AI model to adjust the level of detail in reminders based on the importance of the drug when providing them.

[0120] The reminder unit can apply different reminder algorithms depending on the drug category when providing reminders. For example, if the drug categories are different, the reminder unit can apply a specialized reminder algorithm to each. Alternatively, if the drug categories are the same, the reminder unit can apply a common reminder algorithm. Furthermore, the reminder unit can select the optimal reminder algorithm depending on the drug category. For example, if the drug categories are different, the reminder unit can apply a specialized reminder algorithm to each, and if the drug categories are the same, it can apply a common reminder algorithm. This allows for the provision of more appropriate reminders by applying different reminder algorithms depending on the drug category. Some or all of the above processing in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit can use an AI model to apply different reminder algorithms depending on the drug category when providing reminders.

[0121] The reminder function can estimate the user's emotions and adjust the length of the reminder based on the estimated emotions. For example, if the user is in a hurry, the reminder function will provide a short, to-the-point reminder. If the user is relaxed, the reminder function can also provide a longer reminder with detailed explanations. Furthermore, if the user is excited, the reminder function can provide a reminder with visually stimulating effects. For example, if the user is in a hurry, the reminder function will provide a short, to-the-point reminder, and if the user is relaxed, it will provide a longer reminder with detailed explanations. By adjusting the length of the reminder according to the user's emotions, the system can provide a reminder with an appropriate amount of information. Emotion estimation is achieved using an emotion estimation function, for example, using 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 processing in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit may use an emotion engine or generative AI to estimate the user's emotions and adjust the length of the reminder based on the estimated user emotions.

[0122] The reminder unit can prioritize reminders based on the timing of drug submission when providing reminders. For example, the reminder unit may prioritize providing reminders for the most recent medication. The reminder unit can also refer to past medication reminders and prioritize those that are most relevant. Furthermore, the reminder unit can prioritize those of high importance based on the timing of drug submission. For example, the reminder unit prioritizes providing reminders for the most recent medication and refers to past medication reminders to prioritize those that are most relevant. This ensures that important reminders are prioritized by determining the priority of reminders based on the timing of drug submission. Some or all of the above processing in the reminder unit may be performed using AI, for example, or not using AI. For example, the reminder unit may use an AI model to determine the priority of reminders based on the timing of drug submission when providing reminders.

[0123] The reminder unit can adjust the order of reminders based on the relevance of the drugs when providing them. For example, if the contents of the drugs are related, the reminder unit will adjust the order in which it provides reminders. The reminder unit can also provide reminders in order of relevance if the contents of the drugs are different. Furthermore, if the contents of the drugs overlap, the reminder unit can provide reminders while omitting the overlapping parts. For example, if the contents of the drugs are related, the reminder unit will adjust the order in which it provides reminders, and if the contents of the drugs are different, it will provide reminders in order of relevance. By adjusting the order of reminders based on the relevance of the drugs, the reminder unit can provide more easily understood reminders. Some or all of the above processing in the reminder unit may be performed using AI, for example, or not using AI. For example, the reminder unit can use an AI model to adjust the order of reminders based on the relevance of the drugs when providing them.

[0124] The dialogue unit can estimate the user's emotions and adjust the way the dialogue is expressed based on those emotions. For example, if the user is nervous, the dialogue unit will speak in a calm voice. If the user is relaxed, the dialogue unit can also speak in a cheerful voice. Furthermore, if the user is in a hurry, the dialogue unit can speak quickly and concisely. For example, if the dialogue unit is nervous, it will speak in a calm voice, and if the user is relaxed, it will speak in a cheerful voice. This allows for more effective dialogue by adjusting the way the dialogue is expressed according to the user'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 dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can use an emotion engine or generative AI to estimate the user's emotions and adjust the way the dialogue is expressed based on those estimated emotions.

[0125] The dialogue unit can select the optimal dialogue method by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can prioritize the use of highly relevant information from the user's past dialogue history. The dialogue unit can also analyze the user's past dialogue history to select an efficient dialogue method. Furthermore, the dialogue unit can propose an optimal dialogue method based on the user's past dialogue history. For example, the dialogue unit prioritizes the use of highly relevant information from the user's past dialogue history and analyzes the user's past dialogue history to select an efficient dialogue method. In this way, by referring to the user's past dialogue history, the dialogue unit selects the optimal dialogue method and provides an effective conversation. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit may use an AI model to select the optimal dialogue method by referring to the user's past dialogue history during a conversation.

