system

Abstract

The system according to this embodiment aims to automate the task of recording patient medication records and reduce the burden on pharmacists. [Solution] The system according to the embodiment comprises a recording unit, an analysis unit, a generation unit, an approval unit, and a recording unit. The recording unit records the conversation between the pharmacist and the patient. The analysis unit analyzes the data recorded by the recording unit and transcribes and summarizes the content of the conversation. The generation unit generates objective data, an assessment, and a plan based on the chief complaint generated by the analysis unit. The approval unit allows the pharmacist to confirm, approve, or revise the content generated by the generation unit. The recording unit records the medication history approved or revised by the approval unit.

Description

Technical Field

[0006] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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] In the conventional technology, the writing of medical histories becomes a burden on pharmacists, and there is a risk that the quality of the writing will decline.

[0005] The system according to the embodiment aims to automate the task of writing medical histories and reduce the burden on pharmacists.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a recording unit, an analysis unit, a generation unit, an approval unit, and a recording unit. The recording unit records the conversation between the pharmacist and the patient. The analysis unit analyzes the data recorded by the recording unit, transcribes the conversation content, and summarizes it. The generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit. The approval unit allows the pharmacist to review, approve, or revise the content generated by the generation unit. The recording unit records the medication history approved or revised by the approval unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate the task of recording patient medication history, thereby reducing the burden on pharmacists. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The automated medication history recording system according to an embodiment of the present invention is a system that utilizes generating AI to streamline medication history recording work in pharmacies and reduce the burden on pharmacists. This system records conversations between pharmacists and patients, and the generating AI analyzes the recorded data to transcribe and summarize it. Based on the chief complaint, it automatically generates objective data, assessments, and plans, which are then proposed to the pharmacist. The pharmacist reviews the proposed content, approves or modifies it, and finally records the medication history. For example, the automated medication history recording system installs a recording device to record conversations between pharmacists and patients. This recorded data is saved as data that can be later analyzed by the generating AI. Next, the generating AI automatically analyzes the recorded data, transcribes the conversation content, summarizes it, and compiles it into a chief complaint. This eliminates the need for pharmacists to manually transcribe. Subsequently, the generating AI automatically generates items for objective data, assessments, and plans based on the chief complaint, and proposes them to the pharmacist. The generating AI considers past medication history data and medical history and medication history linked to My Number (Japanese social security number) to make more accurate proposals. The pharmacist reviews the proposed content, approves it if there are no problems, and corrects any omissions or discrepancies. Finally, the completed medication history is recorded in the system to help with the patient's next visit. This system streamlines medication history documentation and reduces the burden on pharmacists. It also reduces the risk of errors and omissions, and improves the quality of medical care by accumulating more accurate medical data. In this way, the automated medication history documentation system can streamline medication history documentation and reduce the burden on pharmacists.

[0029] The automated medication history recording system according to this embodiment comprises a recording unit, an analysis unit, a generation unit, an approval unit, and a recording unit. The recording unit records the conversation between the pharmacist and the patient. The recording unit can, for example, record the conversation between the pharmacist and the patient as high-quality audio data. The recording unit can also automatically detect the start timing of the conversation and start recording. Furthermore, the recording unit can detect the end timing of the conversation and stop recording. The analysis unit analyzes the data recorded by the recording unit and transcribes and summarizes the content of the conversation. The analysis unit can, for example, automatically analyze the recorded data using a generation AI and transcribe the content of the conversation. Furthermore, the analysis unit can also summarize the content of the conversation using a generation AI and compile it into a chief complaint. Furthermore, the analysis unit can also highlight important parts of the conversation content during transcription. The generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit. The generation unit can, for example, generate objective data based on the chief complaint using a generation AI. Furthermore, the generation unit can also generate assessments using a generation AI. Furthermore, the generation unit can generate plans using generation AI. The approval unit allows pharmacists to review, approve, or modify the content generated by the generation unit. For example, the approval unit can approve the generated content after the pharmacist has reviewed it and found no problems. The approval unit can also allow pharmacists to correct any omissions or inconsistencies in the generated content. The recording unit records the medication history approved or modified by the approval unit. For example, the recording unit can record the approved or modified medication history in the system. The recording unit can also use the recorded medication history to help with future patient care. As a result, the automated medication history recording system according to this embodiment can improve the efficiency of medication history recording and reduce the burden on pharmacists.

[0030] The recording unit records conversations between pharmacists and patients. For example, it can record conversations between pharmacists and patients as high-quality audio data. Specifically, it uses noise cancellation technology to remove ambient noise and obtain clear audio data. The recording unit can also automatically detect the start of a conversation and begin recording. For example, it can use speech recognition technology to trigger recording with specific phrases such as "Hello" or "Let's talk about your medication." Furthermore, the recording unit can detect the end of a conversation and stop recording. This can be done by detecting when the conversation does not continue for a certain period of time or by detecting an ending phrase such as "Thank you." By combining these functions, the recording unit can record all conversations between pharmacists and patients without omission, providing high-quality data to the subsequent analysis unit. Additionally, the recording unit can upload the recorded data to a cloud server in real time, allowing the analysis unit to access it immediately. This allows the recording unit to efficiently and accurately record the entire conversation process, improving the overall system performance.

[0031] The analysis unit analyzes the data recorded by the recording unit, transcribing and summarizing the dialogue. For example, the analysis unit can automatically analyze the recorded data and transcribe the dialogue using generative AI. Specifically, it converts the audio data into text data using speech recognition technology and analyzes the grammar and context using natural language processing technology. The analysis unit can also summarize the dialogue using generative AI, condensing it into a main complaint. For example, it extracts and concisely summarizes important information such as the patient's symptoms, the effects of medication, and side effects. Furthermore, the analysis unit can highlight important parts of the dialogue during transcription. This can be done by using keyword extraction technology to highlight important words and phrases such as "pain," "rash," and "dizziness." By combining these functions, the analysis unit can quickly and accurately analyze the dialogue and provide the necessary information to the subsequent generation unit. Additionally, the analysis unit can refer to past dialogue data and medication history data and compare it with the current dialogue to detect abnormal patterns and new problems early. This allows the analysis unit to efficiently analyze dialogue content, improving the overall reliability and accuracy of the system.

[0032] The generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit. For example, the generation unit can generate objective data based on the chief complaint using generation AI. Specifically, it estimates objective data such as blood pressure, body temperature, and pulse rate based on information such as the patient's symptoms, drug effects, and side effects. The generation unit can also generate assessments using generation AI. For example, it evaluates the patient's current health status and drug effects based on the patient's symptoms and past medication history data, and proposes necessary countermeasures. Furthermore, the generation unit can generate plans using generation AI. This includes medication schedules, suggestions for lifestyle improvements, and appointments for the next consultation. By combining these functions, the generation unit can comprehensively support patient health management and streamline the work of pharmacists. In addition, the generation unit provides the generated data and plans in a format that pharmacists can easily review, facilitating the review process in the approval unit. As a result, the generation unit can quickly and accurately generate the information necessary for patient health management, improving the overall efficiency and accuracy of the system.

[0033] The approval unit allows pharmacists to review, approve, or modify the content generated by the generation unit. For example, the approval unit can allow pharmacists to review the generated content and approve it if there are no problems. Specifically, it displays the generated objective data, assessments, and plans on the screen for the pharmacist to review each one. The approval unit also allows pharmacists to correct any deficiencies or inconsistencies in the generated content. For example, if there is an error in the generated plan, the pharmacist can manually correct it and input the correct information. By combining these functions, the approval unit can ensure the accuracy and reliability of the generated content and support the pharmacist's final review. Furthermore, the approval unit can record the content approved or modified by the pharmacist and use it to improve future patient care. This allows the approval unit to efficiently review and modify the generated content, improving the reliability and accuracy of the entire system.

