system

Abstract

The system according to this embodiment aims to streamline the paperwork tasks performed by doctors. [Solution] The system according to the embodiment comprises an extraction unit, a summarization unit, a creation unit, and a confirmation unit. The extraction unit extracts information from the electronic medical record. The summarization unit summarizes the information extracted by the extraction unit. The creation unit creates a draft based on the information summarized by the summarization unit. The confirmation unit allows a physician to confirm the draft created by the creation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the paperwork of doctors contributes to overwork, and there is room for efficiency improvement.

[0005] The system according to the embodiment aims to improve the efficiency of doctors' paperwork.

Means for Solving the Problems

[0006] The system according to the embodiment includes an extraction unit, a summarization unit, a creation unit, and a confirmation unit. The extraction unit extracts information from an electronic medical record. The summarization unit summarizes the information extracted by the extraction unit. The creation unit creates a draft based on the information summarized by the summarization unit. The confirmation unit allows a doctor to confirm the draft created by the creation unit.

Effects of the Invention

[0007] The system according to this embodiment can streamline the paperwork tasks of physicians. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 document creation support system according to an embodiment of the present invention is a tool using generative AI to improve the efficiency of document creation in medical settings. This document creation support system contracts with medical institutions, extracts information from electronic medical records, and the generative AI summarizes the extracted information to create drafts of "medical information provision reports" and "discharge summaries." These drafts are then issued as documents after being reviewed by a physician. This mechanism can significantly reduce the time physicians spend creating documents and alleviate their excessive workload. For example, the document creation support system contracts with medical institutions and extracts information from electronic medical records. In this process, the electronic medical records contain patient medical information and test results, and the generative AI analyzes this information. For example, it can extract information such as the patient's diagnosis, treatment progress, and test results. Next, the generative AI summarizes the extracted information. Based on the extracted information, the generative AI creates drafts of "medical information provision reports" and "discharge summaries." For example, it summarizes the patient's diagnosis, treatment progress, and test results and compiles them into documents. These drafts are then issued as documents after being reviewed by a physician. This mechanism can significantly reduce the time physicians spend creating documents. For example, document creation that previously took more than 30 minutes per document can now be completed in minutes using generative AI. This allows doctors to concentrate on essential tasks, reducing their workload. Furthermore, using generative AI improves document quality. Because generative AI summarizes based on large amounts of data, it reduces information omissions and errors. This enables the creation of accurate and reliable documents. In this way, document creation support tools using generative AI can streamline document creation in medical settings and reduce the workload of doctors. They also contribute to improving document quality and increasing the efficiency of operations in medical settings. As a result, document creation support systems can significantly reduce the time doctors spend creating documents and alleviate their workload.

[0029] The document creation support system according to this embodiment comprises an extraction unit, a summarization unit, a creation unit, and a verification unit. The extraction unit extracts information from the electronic medical record. The extraction unit can extract information such as the patient's diagnosis, treatment progress, and test results. The extraction unit automatically extracts the necessary information from the electronic medical record using a generation AI. For example, the extraction unit inputs a prompt to the generation AI, "Please extract the patient's diagnosis," and the generation AI extracts the diagnosis. The extraction unit can also input a prompt to the generation AI, "Please extract the treatment progress," and the generation AI can extract the treatment progress. Furthermore, the extraction unit can input a prompt to the generation AI, "Please extract the test results," and the generation AI can extract the test results. The summarization unit summarizes the information extracted by the extraction unit. The summarization unit, for example, creates a draft of a "medical information provision document" or a "discharge summary" based on the extracted information. The summarization unit summarizes the extracted information using a generation AI. For example, the summarization unit prompts the generation AI with "Create a draft of the medical information report," and the generation AI creates the draft. The summarization unit can also prompt the generation AI with "Create a draft of the discharge summary," and the generation AI can create the draft. Furthermore, the summarization unit can prompt the generation AI with "Summarize the extracted information," and the generation AI can summarize the information. The creation unit creates a draft based on the information summarized by the summarization unit. For example, the creation unit creates drafts of "medical information reports" and "discharge summaries" based on the summarized information. The creation unit uses the generation AI to create drafts based on the summarized information. For example, the creation unit prompts the generation AI with "Create a draft of the medical information report," and the generation AI creates the draft. Furthermore, the creation unit can prompt the generation AI with "Create a draft of the discharge summary," and the generation AI can create the draft. Furthermore, the creation unit can prompt the generation AI with "Create a draft based on the summarized information," and the generation AI can create the draft. The verification department has doctors review the draft created by the creation department.The verification unit, for example, allows a physician to review the generated draft and make corrections as needed. The verification unit uses a generation AI to allow the physician to review the generated draft. For example, the verification unit inputs a prompt to the generation AI, "Please review the generated draft," and the generation AI reviews the draft. The verification unit can also input a prompt to the generation AI, "Please revise the generated draft," and the generation AI can revise the draft. Furthermore, the verification unit can input a prompt to the generation AI, "Please have the physician review the generated draft," and the generation AI reviews the draft. As a result, the document creation support system according to this embodiment can significantly reduce the time physicians spend creating documents and alleviate their workload.