[0126] The dialogue unit can customize the content of the conversation based on the user's current living situation. For example, the dialogue unit can consider the user's current living situation and provide highly relevant dialogue content. The dialogue unit can also analyze the user's current living situation and suggest the most appropriate dialogue content. Furthermore, the dialogue unit can customize the dialogue content based on the user's current living situation. For example, the dialogue unit considers the user's current living situation, provides highly relevant dialogue content, and analyzes the user's current living situation to suggest the most appropriate dialogue content. By customizing the dialogue content based on the user's current living situation, it provides a more relevant conversation. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can use an AI model to customize the dialogue content based on the user's current living situation during a conversation.

[0127] The dialogue unit can estimate the user's emotions and determine the priority of the dialogue based on the estimated emotions. For example, if the user is nervous, the dialogue unit can set a high priority for the dialogue and respond quickly. Conversely, if the user is relaxed, the dialogue unit can set a low priority for the dialogue and respond slowly. Furthermore, if the user is in a hurry, the dialogue unit can set the highest priority for the dialogue and respond immediately. For example, if the dialogue unit is nervous, it sets a high priority for the dialogue and responds quickly, and if the user is relaxed, it sets a low priority for the dialogue and responds slowly. This allows for a quick and appropriate response by determining the priority of the dialogue according to the user'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 dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can use an emotion engine or generative AI to estimate the user's emotions and determine dialogue priorities based on those estimated emotions.

[0128] The dialogue unit can select the optimal dialogue method during a conversation, taking into account the user's geographical location. For example, if the user is in a hospital, the dialogue unit will prioritize a dialogue method within the hospital. Similarly, if the user is at home, the dialogue unit can prioritize a dialogue method suitable for home use. Furthermore, if the user is traveling, the dialogue unit can prioritize a dialogue method suitable for their travel destination. For instance, if the user is in a hospital, the dialogue unit will prioritize a dialogue method within the hospital; if the user is at home, it will prioritize a dialogue method suitable for home use. This allows for the selection of the optimal dialogue method and appropriate responses by considering the user's geographical location. Some or all of the above processing in the dialogue unit may be performed using AI, or not. For example, the dialogue unit may use an AI model to select the optimal dialogue method during a conversation, taking into account the user's geographical location.

[0129] The dialogue unit can analyze the user's social media activity during a conversation and suggest conversation content. For example, the dialogue unit can suggest highly relevant conversation content based on the user's social media activity. Furthermore, the dialogue unit can analyze the user's social media activity and suggest the most appropriate conversation content. In addition, the dialogue unit can customize conversation content based on the user's social media activity. For example, the dialogue unit suggests highly relevant conversation content based on the user's social media activity and then analyzes the user's social media activity to suggest the most appropriate conversation content. This allows the dialogue unit to suggest highly relevant conversation content and provide an effective conversation by analyzing the user's social media activity. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can use an AI model to analyze the user's social media activity during a conversation and suggest conversation content.

[0130] The verification unit can estimate the user's emotions and adjust the method of checking their health status based on the estimated emotions. For example, if the user is nervous, the verification unit will use a concise and easy-to-understand verification method. If the user is relaxed, the verification unit may also use a verification method that includes detailed explanations. Furthermore, if the user is in a hurry, the verification unit may also use a concise and easy-to-understand verification method. For example, if the user is nervous, the verification unit will use a concise and easy-to-understand verification method, and if the user is relaxed, it will use a verification method that includes detailed explanations. This allows for more appropriate verification by adjusting the method of checking the health status according to the user'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 verification unit may be performed using AI, for example, or without AI. For example, the verification unit can use an emotion engine or generative AI to estimate the user's emotions and adjust the method of checking their health status based on the estimated emotions.