[0034] The Records Unit records medication histories approved or modified by the Approval Unit. For example, the Records Unit can record approved or modified medication histories in the system. Specifically, it can automatically save data to the electronic medical record system or medication history management system, allowing for quick access when needed. The Records Unit can also utilize the recorded medication histories to improve future patient care. For instance, it can refer to past medication history data to assess the patient's current condition and the effectiveness of medications. Furthermore, the Records Unit can analyze the recorded data to improve pharmacist operations and patient health management. This includes analyzing trends in drug effects and side effects to suggest more effective treatments. By combining these functions, the Records Unit can efficiently record and manage medication histories, improving the overall reliability and accuracy of the system. Additionally, the Records Unit implements measures to ensure data security and privacy, safely protecting patients' personal information. This allows the Records Unit to efficiently and securely record and manage medication histories, improving the overall system performance.

[0035] The recording unit can record conversations between pharmacists and patients. For example, the recording unit can record conversations between pharmacists and patients as high-quality audio data. The recording unit can also automatically detect the start of a conversation and begin recording. Furthermore, the recording unit can detect the end of a conversation and stop recording. This ensures accurate recording of conversations between pharmacists and patients, facilitating subsequent analysis. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For instance, the recording unit can use AI to automatically detect the start of a conversation and begin recording.

[0036] The analysis unit can automatically analyze recorded data, transcribe the dialogue, and summarize it. For example, the analysis unit can use a generative AI to automatically analyze the recorded data and transcribe the dialogue. The analysis unit can also use the generative AI to summarize the dialogue and compile it into a main complaint. Furthermore, the analysis unit can highlight important parts of the dialogue during transcription. This reduces the workload for pharmacists by automatically transcribing and summarizing the dialogue. Some or all of the above-described processes in the analysis unit are performed using a generative AI. For example, the analysis unit can input recorded data into the generative AI and have the generative AI transcribe and summarize the dialogue.

[0037] The generation unit can generate objective data, assessments, and plans based on the chief complaint. For example, the generation unit can use a generation AI to generate objective data based on the chief complaint. The generation unit can also generate assessments using the generation AI. Furthermore, the generation unit can generate plans using the generation AI. This improves the quality of medication history by automatically generating data based on the chief complaint. Some or all of the above-mentioned processes in the generation unit are performed using the generation AI. For example, the generation unit can input the chief complaint into the generation AI and have the generation AI generate objective data, assessments, and plans.

[0038] The generation unit can make suggestions by considering past medication history data, medical visit history, and medication history. For example, the generation unit can use a generation AI to consider past medication history data, medical visit history, and medication history and make suggestions. This allows for more accurate suggestions by considering past data. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit can input past medication history data, medical visit history, and medication history into the generation AI and have the generation AI generate suggestions.

[0039] The approval department allows pharmacists to review, approve, or modify the generated content. For example, the approval department can approve the generated content if the pharmacist reviews it and finds no problems. The approval department can also allow pharmacists to correct any omissions or inconsistencies in the generated content. This ensures that a pharmacist-reviewed and accurate medication history is recorded. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department could use AI to automatically review the generated content and present it to the pharmacist.

[0040] The recording unit can record approved or revised medication histories. For example, the recording unit can record approved or revised medication histories in the system. The recording unit can also use the recorded medication histories to help with future patient care. This means that by accurately recording approved or revised medication histories, it can be used to help with future patient care. Some or all of the above processes in the recording unit may be performed using AI or not. For example, the recording unit may have AI automatically record approved or revised medication histories and save them in the system.

[0041] The recording unit may have a function to automatically highlight important parts of a conversation during recording. For example, when important keywords appear during a conversation, the recording unit can highlight and record those parts. The recording unit can also automatically highlight and record parts related to the patient's chief complaint or symptoms. Furthermore, the recording unit can highlight and record parts containing advice or instructions from a pharmacist. This makes subsequent analysis easier by highlighting important parts during recording. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit may use AI to automatically detect and highlight important parts of a conversation during recording.

[0042] The recording unit can analyze the recorded data in real time and automatically tag important keywords. For example, the recording unit can tag drug names and symptoms that appear during the conversation in real time. It can also tag keywords related to the patient's chief complaint and symptoms in real time. Furthermore, the recording unit can tag keywords related to the pharmacist's advice and instructions in real time. This real-time keyword tagging makes subsequent searching and analysis easier. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can have AI analyze the recorded data in real time and automatically tag important keywords.

[0043] The recording unit can automatically filter out background noise from the patient during recording, ensuring a clear recording of the conversation. For example, the recording unit can automatically filter out ambient noise generated during recording. It can also separate the patient's voice from background noise, resulting in a clear recording of the conversation. Furthermore, the recording unit can automatically remove noise generated during recording. This allows for a clear recording of the conversation by filtering out background noise. Some or all of the above processing in the recording unit may be performed using AI, or without AI. For example, the recording unit can use AI to automatically filter out ambient noise generated during recording, resulting in a clear recording of the conversation.

[0044] The recording unit can automatically save the recorded data in multiple formats, making it easier to use for later analysis. For example, the recording unit can save the recorded data as both audio and text files. It can also save the recorded data in different compression formats, facilitating its use for analysis. Furthermore, the recording unit can save the recorded data in both cloud storage and local storage. This allows for easier later analysis by saving in multiple formats. Some or all of the above processing in the recording unit may be performed using AI, or not. For example, the recording unit can use AI to automatically save the recorded data in multiple formats, making it easier to use for later analysis.

[0045] The analysis unit can be equipped with a function to automatically correct typographical errors and grammatical errors by considering the context of the dialogue during analysis. For example, the analysis unit can analyze the context of the dialogue and automatically correct typographical errors. The analysis unit can also automatically complete appropriate words based on the content of the dialogue. Furthermore, the analysis unit can automatically correct grammatical errors by considering the flow of the dialogue. This enables accurate transcription by automatically correcting typographical errors and grammatical errors. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the generation AI can automatically analyze the context of the dialogue and correct typographical errors.

[0046] The analysis unit can adjust the level of detail in the summary by considering the tone and speed of the dialogue during analysis. For example, if the tone of the dialogue is calm, the analysis unit can generate a detailed summary. If the dialogue is fast, the analysis unit can generate a concise summary. Furthermore, if the tone of the dialogue is tense, the analysis unit can generate a summary that emphasizes important information. In this way, an appropriate summary is generated by adjusting the level of detail in the summary according to the tone and speed of the dialogue. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the generation AI can automatically analyze the tone and speed of the dialogue and adjust the level of detail in the summary.

[0047] The analysis unit can improve the accuracy of the summary by referring to background information of the dialogue during analysis. For example, the analysis unit can improve the accuracy of the summary by referring to background information of the dialogue. The analysis unit can also generate an appropriate summary by considering the context of the dialogue. Furthermore, the analysis unit can generate a summary that highlights important information based on the content of the dialogue. This improves the accuracy of the summary by referring to background information. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the generation AI can automatically refer to background information of the dialogue in the analysis unit to improve the accuracy of the summary.

[0048] The analysis unit can determine the priority of summaries based on the importance of the dialogue during analysis. For example, the analysis unit can determine the priority of summaries based on the importance of the dialogue. The analysis unit can also prioritize summarizing important information. Furthermore, the analysis unit can adjust the priority of summaries based on the content of the dialogue. This enables efficient information management by prioritizing the summarization of important information. Some or all of the above processing in the analysis unit is performed using generative AI. For example, the generative AI can automatically evaluate the importance of the dialogue and determine the priority of summaries.

[0049] The generation unit can improve the accuracy of the generated data by referring to past medication history data during generation. For example, the generation unit can improve the accuracy of the generated data by referring to past medication history data. The generation unit can also generate appropriate data by considering past medical visit history. Furthermore, the generation unit can generate highly accurate data based on past medication history. In this way, the accuracy of the generated data is improved by referring to past data. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can improve the accuracy of the generated data by having the generation AI automatically refer to past medication history data.

[0050] The generation unit can customize assessments and plans by considering the patient's lifestyle and environmental information during the generation process. For example, the generation unit can generate appropriate assessments and plans by considering the patient's lifestyle. Furthermore, the generation unit can generate customized assessments and plans based on the patient's environmental information. In addition, the generation unit can generate optimal assessments and plans by comprehensively considering the patient's lifestyle and environmental information. This results in the generation of more appropriate assessments and plans by considering the patient's lifestyle and environmental information. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can automatically reference the patient's lifestyle and environmental information using the generation AI to customize assessments and plans.