[0030] The extraction unit extracts information from electronic medical records. For example, it can extract information such as a patient's diagnosis, treatment progress, and test results. Specifically, it utilizes generative AI to automatically extract necessary information from text and structured data within the electronic medical record. The generative AI employs natural language processing technology to analyze the contents of the electronic medical record and accurately extract the specified information. For example, if the prompt "Extract the patient's diagnosis" is entered into the generative AI, the AI ​​will identify and extract text related to the diagnosis within the medical record. Similarly, if the prompt "Extract the treatment progress" is entered, the AI ​​will extract text containing information about the progress of treatment and procedures. Furthermore, if the prompt "Extract the test results" is entered, the AI ​​will extract details such as the type of test, results, and date. This allows the extraction unit to quickly and accurately obtain the necessary information, saving doctors and medical staff the trouble of manually searching for information. The extracted information is then sent to the next steps, the summarization and creation units, where it is used as basic data for document creation. The extraction unit regularly updates the training data for the generating AI, ensuring that it can always extract information with high accuracy by adapting to the latest medical terminology and clinical guidelines.

[0031] The summarization unit summarizes the information extracted by the extraction unit. For example, the summarization unit creates drafts of "medical information provision reports" and "discharge summaries" based on the extracted information. Specifically, it uses a generation AI to summarize the extracted information and create draft documents. The generation AI analyzes the extracted information, extracts important points, and generates a summary. For example, if the prompt "Create a draft medical information provision report" is entered into the generation AI, the AI ​​combines information such as diagnosis, treatment progress, and test results to create a draft medical information provision report. Similarly, if the prompt "Create a draft discharge summary" is entered, the AI ​​summarizes the patient's condition at discharge, treatment details, and future follow-up plan to create a draft discharge summary. Furthermore, if the prompt "Summarize the extracted information" is entered, the AI ​​summarizes all the extracted information and generates a concise and easy-to-understand summary. The summarization unit optimizes the generation AI's summarization algorithm and performs summarization tailored to the characteristics of medical documents, enabling doctors and medical staff to quickly grasp the information. The summarized information is sent to the next step, the drafting department, where it is used to create the final document draft.

[0032] The creation unit creates drafts based on the information summarized by the summarization unit. For example, the creation unit creates drafts of "medical information provision reports" and "discharge summaries" based on the summarized information. Specifically, it uses a generation AI to create drafts based on the summarized information. The generation AI generates drafts according to the document structure and format based on the summarized information. For example, if the prompt "Create a draft of a medical information provision report" is entered into the generation AI, the AI ​​will create a draft according to the standard format of a medical information provision report, appropriately arranging information such as the diagnosis, treatment progress, and test results. Similarly, if the prompt "Create a draft of a discharge summary" is entered, the AI ​​will create a draft according to the standard format of a discharge summary, appropriately arranging information such as the patient's condition at discharge, treatment details, and future follow-up plan. Furthermore, if the prompt "Create a draft based on the summarized information" is entered, the AI ​​will create a draft of the specified document based on the summarized information. The creation unit optimizes the document generation algorithm of the generation AI and creates drafts tailored to the characteristics of medical documents, enabling doctors and medical staff to complete documents quickly. The created draft is sent to the next step, the review section, where it undergoes final verification and revisions.