[0131] The verification unit can select the optimal verification method by referring to past health data when checking a person's health status. For example, the verification unit selects the optimal verification method based on past health data. The verification unit can also prioritize checking highly relevant information from past health data. Furthermore, the verification unit can analyze past health data and select an efficient verification method. For example, the verification unit selects the optimal verification method based on past health data and prioritizes checking highly relevant information from past health data. This makes it possible to select the optimal verification method by referring to past health data and to perform an efficient health check. Some or all of the above processing in the verification unit may be performed using AI, for example, or without using AI. For example, the verification unit may use an AI model to select the optimal verification method by referring to past health data when checking a person's health status.

[0132] The verification unit can customize the verification methods based on the user's current living situation when verifying health status. For example, the verification unit considers the user's current living situation and provides highly relevant verification methods. The verification unit can also analyze the user's current living situation and propose the optimal verification method. Furthermore, the verification unit can customize the verification methods based on the user's current living situation. For example, the verification unit considers the user's current living situation, provides highly relevant verification methods, and analyzes the user's current living situation to propose the optimal verification method. By customizing the verification methods based on the user's current living situation, more relevant verification becomes possible. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can use an AI model to customize the verification methods based on the user's current living situation when verifying health status.

[0133] The verification unit can estimate the user's emotions and determine the priority of health status based on the estimated emotions. For example, if the user is tense, the verification unit can set a high priority for health status and perform a quick check. Conversely, if the user is relaxed, the verification unit can set a low priority for health status and perform a slow check. Furthermore, if the user is in a hurry, the verification unit can set the highest priority for health status and perform an immediate check. For example, if the verification unit is tense, it can set a high priority for health status and perform a quick check, and if the user is relaxed, it can set a low priority for health status and perform a slow check. This enables quick and appropriate verification by determining the priority of health status according to the user'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 verification unit may be performed using AI, for example, or without AI. For example, the verification unit can estimate the user's emotions and use an emotion engine or generative AI to determine the priority of health conditions based on the estimated user emotions.

[0134] The verification unit can select the optimal verification method when checking the user's health status, taking into account the user's geographical location information. For example, if the user is in a hospital, the verification unit will prioritize selecting a verification method within the hospital. Similarly, if the user is at home, the verification unit can prioritize selecting a verification method at their home. Furthermore, if the user is traveling, the verification unit can prioritize selecting a verification method at their travel destination. For example, if the user is in a hospital, the verification unit will prioritize selecting a verification method within the hospital; if the user is at home, it will prioritize selecting a verification method at their home. This allows for the selection of the optimal verification method and appropriate action by considering the user's geographical location information. Some or all of the above processing in the verification unit may be performed using AI, or not. For example, the verification unit may use an AI model to select the optimal verification method when checking the user's health status, taking into account the user's geographical location information.

[0135] The verification unit can analyze the user's social media activity and propose verification methods when checking the user's health status. For example, the verification unit can propose highly relevant verification methods based on the user's social media activity. The verification unit can also analyze the user's social media activity and propose the most suitable verification method. Furthermore, the verification unit can customize the verification methods based on the user's social media activity. For example, the verification unit can propose highly relevant verification methods based on the user's social media activity and propose the most suitable verification method by analyzing the user's social media activity. This enables effective health checks by proposing highly relevant verification methods through analysis of the user's social media activity. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can use an AI model to propose verification methods by analyzing the user's social media activity when checking the user's health status.

[0136] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0137] The WellnessNavigator system can also acquire user exercise data and use it to help with health management. For example, the management department can record users' steps and exercise volume to understand their daily exercise habits. The management department can also provide appropriate exercise advice based on the exercise data. Furthermore, the management department can evaluate the user's health status based on the exercise data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' exercise habits and using that information for health management.

[0138] The WellnessNavigator system can also acquire users' dietary data and use it to support their health management. For example, the management department can record the user's meals and evaluate their nutritional balance. The management department can also provide appropriate dietary advice based on this data. Furthermore, the management department can assess the user's health status based on the dietary data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' eating habits and utilizing that information for health management.

[0139] The WellnessNavigator system can also acquire user sleep data and use it for health management. For example, the management department can record the user's sleep duration and quality to understand their sleep patterns. The management department can also provide appropriate sleep advice based on the sleep data. Furthermore, the management department can evaluate the user's health status based on the sleep data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding the user's sleep habits and using that information for health management.