[0051] The generation unit can propose optimal assessments and plans by considering the patient's geographical location information during generation. For example, the generation unit can propose appropriate assessments and plans based on the patient's geographical location information. Furthermore, the generation unit can propose optimal assessments and plans by considering the medical resources in the patient's area of ​​residence. In addition, the generation unit can propose optimal assessments and plans by comprehensively considering the patient's geographical location information and medical resources. This allows for the proposal of more appropriate assessments and plans by considering geographical location information. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can automatically reference the patient's geographical location information using generation AI to propose optimal assessments and plans.

[0052] The generation unit can analyze the patient's social media activity during generation and adjust the generated content accordingly. For example, the generation unit can analyze the patient's social media activity and generate appropriate data. It can also adjust the generated content based on the patient's health-related posts on social media. Furthermore, the generation unit can comprehensively consider the patient's social media activity and health status to generate optimal data. This allows for the generation of more appropriate data by analyzing social media activity. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can automatically analyze the patient's social media activity using generation AI and adjust the generated content accordingly.

[0053] The approval unit can propose the optimal approval method by referring to past approval history during the approval process. For example, the approval unit can refer to past approval history and propose the optimal approval method. Furthermore, the approval unit can propose appropriate approval procedures based on past approval history. In addition, the approval unit can propose the optimal approval method by comprehensively considering past approval history and the current situation. Thus, the optimal approval method is proposed by referring to past approval history. Some or all of the above processes in the approval unit may be performed using AI, or not. For example, the approval unit can have AI automatically refer to past approval history and propose the optimal approval method.

[0054] The approval unit may have a function to automatically evaluate the reliability of the data generated during the approval process. For example, the approval unit can evaluate the reliability of the generated data by comparing it with past data. Furthermore, the approval unit may have AI automatically evaluate the reliability of the generated data and present it to the pharmacist. In addition, the approval unit may set criteria for evaluating the reliability of the generated data and evaluate it based on those criteria. This enables accurate approval by automatically evaluating the reliability of the data. Some or all of the above processes in the approval unit may be performed using AI or not. For example, the approval unit may have AI automatically evaluate the reliability of the generated data and present it to the pharmacist.

[0055] The approval department can adjust the approval content by referring to the pharmacist's past revision history at the time of approval. For example, the approval department can refer to the pharmacist's past revision history and adjust the approval content. The approval department can also propose an appropriate approval procedure based on the past revision history. Furthermore, the approval department can adjust the approval content by comprehensively considering the past revision history and the current situation. In this way, appropriate approval content is adjusted by referring to the past revision history. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department can use AI to automatically refer to the pharmacist's past revision history and adjust the approval content.

[0056] The approval department can customize the approval process based on the pharmacist's area of ​​expertise at the time of approval. For example, the approval department can customize the approval process based on the pharmacist's area of ​​expertise. The approval department can also propose approval procedures tailored to the area of ​​expertise. Furthermore, the approval department can customize the approval process by comprehensively considering the area of ​​expertise and the current situation. This allows for efficient approval by customizing the approval process based on the area of ​​expertise. Some or all of the above processes in the approval department may be performed using AI, or not. For example, the approval department can use AI to automatically refer to the pharmacist's area of ​​expertise and customize the approval process.

[0057] The recording unit can propose an optimal recording format by referring to past recording data during recording. For example, the recording unit can refer to past recording data and propose an optimal recording format. Furthermore, the recording unit can provide an appropriate recording format based on past recording data. In addition, the recording unit can propose an optimal recording format by comprehensively considering past recording data and the current situation. Thus, by referring to past recording data, an optimal recording format is proposed. Some or all of the above processing in the recording unit may be performed using AI, or without AI. For example, the recording unit can have AI automatically refer to past recording data and propose an optimal recording format.

[0058] The recording unit can be equipped with a function to automatically check the consistency of data during recording. For example, the recording unit can check the consistency of recorded data by comparing it with past data. Furthermore, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist. In addition, the recording unit can set criteria for checking the consistency of recorded data and perform checks based on those criteria. This enables accurate recording by automatically checking data consistency. Some or all of the above processes in the recording unit may be performed using AI or not. For example, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist.

[0059] The recording unit can adjust the recording content by referring to the pharmacist's past recording history at the time of recording. For example, the recording unit can refer to the pharmacist's past recording history and adjust the recording content. The recording unit can also suggest appropriate recording procedures based on past recording history. Furthermore, the recording unit can adjust the recording content by comprehensively considering past recording history and the current situation. In this way, appropriate recording content is adjusted by referring to past recording history. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can use AI to automatically refer to the pharmacist's past recording history and adjust the recording content.

[0060] The recording unit can customize the recording format based on the pharmacist's area of ​​expertise at the time of recording. For example, the recording unit can customize the recording format based on the pharmacist's area of ​​expertise. The recording unit can also suggest recording procedures appropriate to the area of ​​expertise. Furthermore, the recording unit can customize the recording format by comprehensively considering the area of ​​expertise and the current situation. This allows for efficient recording by customizing the recording format based on the area of ​​expertise. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can use AI to automatically refer to the pharmacist's area of ​​expertise and customize the recording format.

[0061] The recording unit can be equipped with a function to automatically check the consistency of data during recording. For example, the recording unit can check the consistency of recorded data by comparing it with past data. Furthermore, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist. In addition, the recording unit can set criteria for checking the consistency of recorded data and perform checks based on those criteria. This enables accurate recording by automatically checking data consistency. Some or all of the above processes in the recording unit may be performed using AI or not. For example, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The automated medication history recording system can also include a lifestyle analysis unit that takes into account the patient's lifestyle. This unit can collect data such as the patient's diet, exercise, and sleep, and use this data to customize medication history assessments and plans. For example, if a patient has hypertension, the lifestyle analysis unit can consider their salt intake and suggest appropriate medications. It can also generate plans that include advice to encourage exercise for patients who are sedentary. Furthermore, based on sleep data, it can suggest appropriate medications and lifestyle improvements for sleep disorders. This allows for the creation of more personalized medication histories based on the patient's lifestyle, which is expected to improve treatment effectiveness.

[0064] The automated medication history recording system can also be equipped with a geographic information analysis unit that takes into account the patient's geographic location. This unit can, for example, propose appropriate medication history assessments and plans based on information about medical resources and the environment in the patient's area. For instance, if a patient lives in an area with limited medical resources, it can suggest the use of telemedicine. If a patient lives in an urban area, it can provide information about nearby medical institutions and pharmacies. Furthermore, it can offer suggestions for lifestyle improvements tailored to the patient's living environment. This results in the creation of more appropriate medication histories that consider geographical factors, improving patient convenience.

[0065] The automated medication history recording system can also include a social media analysis unit that analyzes patients' social media activity. This unit can, for example, analyze health-related posts on a patient's social media and reflect the findings in medication history assessments and plans. For instance, if a patient frequently posts about a specific symptom on social media, the system can record appropriate responses to that symptom in the medication history. Furthermore, if a patient actively shares health-related information, the system can use that information to suggest lifestyle improvements. Additionally, the system can consider the patient's psychological state as revealed by their social media activity to ensure appropriate medication history entries. This results in the creation of more personalized medication histories that leverage the patient's social media activity.