[0033] The verification unit allows physicians to review drafts created by the creation unit. Specifically, the verification unit uses a generation AI to allow physicians to review the drafts. The generation AI analyzes the draft content, detects grammatical and terminological errors, and suggests revisions. For example, if the prompt "Please review the generated draft" is entered into the generation AI, the AI ​​checks the draft content and points out errors and inappropriate expressions. If the prompt "Please revise the generated draft" is entered, the AI ​​corrects the identified errors and suggests revisions. Furthermore, if the prompt "Please have the physician review the generated draft" is entered, the AI ​​analyzes the draft content and highlights points that the physician should review. The verification unit optimizes the generation AI's verification algorithm and performs verification work tailored to the characteristics of medical documents, enabling physicians and medical staff to quickly review and revise documents. This allows the verification unit to significantly reduce the time physicians spend creating documents and alleviate their workload. Finally, the reviewed documents are stored as official medical records and used to assist in patient care.

[0034] The medical record extraction unit extracts information from electronic medical records. For example, it can extract information such as the patient's diagnosis, treatment progress, and test results. The medical record extraction unit uses a generation AI to automatically extract the necessary information from the electronic medical records. For example, the medical record extraction unit can input a prompt to the generation AI, such as "Please extract the patient's diagnosis," and the generation AI will extract the diagnosis. The medical record extraction unit can also input a prompt to the generation AI, such as "Please extract the treatment progress," and the generation AI will extract the treatment progress. Furthermore, the medical record extraction unit can input a prompt to the generation AI, such as "Please extract the test results," and the generation AI will extract the test results. This allows for efficient information extraction from electronic medical records.

[0035] The issuing department issues summarized information as a document. For example, the issuing department can issue a "medical information provision form" or a "discharge summary" based on the summarized information. The issuing department can also issue summarized information as a document using a generative AI. For example, the issuing department can input the prompt "Please issue a medical information provision form" to the generative AI, and the generative AI will issue the medical information provision form. The issuing department can also input the prompt "Please issue a discharge summary" to the generative AI, and the generative AI will issue a discharge summary. Furthermore, the issuing department can input the prompt "Please issue a document based on the summarized information" to the generative AI, and the generative AI will issue a document. This allows for the rapid issuance of summarized information as a document.

[0036] The extraction unit can extract information such as the patient's diagnosis, treatment history, and test results. For example, the extraction unit can extract the patient's diagnosis. The extraction unit uses a generation AI to automatically extract the patient's diagnosis. For example, the extraction unit can input a prompt to the generation AI, "Please extract the patient's diagnosis," and the generation AI will extract the diagnosis. The extraction unit can also extract the treatment history. The extraction unit uses a generation AI to automatically extract the treatment history. For example, the extraction unit can input a prompt to the generation AI, "Please extract the treatment history," and the generation AI will extract the treatment history. Furthermore, the extraction unit can also extract test results. The extraction unit uses a generation AI to automatically extract test results. For example, the extraction unit can input a prompt to the generation AI, "Please extract the test results," and the generation AI will extract the test results. This allows for the efficient extraction of information such as the patient's diagnosis, treatment history, and test results.