[0140] The WellnessNavigator system can further monitor users' stress levels and utilize this information for health management. For example, the management department can record users' heart rate and skin electrical activity to assess their stress levels. Based on this stress data, the management department can also provide appropriate relaxation advice. Furthermore, based on the stress data, the management department can evaluate the user's health status and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' stress levels and utilizing this information for health management.

[0141] The WellnessNavigator system can further monitor users' fluid intake and utilize this information for health management. For example, the management department can record users' fluid intake and encourage appropriate hydration. The management department can also provide appropriate hydration advice based on the fluid intake data. Furthermore, the management department can evaluate users' health status based on the fluid intake data and notify healthcare professionals as needed. This allows for a more comprehensive health support system by understanding users' fluid intake habits and utilizing this information for health management.

[0142] The WellnessNavigator system can estimate a user's emotions and provide exercise advice based on those emotions. For example, if a user is feeling stressed, it can suggest relaxing exercises. If the user is feeling energetic, it can suggest energetic exercises. Furthermore, if the user is tired, it can suggest light stretching. By providing exercise advice tailored to the user's emotions, it can achieve more effective health support.

[0143] The WellnessNavigator system can estimate a user's emotions and provide dietary advice based on those emotions. For example, if a user is feeling stressed, it can suggest a relaxing meal. If the user is feeling energetic, it can suggest an energizing meal. Furthermore, if the user is tired, it can suggest an easily digestible meal. By providing dietary advice tailored to the user's emotions, it can achieve more effective health support.

[0144] The WellnessNavigator system can estimate a user's emotions and provide sleep advice based on those emotions. For example, if a user is feeling stressed, it can suggest a relaxing sleep environment. If the user is feeling energetic, it can suggest an appropriate amount of sleep. Furthermore, if the user is tired, it can suggest ways to promote deep sleep. By providing sleep advice tailored to the user's emotions, it can achieve more effective health support.

[0145] The WellnessNavigator system can estimate a user's emotions and provide stress management advice based on those emotions. For example, if a user is feeling stressed, it can suggest relaxation methods. If the user is feeling energetic, it can suggest stress-relieving activities. Furthermore, if the user is feeling tired, it can suggest ways to refresh themselves. By providing stress management advice tailored to the user's emotions, it can achieve more effective health support.

[0146] The WellnessNavigator system can estimate a user's emotions and provide hydration advice based on those emotions. For example, if a user is feeling stressed, it can suggest a relaxing drink. If the user is feeling energetic, it can suggest an energizing drink. Furthermore, if the user is tired, it can suggest a refreshing drink. By providing hydration advice tailored to the user's emotions, it can achieve more effective health support.

[0147] The following briefly describes the processing flow for example form 2.

[0148] Step 1: The reception desk accepts voice input. For example, voice input can be accepted using a microphone or a smartphone app. Alternatively, voice recognition technology can be used to accept voice input. Step 2: The text conversion unit converts the audio received by the reception unit into text. For example, it uses speech recognition technology to convert the audio into text and improves the accuracy of the text conversion using a method to correct misrecognition. Step 3: The organization unit organizes the content converted into text by the text conversion unit as a medical record. For example, it organizes the content converted into text according to the medical record format and saves the content converted into text according to the medical record saving method. Step 4: The administration department manages the user's medication schedule. For example, they input the user's medication schedule and manage it according to the reminder settings. Step 5: The reminder department provides reminders based on the schedule managed by the management department. For example, it provides reminders according to the format and timing of the notifications. Step 6: The dialogue unit interacts with the user. For example, it interacts with the user according to the content and frequency of the conversation. Step 7: The verification unit checks the user's health status based on the information obtained by the dialogue unit. For example, it checks the user's health status according to the items and frequency to be checked.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the reception unit, text conversion unit, organization unit, management unit, reminder unit, dialogue unit, and confirmation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 38B of the smart device 14 and converts the voice to text using the control unit 46A. The text conversion unit converts the voice to text using the identification processing unit 290 of the data processing unit 12 and corrects any misrecognitions. The organization unit organizes the texted content as a medical record and stores it in the database 24. The management unit manages the user's medication schedule, and the reminder unit provides reminders based on the managed schedule. The dialogue unit interacts with the user, and the confirmation unit confirms the user's health status based on the information obtained by the dialogue unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0153] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the reception unit, text conversion unit, organization unit, management unit, reminder unit, dialogue unit, and confirmation 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 voice input using the microphone 238 of the smart glasses 214 and converts the voice to text by the control unit 46A. The text conversion unit converts the voice to text using the identification processing unit 290 of the data processing unit 12 and corrects any misrecognitions. The organization unit organizes the texted content as a medical record and stores it in the database 24. The management unit manages the user's medication schedule, and the reminder unit provides reminders based on the managed schedule. The dialogue unit interacts with the user, and the confirmation unit confirms the user's health status based on the information obtained by the dialogue unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0169] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] Each of the multiple elements described above, including the reception unit, text conversion unit, organization unit, management unit, reminder unit, dialogue unit, and confirmation unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the headset terminal 314 and converts the voice to text using the control unit 46A. The text conversion unit converts the voice to text using the identification processing unit 290 of the data processing unit 12 and corrects any misrecognitions. The organization unit organizes the texted content as a medical record and stores it in the database 24. The management unit manages the user's medication schedule, and the reminder unit provides reminders based on the managed schedule. The dialogue unit interacts with the user, and the confirmation unit confirms the user's health status based on the information obtained by the dialogue unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0185] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.).