[0066] The automated medication history recording system can also include a living environment analysis unit that considers the patient's lifestyle and environmental information. For example, the living environment analysis unit can collect data on the patient's living environment and lifestyle, and customize medication history assessments and plans based on this data. For instance, if the patient is elderly, it can suggest appropriate medications tailored to their living environment. If the patient is sedentary, it can generate a plan that includes advice to promote exercise. Furthermore, it can consider the patient's dietary habits and propose a plan that includes dietary advice. This allows for the creation of more personalized medication histories based on the patient's living environment, which is expected to improve treatment effectiveness.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The recording unit records the conversation between the pharmacist and the patient. The recording unit can, for example, record the conversation between the pharmacist and the patient as high-quality audio data. The recording unit can also automatically detect when the conversation begins and start recording. Furthermore, the recording unit can detect when the conversation ends and stop recording. Step 2: The analysis unit analyzes the data recorded by the recording unit, transcribes and summarizes the dialogue. The analysis unit can, for example, automatically analyze the recorded data using generative AI and transcribe the dialogue. The analysis unit can also summarize the dialogue using generative AI and compile it into a main complaint. Furthermore, the analysis unit can highlight important parts of the dialogue during transcription. Step 3: The generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit. For example, the generation unit can generate objective data based on the chief complaint using generation AI. The generation unit can also generate assessments using generation AI. Furthermore, the generation unit can also generate plans using generation AI. Step 4: The approval department allows the pharmacist to review and approve or revise the content generated by the generation department. For example, the approval department can approve the generated content after the pharmacist has reviewed it and found no problems. The approval department can also allow the pharmacist to revise the generated content if there are any omissions or inconsistencies. Step 5: The Records Unit records the medication history approved or modified by the Approval Unit. For example, the Records Unit can record approved or modified medication history in the system. The Records Unit can also use the recorded medication history to help with future patient care.

[0069] (Example of form 2) The automated medication history recording system according to an embodiment of the present invention is a system that utilizes generating AI to streamline medication history recording work in pharmacies and reduce the burden on pharmacists. This system records conversations between pharmacists and patients, and the generating AI analyzes the recorded data to transcribe and summarize it. Based on the chief complaint, it automatically generates objective data, assessments, and plans, which are then proposed to the pharmacist. The pharmacist reviews the proposed content, approves or modifies it, and finally records the medication history. For example, the automated medication history recording system installs a recording device to record conversations between pharmacists and patients. This recorded data is saved as data that can be later analyzed by the generating AI. Next, the generating AI automatically analyzes the recorded data, transcribes the conversation content, summarizes it, and compiles it into a chief complaint. This eliminates the need for pharmacists to manually transcribe. Subsequently, the generating AI automatically generates items for objective data, assessments, and plans based on the chief complaint, and proposes them to the pharmacist. The generating AI considers past medication history data and medical history and medication history linked to My Number (Japanese social security number) to make more accurate proposals. The pharmacist reviews the proposed content, approves it if there are no problems, and corrects any omissions or discrepancies. Finally, the completed medication history is recorded in the system to help with the patient's next visit. This system streamlines medication history documentation and reduces the burden on pharmacists. It also reduces the risk of errors and omissions, and improves the quality of medical care by accumulating more accurate medical data. In this way, the automated medication history documentation system can streamline medication history documentation and reduce the burden on pharmacists.

[0070] The automated medication history recording system according to this embodiment comprises a recording unit, an analysis unit, a generation unit, an approval unit, and a recording unit. The recording unit records the conversation between the pharmacist and the patient. The recording unit can, for example, record the conversation between the pharmacist and the patient as high-quality audio data. The recording unit can also automatically detect the start timing of the conversation and start recording. Furthermore, the recording unit can detect the end timing of the conversation and stop recording. The analysis unit analyzes the data recorded by the recording unit and transcribes and summarizes the content of the conversation. The analysis unit can, for example, automatically analyze the recorded data using a generation AI and transcribe the content of the conversation. Furthermore, the analysis unit can also summarize the content of the conversation using a generation AI and compile it into a chief complaint. Furthermore, the analysis unit can also highlight important parts of the conversation content during transcription. The generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit. The generation unit can, for example, generate objective data based on the chief complaint using a generation AI. Furthermore, the generation unit can also generate assessments using a generation AI. Furthermore, the generation unit can generate plans using generation AI. The approval unit allows pharmacists to review, approve, or modify the content generated by the generation unit. For example, the approval unit can approve the generated content after the pharmacist has reviewed it and found no problems. The approval unit can also allow pharmacists to correct any omissions or inconsistencies in the generated content. The recording unit records the medication history approved or modified by the approval unit. For example, the recording unit can record the approved or modified medication history in the system. The recording unit can also use the recorded medication history to help with future patient care. As a result, the automated medication history recording system according to this embodiment can improve the efficiency of medication history recording and reduce the burden on pharmacists.

[0071] The recording unit records conversations between pharmacists and patients. For example, it can record conversations between pharmacists and patients as high-quality audio data. Specifically, it uses noise cancellation technology to remove ambient noise and obtain clear audio data. The recording unit can also automatically detect the start of a conversation and begin recording. For example, it can use speech recognition technology to trigger recording with specific phrases such as "Hello" or "Let's talk about your medication." Furthermore, the recording unit can detect the end of a conversation and stop recording. This can be done by detecting when the conversation does not continue for a certain period of time or by detecting an ending phrase such as "Thank you." By combining these functions, the recording unit can record all conversations between pharmacists and patients without omission, providing high-quality data to the subsequent analysis unit. Additionally, the recording unit can upload the recorded data to a cloud server in real time, allowing the analysis unit to access it immediately. This allows the recording unit to efficiently and accurately record the entire conversation process, improving the overall system performance.

[0072] The analysis unit analyzes the data recorded by the recording unit, transcribing and summarizing the dialogue. For example, the analysis unit can automatically analyze the recorded data and transcribe the dialogue using generative AI. Specifically, it converts the audio data into text data using speech recognition technology and analyzes the grammar and context using natural language processing technology. The analysis unit can also summarize the dialogue using generative AI, condensing it into a main complaint. For example, it extracts and concisely summarizes important information such as the patient's symptoms, the effects of medication, and side effects. Furthermore, the analysis unit can highlight important parts of the dialogue during transcription. This can be done by using keyword extraction technology to highlight important words and phrases such as "pain," "rash," and "dizziness." By combining these functions, the analysis unit can quickly and accurately analyze the dialogue and provide the necessary information to the subsequent generation unit. Additionally, the analysis unit can refer to past dialogue data and medication history data and compare it with the current dialogue to detect abnormal patterns and new problems early. This allows the analysis unit to efficiently analyze dialogue content, improving the overall reliability and accuracy of the system.

[0073] The generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit. For example, the generation unit can generate objective data based on the chief complaint using generation AI. Specifically, it estimates objective data such as blood pressure, body temperature, and pulse rate based on information such as the patient's symptoms, drug effects, and side effects. The generation unit can also generate assessments using generation AI. For example, it evaluates the patient's current health status and drug effects based on the patient's symptoms and past medication history data, and proposes necessary countermeasures. Furthermore, the generation unit can generate plans using generation AI. This includes medication schedules, suggestions for lifestyle improvements, and appointments for the next consultation. By combining these functions, the generation unit can comprehensively support patient health management and streamline the work of pharmacists. In addition, the generation unit provides the generated data and plans in a format that pharmacists can easily review, facilitating the review process in the approval unit. As a result, the generation unit can quickly and accurately generate the information necessary for patient health management, improving the overall efficiency and accuracy of the system.

[0074] The approval unit allows pharmacists to review, approve, or modify the content generated by the generation unit. For example, the approval unit can allow pharmacists to review the generated content and approve it if there are no problems. Specifically, it displays the generated objective data, assessments, and plans on the screen for the pharmacist to review each one. The approval unit also allows pharmacists to correct any deficiencies or inconsistencies in the generated content. For example, if there is an error in the generated plan, the pharmacist can manually correct it and input the correct information. By combining these functions, the approval unit can ensure the accuracy and reliability of the generated content and support the pharmacist's final review. Furthermore, the approval unit can record the content approved or modified by the pharmacist and use it to improve future patient care. This allows the approval unit to efficiently review and modify the generated content, improving the reliability and accuracy of the entire system.

[0075] The Records Unit records medication histories approved or modified by the Approval Unit. For example, the Records Unit can record approved or modified medication histories in the system. Specifically, it can automatically save data to the electronic medical record system or medication history management system, allowing for quick access when needed. The Records Unit can also utilize the recorded medication histories to improve future patient care. For instance, it can refer to past medication history data to assess the patient's current condition and the effectiveness of medications. Furthermore, the Records Unit can analyze the recorded data to improve pharmacist operations and patient health management. This includes analyzing trends in drug effects and side effects to suggest more effective treatments. By combining these functions, the Records Unit can efficiently record and manage medication histories, improving the overall reliability and accuracy of the system. Additionally, the Records Unit implements measures to ensure data security and privacy, safely protecting patients' personal information. This allows the Records Unit to efficiently and securely record and manage medication histories, improving the overall system performance.

[0076] The recording unit can record conversations between pharmacists and patients. For example, the recording unit can record conversations between pharmacists and patients as high-quality audio data. The recording unit can also automatically detect the start of a conversation and begin recording. Furthermore, the recording unit can detect the end of a conversation and stop recording. This ensures accurate recording of conversations between pharmacists and patients, facilitating subsequent analysis. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For instance, the recording unit can use AI to automatically detect the start of a conversation and begin recording.

[0077] The analysis unit can automatically analyze recorded data, transcribe the dialogue, and summarize it. For example, the analysis unit can use a generative AI to automatically analyze the recorded data and transcribe the dialogue. The analysis unit can also use the generative AI to summarize the dialogue and compile it into a main complaint. Furthermore, the analysis unit can highlight important parts of the dialogue during transcription. This reduces the workload for pharmacists by automatically transcribing and summarizing the dialogue. Some or all of the above-described processes in the analysis unit are performed using a generative AI. For example, the analysis unit can input recorded data into the generative AI and have the generative AI transcribe and summarize the dialogue.

[0078] The generation unit can generate objective data, assessments, and plans based on the chief complaint. For example, the generation unit can use a generation AI to generate objective data based on the chief complaint. The generation unit can also generate assessments using the generation AI. Furthermore, the generation unit can generate plans using the generation AI. This improves the quality of medication history by automatically generating data based on the chief complaint. Some or all of the above-mentioned processes in the generation unit are performed using the generation AI. For example, the generation unit can input the chief complaint into the generation AI and have the generation AI generate objective data, assessments, and plans.

[0079] The generation unit can make suggestions by considering past medication history data, medical visit history, and medication history. For example, the generation unit can use a generation AI to consider past medication history data, medical visit history, and medication history and make suggestions. This allows for more accurate suggestions by considering past data. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit can input past medication history data, medical visit history, and medication history into the generation AI and have the generation AI generate suggestions.

[0080] The approval department allows pharmacists to review, approve, or modify the generated content. For example, the approval department can approve the generated content if the pharmacist reviews it and finds no problems. The approval department can also allow pharmacists to correct any omissions or inconsistencies in the generated content. This ensures that a pharmacist-reviewed and accurate medication history is recorded. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department could use AI to automatically review the generated content and present it to the pharmacist.

[0081] The recording unit can record approved or revised medication histories. For example, the recording unit can record approved or revised medication histories in the system. The recording unit can also use the recorded medication histories to help with future patient care. This means that by accurately recording approved or revised medication histories, it can be used to help with future patient care. Some or all of the above processes in the recording unit may be performed using AI or not. For example, the recording unit may have AI automatically record approved or revised medication histories and save them in the system.

[0082] The recording unit can estimate the patient's emotions and adjust the recording start time based on the estimated emotions. For example, if the patient is nervous, the recording unit can allow time for relaxation before the conversation begins before starting recording. If the patient is relaxed, the recording unit can start recording from the beginning of the conversation to record a natural conversation. Furthermore, if the patient is in a hurry, the recording unit can start recording at a time when important information is being spoken. In this way, a natural conversation can be recorded by adjusting the recording start time according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI 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 recording unit may be performed using AI or not. For example, the recording unit can have AI automatically estimate the patient's emotions and adjust the recording start time accordingly.

[0083] The recording unit may have a function to automatically highlight important parts of a conversation during recording. For example, when important keywords appear during a conversation, the recording unit can highlight and record those parts. The recording unit can also automatically highlight and record parts related to the patient's chief complaint or symptoms. Furthermore, the recording unit can highlight and record parts containing advice or instructions from a pharmacist. This makes subsequent analysis easier by highlighting important parts during recording. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit may use AI to automatically detect and highlight important parts of a conversation during recording.

[0084] The recording unit can analyze the recorded data in real time and automatically tag important keywords. For example, the recording unit can tag drug names and symptoms that appear during the conversation in real time. It can also tag keywords related to the patient's chief complaint and symptoms in real time. Furthermore, the recording unit can tag keywords related to the pharmacist's advice and instructions in real time. This real-time keyword tagging makes subsequent searching and analysis easier. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can have AI analyze the recorded data in real time and automatically tag important keywords.

[0085] The recording unit can estimate the patient's emotions and adjust the retention period of the recording data based on the estimated emotions. For example, if the patient is nervous, the recording unit can set a shorter retention period for the recording data. Conversely, if the patient is relaxed, the recording unit can set a longer retention period for the recording data. Furthermore, if the patient is in a hurry, the recording unit can save only the important parts for a longer period. This ensures that important data is properly saved by adjusting the retention period according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can have AI automatically estimate the patient's emotions and adjust the retention period of the recording data.

[0086] The recording unit can automatically filter out background noise from the patient during recording, ensuring a clear recording of the conversation. For example, the recording unit can automatically filter out ambient noise generated during recording. It can also separate the patient's voice from background noise, resulting in a clear recording of the conversation. Furthermore, the recording unit can automatically remove noise generated during recording. This allows for a clear recording of the conversation by filtering out background noise. Some or all of the above processing in the recording unit may be performed using AI, or without AI. For example, the recording unit can use AI to automatically filter out ambient noise generated during recording, resulting in a clear recording of the conversation.

[0087] The recording unit can automatically save the recorded data in multiple formats, making it easier to use for later analysis. For example, the recording unit can save the recorded data as both audio and text files. It can also save the recorded data in different compression formats, facilitating its use for analysis. Furthermore, the recording unit can save the recorded data in both cloud storage and local storage. This allows for easier later analysis by saving in multiple formats. Some or all of the above processing in the recording unit may be performed using AI, or not. For example, the recording unit can use AI to automatically save the recorded data in multiple formats, making it easier to use for later analysis.

[0088] The analysis unit can estimate the patient's emotions and adjust the transcription accuracy based on the estimated emotions. For example, if the patient is nervous, the analysis unit can increase the transcription accuracy to accurately record important information. Conversely, if the patient is relaxed, the analysis unit can set the transcription accuracy to normal. Furthermore, if the patient is in a hurry, the analysis unit can transcribe only the important parts with high accuracy. This allows for accurate recording of important information by adjusting the transcription accuracy according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit are performed using generative AI. For example, the analysis unit can use generative AI to automatically estimate the patient's emotions and adjust the transcription accuracy.

[0089] The analysis unit can be equipped with a function to automatically correct typographical errors and grammatical errors by considering the context of the dialogue during analysis. For example, the analysis unit can analyze the context of the dialogue and automatically correct typographical errors. The analysis unit can also automatically complete appropriate words based on the content of the dialogue. Furthermore, the analysis unit can automatically correct grammatical errors by considering the flow of the dialogue. This enables accurate transcription by automatically correcting typographical errors and grammatical errors. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the generation AI can automatically analyze the context of the dialogue and correct typographical errors.

[0090] The analysis unit can adjust the level of detail in the summary by considering the tone and speed of the dialogue during analysis. For example, if the tone of the dialogue is calm, the analysis unit can generate a detailed summary. If the dialogue is fast, the analysis unit can generate a concise summary. Furthermore, if the tone of the dialogue is tense, the analysis unit can generate a summary that emphasizes important information. In this way, an appropriate summary is generated by adjusting the level of detail in the summary according to the tone and speed of the dialogue. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the generation AI can automatically analyze the tone and speed of the dialogue and adjust the level of detail in the summary.