[0198] 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.

[0199] 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.

[0200] 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.

[0201] Each of the multiple elements described above, including the reception unit, text conversion unit, organization unit, management unit, reminder unit, dialogue unit, and confirmation unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the robot 414 and converts the voice to text by the control unit 46A. The text conversion unit converts the voice to text using the identification processing unit 290 of the data processing unit 12 and corrects any misrecognitions. The organization unit organizes the texted content as a medical record and stores it in the database 24. The management unit manages the user's medication schedule, and the reminder unit provides reminders based on the managed schedule. The dialogue unit interacts with the user, and the confirmation unit confirms the user's health status based on the information obtained by the dialogue unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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."

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] (Note 1) A reception desk that accepts voice input, A text conversion unit that converts the audio received by the reception unit into text, A text conversion unit organizes the content converted into text as a medical record, The management department manages the users' medication schedules, A reminder unit provides reminders based on the schedule managed by the aforementioned management unit, A dialogue unit that interacts with the user, The system includes a confirmation unit that checks the user's health status based on the information obtained by the aforementioned dialogue unit. A system characterized by the following features. (Note 2) The aforementioned reception unit is The conversation during the consultation is transcribed into text in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The text conversion unit, Automatically create medical records based on the transcribed text. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned management department, Understand the user's medication schedule and provide reminders at the appropriate time. The system described in Appendix 1, characterized by the features described herein. (Note 5) The reminder unit is, Explain the risks of drug interactions and side effects, and issue a warning. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned dialogue unit, Checking users' daily health and mood, and increasing opportunities for communication. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned verification unit is We provide medical consultation support based on the user's health status. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is The importance of conversations during consultations is analyzed, and the most important parts are prioritized for transcription. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is Automatically removes background noise from voice input to obtain clear audio data. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is It estimates the user's emotions and determines the priority of voice input based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When using voice input, the system prioritizes retrieving highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is During voice input, the system prioritizes retrieving relevant information by referencing the user's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 14) The text conversion unit, It estimates the user's emotions and adjusts the textual expression based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The text conversion unit, When transcribing, adjust the level of detail in the text based on the speed and tone of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 16) The text conversion unit, During text conversion, technical terms and abbreviations are automatically expanded to generate easily understandable text. The system described in Appendix 1, characterized by the features described herein. (Note 17) The text conversion unit, It estimates the user's emotions and adjusts the length of the text based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The text conversion unit, When transcribing, the text is prioritized based on when the audio was recorded. The system described in Appendix 1, characterized by the features described herein. (Note 19) The text conversion unit, When transcribing, the order of the text is adjusted based on the relevance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned editing unit, The system estimates the user's emotions and adjusts the method of organizing medical records based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned editing unit, When organizing medical records, refer to past medical data to select the most suitable organization method. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned editing unit, When organizing medical records, different organizational algorithms are applied to each category of medical treatment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned editing unit, The system estimates the user's emotions and prioritizes medical records based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned editing unit, When organizing medical records, prioritize the organization based on when the consultation was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned editing unit, When organizing medical records, adjust the order of organization based on the relevance of the consultations. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned management department, The system estimates the user's emotions and adjusts the medication schedule management method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned management department, When managing medication schedules, refer to past medication data to select the optimal management method. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned management department, When managing medication schedules, different management algorithms are applied for each type of medication. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned management department, The system estimates the user's emotions and prioritizes the medication schedule based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned management department, When managing medication schedules, the system prioritizes highly relevant schedules by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned management department, When managing medication schedules, analyze users' social media activity and manage relevant schedules. The system described in Appendix 1, characterized by the features described herein. (Note 32) The reminder unit is, It estimates the user's emotions and adjusts how reminders are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The reminder unit is, When providing reminders, adjust the level of detail in the reminders based on the importance of the medication. The system described in Appendix 1, characterized by the features described herein. (Note 34) The reminder unit is, When providing reminders, different reminder algorithms are applied depending on the drug category. The system described in Appendix 1, characterized by the features described herein. (Note 35) The reminder unit is, It estimates the user's emotions and adjusts the length of the reminder based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The reminder unit is, When providing reminders, prioritize them based on when the medication should be submitted. The system described in Appendix 1, characterized by the features described herein. (Note 37) The reminder unit is, When providing reminders, adjust the order of reminders based on their relevance to the medication. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way the dialogue is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned dialogue unit, During a conversation, the system selects the optimal conversation method by referring to the user's past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned dialogue unit, Customize the content of the dialogue based on the user's current living situation during the dialogue The system according to appended note 1, characterized in that (Appended note 41) The dialogue unit Estimate the user's emotion and determine the priority of the dialogue based on the estimated user's emotion The system according to appended note 1, characterized in that (Appended note 42) The dialogue unit Select an optimal dialogue method by considering the user's geographical location information during the dialogue The system according to appended note 1, characterized in that (Appended note 43) The dialogue unit Analyze the user's social media activities and propose the content of the dialogue during the dialogue The system according to appended note 1, characterized in that (Appended note 44) The confirmation unit Estimate the user's emotion and adjust the method of confirming the health status based on the estimated user's emotion The system according to appended note 1, characterized in that (Appended note 45) The confirmation unit Select an optimal confirmation method by referring to past health data when confirming the health status The system according to appended note 1, characterized in that (Appended note 46) The confirmation unit Customize the means of confirmation based on the user's current living situation when confirming the health status The system according to appended note 1, characterized in that (Appended note 47) The confirmation unit Estimate the user's emotion and determine the priority of the health status based on the estimated user's emotion The system according to appended note 1, characterized in that (Appended note 48) The confirmation unit When checking a user's health status, the system selects the most appropriate verification method, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 49) The aforementioned verification unit is When checking a user's health status, we analyze their social media activity and suggest methods for verification. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0221] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that accepts voice input, A text conversion unit that converts the audio received by the reception unit into text, A text conversion unit organizes the content converted into text as a medical record, The management department manages the users' medication schedules, A reminder unit provides reminders based on the schedule managed by the aforementioned management unit, A dialogue unit that interacts with the user, The system includes a confirmation unit that checks the user's health status based on the information obtained by the aforementioned dialogue unit. A system characterized by the following features.

2. The aforementioned reception unit is The conversation during the consultation is transcribed into text in real time. The system according to feature 1.

3. The text conversion unit, Automatically create medical records based on the transcribed text. The system according to feature 1.

4. The aforementioned management department, Understand the user's medication schedule and provide reminders at the appropriate time. The system according to feature 1.

5. The reminder unit is, Explain the risks of drug interactions and side effects, and issue a warning. The system according to feature 1.

6. The aforementioned dialogue unit, Checking users' daily health and mood, and increasing opportunities for communication. The system according to feature 1.

7. The aforementioned verification unit is We provide medical consultation support based on the user's health status. The system according to feature 1.

8. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system according to feature 1.

Images