[0091] The analysis unit can estimate the patient's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the patient is tense, the analysis unit can use a concise and clear presentation. If the patient is relaxed, the analysis unit can use a detailed and polite presentation. Furthermore, if the patient is in a hurry, the analysis unit can use a concise and to-the-point presentation. By adjusting the presentation of the summary according to the patient's emotions, a more appropriate summary is generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit is performed using generative AI. For example, the analysis unit can have the generative AI automatically estimate the patient's emotions and adjust the presentation of the summary.

[0092] The analysis unit can improve the accuracy of the summary by referring to background information of the dialogue during analysis. For example, the analysis unit can improve the accuracy of the summary by referring to background information of the dialogue. The analysis unit can also generate an appropriate summary by considering the context of the dialogue. Furthermore, the analysis unit can generate a summary that highlights important information based on the content of the dialogue. This improves the accuracy of the summary by referring to background information. Some or all of the above processing in the analysis unit is performed using a generation AI. For example, the generation AI can automatically refer to background information of the dialogue in the analysis unit to improve the accuracy of the summary.

[0093] The analysis unit can determine the priority of summaries based on the importance of the dialogue during analysis. For example, the analysis unit can determine the priority of summaries based on the importance of the dialogue. The analysis unit can also prioritize summarizing important information. Furthermore, the analysis unit can adjust the priority of summaries based on the content of the dialogue. This enables efficient information management by prioritizing the summarization of important information. Some or all of the above processing in the analysis unit is performed using generative AI. For example, the generative AI can automatically evaluate the importance of the dialogue and determine the priority of summaries.

[0094] The generation unit can estimate the patient's emotions and adjust the level of detail of the generated data based on the estimated emotions. For example, if the patient is tense, the generation unit can generate detailed data. If the patient is relaxed, the generation unit can generate data at a normal level of detail. Furthermore, if the patient is in a hurry, the generation unit can generate only the important parts in detail. This ensures that appropriate data is generated by adjusting the level of detail according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit is performed using the generative AI. For example, the generation unit can have the generative AI automatically estimate the patient's emotions and adjust the level of detail of the generated data.

[0095] The generation unit can improve the accuracy of the generated data by referring to past medication history data during generation. For example, the generation unit can improve the accuracy of the generated data by referring to past medication history data. The generation unit can also generate appropriate data by considering past medical visit history. Furthermore, the generation unit can generate highly accurate data based on past medication history. In this way, the accuracy of the generated data is improved by referring to past data. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can improve the accuracy of the generated data by having the generation AI automatically refer to past medication history data.

[0096] The generation unit can customize assessments and plans by considering the patient's lifestyle and environmental information during the generation process. For example, the generation unit can generate appropriate assessments and plans by considering the patient's lifestyle. Furthermore, the generation unit can generate customized assessments and plans based on the patient's environmental information. In addition, the generation unit can generate optimal assessments and plans by comprehensively considering the patient's lifestyle and environmental information. This results in the generation of more appropriate assessments and plans by considering the patient's lifestyle and environmental information. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can automatically reference the patient's lifestyle and environmental information using the generation AI to customize assessments and plans.

[0097] The generation unit can estimate the patient's emotions and determine the priority of the data to be generated based on the estimated emotions. For example, if the patient is anxious, the generation unit can prioritize generating important data. If the patient is relaxed, the generation unit can also generate data with normal priority. Furthermore, if the patient is in a hurry, the generation unit can prioritize generating only the important parts. In this way, by prioritizing data according to the patient's emotions, important data can be generated preferentially. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit can have the generation AI automatically estimate the patient's emotions and determine the priority of the data to be generated.

[0098] The generation unit can propose optimal assessments and plans by considering the patient's geographical location information during generation. For example, the generation unit can propose appropriate assessments and plans based on the patient's geographical location information. Furthermore, the generation unit can propose optimal assessments and plans by considering the medical resources in the patient's area of ​​residence. In addition, the generation unit can propose optimal assessments and plans by comprehensively considering the patient's geographical location information and medical resources. This allows for the proposal of more appropriate assessments and plans by considering geographical location information. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can automatically reference the patient's geographical location information using generation AI to propose optimal assessments and plans.

[0099] The generation unit can analyze the patient's social media activity during generation and adjust the generated content accordingly. For example, the generation unit can analyze the patient's social media activity and generate appropriate data. It can also adjust the generated content based on the patient's health-related posts on social media. Furthermore, the generation unit can comprehensively consider the patient's social media activity and health status to generate optimal data. This allows for the generation of more appropriate data by analyzing social media activity. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can automatically analyze the patient's social media activity using generation AI and adjust the generated content accordingly.

[0100] The approval unit can estimate the pharmacist's emotions and adjust the approval process based on the estimated emotions. For example, if the pharmacist is tired, the approval unit can simplify the approval process. Conversely, if the pharmacist is relaxed, the approval unit can perform the normal approval process. Furthermore, if the pharmacist is in a hurry, the approval unit can prioritize approving only the important parts. This allows for efficient approval by adjusting the approval process according to the pharmacist's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the approval unit may be performed using AI or not. For example, the approval unit can use AI to automatically estimate the pharmacist's emotions and adjust the approval process accordingly.

[0101] The approval unit can propose the optimal approval method by referring to past approval history during the approval process. For example, the approval unit can refer to past approval history and propose the optimal approval method. Furthermore, the approval unit can propose appropriate approval procedures based on past approval history. In addition, the approval unit can propose the optimal approval method by comprehensively considering past approval history and the current situation. Thus, the optimal approval method is proposed by referring to past approval history. Some or all of the above processes in the approval unit may be performed using AI, or not. For example, the approval unit can have AI automatically refer to past approval history and propose the optimal approval method.

[0102] The approval unit may have a function to automatically evaluate the reliability of the data generated during the approval process. For example, the approval unit can evaluate the reliability of the generated data by comparing it with past data. Furthermore, the approval unit may have AI automatically evaluate the reliability of the generated data and present it to the pharmacist. In addition, the approval unit may set criteria for evaluating the reliability of the generated data and evaluate it based on those criteria. This enables accurate approval by automatically evaluating the reliability of the data. Some or all of the above processes in the approval unit may be performed using AI or not. For example, the approval unit may have AI automatically evaluate the reliability of the generated data and present it to the pharmacist.

[0103] The approval unit can estimate the pharmacist's emotions and determine approval priorities based on those emotions. For example, if the pharmacist is tired, the approval unit can prioritize important approvals. If the pharmacist is relaxed, the approval unit can also approve approvals with normal priorities. Furthermore, if the pharmacist is in a hurry, the approval unit can prioritize approving only the important parts. This allows for prioritizing important approvals by determining approval priorities according to the pharmacist's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the approval unit may be performed using AI or not. For example, the approval unit can use AI to automatically estimate the pharmacist's emotions and determine approval priorities.

[0104] The approval department can adjust the approval content by referring to the pharmacist's past revision history at the time of approval. For example, the approval department can refer to the pharmacist's past revision history and adjust the approval content. The approval department can also propose an appropriate approval procedure based on the past revision history. Furthermore, the approval department can adjust the approval content by comprehensively considering the past revision history and the current situation. In this way, appropriate approval content is adjusted by referring to the past revision history. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department can use AI to automatically refer to the pharmacist's past revision history and adjust the approval content.

[0105] The approval department can customize the approval process based on the pharmacist's area of ​​expertise at the time of approval. For example, the approval department can customize the approval process based on the pharmacist's area of ​​expertise. The approval department can also propose approval procedures tailored to the area of ​​expertise. Furthermore, the approval department can customize the approval process by comprehensively considering the area of ​​expertise and the current situation. This allows for efficient approval by customizing the approval process based on the area of ​​expertise. Some or all of the above processes in the approval department may be performed using AI, or not. For example, the approval department can use AI to automatically refer to the pharmacist's area of ​​expertise and customize the approval process.

[0106] The recording unit can estimate the pharmacist's emotions and adjust the recording method based on the estimated emotions. For example, if the pharmacist is tired, the recording unit can provide a simplified recording method. If the pharmacist is relaxed, the recording unit can provide a standard recording method. Furthermore, if the pharmacist is in a hurry, the recording unit can prioritize saving only the important parts. This allows for efficient recording by adjusting the recording method according to the pharmacist's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 recording unit may be performed using AI or not. For example, the recording unit can have AI automatically estimate the pharmacist's emotions and adjust the recording method accordingly.

[0107] The recording unit can propose an optimal recording format by referring to past recording data during recording. For example, the recording unit can refer to past recording data and propose an optimal recording format. Furthermore, the recording unit can provide an appropriate recording format based on past recording data. In addition, the recording unit can propose an optimal recording format by comprehensively considering past recording data and the current situation. Thus, by referring to past recording data, an optimal recording format is proposed. Some or all of the above processing in the recording unit may be performed using AI, or without AI. For example, the recording unit can have AI automatically refer to past recording data and propose an optimal recording format.

[0108] The recording unit can be equipped with a function to automatically check the consistency of data during recording. For example, the recording unit can check the consistency of recorded data by comparing it with past data. Furthermore, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist. In addition, the recording unit can set criteria for checking the consistency of recorded data and perform checks based on those criteria. This enables accurate recording by automatically checking data consistency. Some or all of the above processes in the recording unit may be performed using AI or not. For example, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist.

[0109] The recording unit can estimate the pharmacist's emotions and determine the priority of recordings based on the estimated emotions. For example, if the pharmacist is tired, the recording unit can prioritize important recordings. If the pharmacist is relaxed, the recording unit can record with normal priorities. Furthermore, if the pharmacist is in a hurry, the recording unit can prioritize recording only the important parts. In this way, by determining the priority of recordings according to the pharmacist's emotions, important recordings can be prioritized. Emotion estimation is achieved using an emotion estimation function, such as 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 recording unit may be performed using AI or not. For example, the recording unit can have AI automatically estimate the pharmacist's emotions and determine the priority of recordings.

[0110] The recording unit can adjust the recording content by referring to the pharmacist's past recording history at the time of recording. For example, the recording unit can refer to the pharmacist's past recording history and adjust the recording content. The recording unit can also suggest appropriate recording procedures based on past recording history. Furthermore, the recording unit can adjust the recording content by comprehensively considering past recording history and the current situation. In this way, appropriate recording content is adjusted by referring to past recording history. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can use AI to automatically refer to the pharmacist's past recording history and adjust the recording content.

[0111] The recording unit can customize the recording format based on the pharmacist's area of ​​expertise at the time of recording. For example, the recording unit can customize the recording format based on the pharmacist's area of ​​expertise. The recording unit can also suggest recording procedures appropriate to the area of ​​expertise. Furthermore, the recording unit can customize the recording format by comprehensively considering the area of ​​expertise and the current situation. This allows for efficient recording by customizing the recording format based on the area of ​​expertise. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can use AI to automatically refer to the pharmacist's area of ​​expertise and customize the recording format.

[0112] The recording unit can be equipped with a function to automatically check the consistency of data during recording. For example, the recording unit can check the consistency of recorded data by comparing it with past data. Furthermore, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist. In addition, the recording unit can set criteria for checking the consistency of recorded data and perform checks based on those criteria. This enables accurate recording by automatically checking data consistency. Some or all of the above processes in the recording unit may be performed using AI or not. For example, the recording unit can have AI automatically check the consistency of recorded data and present it to the pharmacist.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] The automated medication history recording system can also include a lifestyle analysis unit that takes into account the patient's lifestyle. This unit can collect data such as the patient's diet, exercise, and sleep, and use this data to customize medication history assessments and plans. For example, if a patient has hypertension, the lifestyle analysis unit can consider their salt intake and suggest appropriate medications. It can also generate plans that include advice to encourage exercise for patients who are sedentary. Furthermore, based on sleep data, it can suggest appropriate medications and lifestyle improvements for sleep disorders. This allows for the creation of more personalized medication histories based on the patient's lifestyle, which is expected to improve treatment effectiveness.

[0115] The automated medication history recording system can further include an emotion analysis unit that estimates the patient's emotions and adjusts the content of the medication history based on those emotions. For example, if the patient is feeling anxious, the emotion analysis unit can record this in the medication history, allowing the pharmacist to take steps to alleviate the patient's anxiety. If the patient is relaxed, the system can maintain the normal content of the record. Furthermore, if the patient is in a hurry, the system can prioritize recording important information to encourage a quick response. This enables flexible medication history recording that responds to the patient's emotions, which is expected to improve patient satisfaction.

[0116] The automated medication history recording system can also be equipped with a geographic information analysis unit that takes into account the patient's geographic location. This unit can, for example, propose appropriate medication history assessments and plans based on information about medical resources and the environment in the patient's area. For instance, if a patient lives in an area with limited medical resources, it can suggest the use of telemedicine. If a patient lives in an urban area, it can provide information about nearby medical institutions and pharmacies. Furthermore, it can offer suggestions for lifestyle improvements tailored to the patient's living environment. This results in the creation of more appropriate medication histories that consider geographical factors, improving patient convenience.

[0117] The automated medication history recording system can also include a social media analysis unit that analyzes patients' social media activity. This unit can, for example, analyze health-related posts on a patient's social media and reflect the findings in medication history assessments and plans. For instance, if a patient frequently posts about a specific symptom on social media, the system can record appropriate responses to that symptom in the medication history. Furthermore, if a patient actively shares health-related information, the system can use that information to suggest lifestyle improvements. Additionally, the system can consider the patient's psychological state as revealed by their social media activity to ensure appropriate medication history entries. This results in the creation of more personalized medication histories that leverage the patient's social media activity.

[0118] The automated medication history recording system may also include an emotion order adjustment unit that estimates the patient's emotions and adjusts the order of medication history entries based on those emotions. For example, if the patient is anxious, the emotion order adjustment unit can record information to help them relax first, followed by important information. If the patient is relaxed, it can record the information in the usual order. Furthermore, if the patient is in a hurry, it can record important information first to encourage a quick response. This enables flexible medication history recording that responds to the patient's emotions, which is expected to improve patient satisfaction.

[0119] The automated medication history recording system can also include a living environment analysis unit that considers the patient's lifestyle and environmental information. For example, the living environment analysis unit can collect data on the patient's living environment and lifestyle, and customize medication history assessments and plans based on this data. For instance, if the patient is elderly, it can suggest appropriate medications tailored to their living environment. If the patient is sedentary, it can generate a plan that includes advice to promote exercise. Furthermore, it can consider the patient's dietary habits and propose a plan that includes dietary advice. This allows for the creation of more personalized medication histories based on the patient's living environment, which is expected to improve treatment effectiveness.

[0120] The automated medication history recording system can further include an emotion content adjustment unit that estimates the patient's emotions and adjusts the content of the medication history based on the estimated emotions. For example, if the patient is feeling anxious, the emotion content adjustment unit can record this in the medication history, allowing the pharmacist to take action to alleviate the patient's anxiety. If the patient is relaxed, the system can maintain the normal content of the record. Furthermore, if the patient is in a hurry, the system can prioritize recording important information to encourage a quick response. This enables flexible medication history recording that responds to the patient's emotions, which is expected to improve patient satisfaction.

[0121] The automated medication history recording system may further include an emotion-based adjustment unit that estimates the patient's emotions and adjusts the method of recording the medication history based on those emotions. For example, if the patient is anxious, the emotion-based adjustment unit can use a concise and clear recording method. If the patient is relaxed, it can use a detailed and polite recording method. Furthermore, if the patient is in a hurry, it can use a concise and to-the-point recording method. This enables flexible medication history recording that responds to the patient's emotions, which is expected to improve patient satisfaction.

[0122] The automated medication history recording system can further include an emotion content adjustment unit that estimates the patient's emotions and adjusts the content of the medication history based on the estimated emotions. For example, if the patient is feeling anxious, the emotion content adjustment unit can record this in the medication history, allowing the pharmacist to take action to alleviate the patient's anxiety. If the patient is relaxed, the system can maintain the normal content of the record. Furthermore, if the patient is in a hurry, the system can prioritize recording important information to encourage a quick response. This enables flexible medication history recording that responds to the patient's emotions, which is expected to improve patient satisfaction.

[0123] The automated medication history recording system may also include an emotion order adjustment unit that estimates the patient's emotions and adjusts the order of medication history entries based on those emotions. For example, if the patient is anxious, the emotion order adjustment unit can record information to help them relax first, followed by important information. If the patient is relaxed, it can record the information in the usual order. Furthermore, if the patient is in a hurry, it can record important information first to encourage a quick response. This enables flexible medication history recording that responds to the patient's emotions, which is expected to improve patient satisfaction.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The recording unit records the conversation between the pharmacist and the patient. The recording unit can, for example, record the conversation between the pharmacist and the patient as high-quality audio data. The recording unit can also automatically detect when the conversation begins and start recording. Furthermore, the recording unit can detect when the conversation ends and stop recording. Step 2: The analysis unit analyzes the data recorded by the recording unit, transcribes and summarizes the dialogue. The analysis unit can, for example, automatically analyze the recorded data using generative AI and transcribe the dialogue. The analysis unit can also summarize the dialogue using generative AI and compile it into a main complaint. Furthermore, the analysis unit can highlight important parts of the dialogue during transcription. Step 3: The generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit. For example, the generation unit can generate objective data based on the chief complaint using generation AI. The generation unit can also generate assessments using generation AI. Furthermore, the generation unit can also generate plans using generation AI. Step 4: The approval department allows the pharmacist to review and approve or revise the content generated by the generation department. For example, the approval department can approve the generated content after the pharmacist has reviewed it and found no problems. The approval department can also allow the pharmacist to revise the generated content if there are any omissions or inconsistencies. Step 5: The Records Unit records the medication history approved or modified by the Approval Unit. For example, the Records Unit can record approved or modified medication history in the system. The Records Unit can also use the recorded medication history to help with future patient care.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, approval unit, and recording unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records the conversation between the pharmacist and the patient using the microphone 38B of the smart device 14. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the recorded data to transcribe and summarize it. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates objective data, assessments, and plans based on the chief complaint. The approval unit is implemented in the specific processing unit 46A of the smart device 14, for example, and the pharmacist reviews, approves, or modifies the generated content. The recording unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and records the approved or modified medication history. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, approval unit, and recording unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit records the conversation between the pharmacist and the patient using the microphone 238 of the smart glasses 214. The analysis unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and analyzes the recorded data to transcribe and summarize it. The generation unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and generates objective data, assessments, and plans based on the chief complaint. The approval unit is implemented, for example, in the control unit 46A of the smart glasses 214, and the pharmacist reviews and approves or modifies the generated content. The recording unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and records the approved or modified medication history. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, approval unit, and recording unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit records the conversation between the pharmacist and the patient using the microphone 238 of the headset terminal 314. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the recorded data to transcribe and summarize it. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates objective data, assessments, and plans based on the chief complaint. The approval unit is implemented in the specific processing unit 46A of the headset terminal 314, for example, and the pharmacist reviews and approves or modifies the generated content. The recording unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and records the approved or modified medication history. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, approval unit, and recording unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the recording unit records the conversation between the pharmacist and the patient using the microphone 238 of the robot 414. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which analyzes the recorded data and performs transcription and summarization. The generation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which generates objective data, assessments, and plans based on the chief complaint. The approval unit is implemented by, for example, the control unit 46A of the robot 414, which allows the pharmacist to review, approve, or modify the generated content. The recording unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which records the approved or modified medication history. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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."

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] (Note 1) A recording unit that records conversations between pharmacists and patients, An analysis unit analyzes the data recorded by the aforementioned recording unit, transcribes the dialogue content, and summarizes it. A generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit, An approval unit in which a pharmacist reviews, approves, or modifies the content generated by the generation unit, The system includes a recording unit for recording the medication history approved or modified by the aforementioned approval unit. A system characterized by the following features. (Note 2) The aforementioned recording unit is Record the conversation between the pharmacist and the patient. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Automatically analyzes recorded data, transcribes the dialogue, and summarizes it. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Based on the chief complaint, we generate objective data, assessments, and plans. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is We will make suggestions based on past medication history data, medical consultation history, and medication use history. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned approval unit, The pharmacist reviews the generated content and approves or corrects it. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned recording unit is Record approved or revised medication history. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recording unit is The system estimates the patient's emotions and adjusts the recording start time based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned recording unit is It features a function that automatically highlights important parts of a conversation during recording. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned recording unit is The system analyzes recorded data in real time and automatically tags it with important keywords. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned recording unit is The system estimates the patient's emotions and adjusts the retention period of the recorded data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned recording unit is The system automatically filters out background noise from the patient during recording, ensuring clear recording of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned recording unit is Automatically saves audio data in multiple formats, making it easier to use for later analysis. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, The system estimates the patient's emotions and adjusts the accuracy of the transcription based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It has a feature that automatically corrects typos and grammatical errors by considering the context of the dialogue during analysis. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The level of detail in the summary is adjusted during analysis, taking into account the tone and speed of the dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, The system estimates the patient's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, Referencing background information from the dialogue during analysis improves the accuracy of the summary. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, summaries are prioritized based on the importance of the dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is It estimates the patient's emotions and adjusts the level of detail in the data generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is The accuracy of the generated data is improved by referencing past patient history data during the generation process. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is The assessment and plan are customized during generation, taking into account the patient's lifestyle and environmental information. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is The system estimates the patient's emotions and prioritizes the data to be generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating a plan, the system considers the patient's geographical location to propose the most suitable assessment and plan. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is Analyze the patient's social media activity during generation to adjust the generated content. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned approval unit, Estimate the pharmacist's emotions and adjust the approval process procedures based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned approval unit, During the approval process, we refer to past approval history to suggest the most suitable approval method. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned approval unit, It includes a function to automatically evaluate the reliability of data generated during the approval process. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned approval unit, The system estimates the pharmacist's emotions and determines approval priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned approval unit, The approval process involves referencing the pharmacist's past revision history to adjust the approval details. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned approval unit, Customize the approval process based on the pharmacist's area of ​​expertise during the approval process. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned recording unit is The system estimates the pharmacist's emotions and adjusts the record-keeping method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned recording unit is When recording, the system refers to past recording data to suggest the optimal recording format. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned recording unit is It includes a feature that automatically checks data consistency during recording. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned recording unit is The system estimates the pharmacist's emotions and determines the priority of records based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned recording unit is When recording, refer to the pharmacist's past record history to adjust the record content. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned recording unit is Customize the record format based on the pharmacist's area of ​​expertise when recording information. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned recording unit is It includes a feature that automatically checks data consistency during recording. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0198] 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 recording unit that records conversations between pharmacists and patients, An analysis unit analyzes the data recorded by the aforementioned recording unit, transcribes the dialogue content, and summarizes it. A generation unit generates objective data, assessments, and plans based on the chief complaint generated by the analysis unit, An approval unit in which a pharmacist reviews, approves, or modifies the content generated by the generation unit, The system includes a recording unit for recording the medication history approved or modified by the aforementioned approval unit. A system characterized by the following features.

2. The aforementioned recording unit is Record the conversation between the pharmacist and the patient. The system according to feature 1.

3. The aforementioned analysis unit, Automatically analyzes recorded data, transcribes the dialogue, and summarizes it. The system according to feature 1.

4. The generating unit is Based on the chief complaint, we generate objective data, assessments, and plans. The system according to feature 1.

5. The generating unit is We will make suggestions based on past medication history data, medical consultation history, and medication use history. The system according to feature 1.

6. The aforementioned approval unit, The pharmacist reviews the generated content and approves or corrects it. The system according to feature 1.

7. The recording unit is, Record approved or revised medication history. The system according to feature 1.

8. The aforementioned recording unit is The system estimates the patient's emotions and adjusts the recording start time based on those estimated emotions. The system according to feature 1.

9. The aforementioned recording unit is It features a function that automatically highlights important parts of a conversation during recording. The system according to feature 1.

10. The aforementioned recording unit is The system analyzes recorded data in real time and automatically tags it with important keywords. The system according to feature 1.

Images