[0037] The summarization unit can create drafts of "medical information provision reports" and "discharge summaries" based on the extracted information. For example, the summarization unit can create a draft of a "medical information provision report" based on the extracted information. The summarization unit uses a generative AI to create drafts based on the extracted information. For example, the summarization unit can input a prompt to the generative AI, such as "Please create a draft of a medical information provision report," and the generative AI will create the draft. The summarization unit can also create drafts of "discharge summaries." The summarization unit uses a generative AI to create drafts based on the extracted information. For example, the summarization unit can input a prompt to the generative AI, such as "Please create a draft of a discharge summary," and the generative AI will create the draft. Furthermore, the summarization unit can also create drafts based on the extracted information. The summarization unit uses a generative AI to create drafts based on the extracted information. For example, the summarization unit can input a prompt to the generative AI, such as "Please create a draft based on the extracted information," and the generative AI will create the draft. This allows for efficient draft creation based on the extracted information.

[0038] The review unit allows physicians to review the generated draft. For example, the review unit allows physicians to review the generated draft and make corrections as needed. The review unit can also use a generation AI to allow physicians to review the generated draft. For example, the review unit can input a prompt to the generation AI such as "Please review the generated draft," and the generation AI will review the draft. The review unit can also input a prompt to the generation AI such as "Please revise the generated draft," and the generation AI will revise the draft. Furthermore, the review unit can input a prompt to the generation AI such as "Please have the physician review the generated draft," and the generation AI will review the draft. This ensures the accuracy of the document by allowing physicians to review the generated draft.

[0039] The extraction unit can estimate the doctor's emotions and adjust the timing of information extraction based on the estimated emotions. For example, if the doctor is tired, the extraction unit will adjust the timing to extract information during break times. The extraction unit uses a generation AI to estimate the doctor's emotions and adjust the timing of information extraction. For example, the extraction unit can input a prompt to the generation AI such as "Estimate the doctor's emotions," and the generation AI will estimate the doctor's emotions. The extraction unit can also input a prompt to the generation AI such as "Adjust the timing of information extraction based on the doctor's emotions," and the generation AI will adjust the timing of information extraction. Furthermore, the extraction unit can input a prompt to the generation AI such as "If the doctor is tired, extract information during break times," and the generation AI will adjust the timing of information extraction. This allows for efficient information extraction by adjusting the timing of information extraction according to the doctor's emotions.

[0040] The extraction unit can analyze a patient's medical history and select the optimal information extraction method. For example, the extraction unit can prioritize extracting highly relevant information based on the patient's past medical history. The extraction unit uses a generating AI to analyze the patient's medical history and select the optimal information extraction method. For example, the extraction unit can input a prompt to the generating AI, such as "Please analyze the patient's medical history," and the generating AI will analyze the medical history. Alternatively, the extraction unit can input a prompt to the generating AI, such as "Please select the optimal information extraction method," and the generating AI will select an information extraction method. Furthermore, the extraction unit can input a prompt to the generating AI, such as "Please prioritize extracting highly relevant information based on the patient's past medical history," and the generating AI will select an information extraction method. In this way, the optimal information extraction method can be selected by analyzing the patient's medical history.

[0041] The extraction unit can filter information based on the patient's current medical condition and treatment plan during the information extraction process. For example, the extraction unit can extract only relevant information based on the patient's current medical condition. The extraction unit uses a generation AI to perform filtering based on the patient's current medical condition and treatment plan. For example, the extraction unit can input a prompt to the generation AI saying, "Please filter the information based on the patient's current medical condition," and the generation AI will filter the information. Alternatively, the extraction unit can input a prompt to the generation AI saying, "Please filter the information based on the patient's treatment plan," and the generation AI will filter the information. Furthermore, the extraction unit can input a prompt to the generation AI saying, "Please filter based on the patient's current medical condition and treatment plan," and the generation AI will filter the information. This allows for the extraction of only relevant information by filtering based on the patient's current medical condition and treatment plan.

[0042] The extraction unit can estimate the doctor's emotions and determine the priority of information to extract based on the estimated emotions. For example, if the doctor is tired, the extraction unit will prioritize extracting important information. The extraction unit uses a generative AI to estimate the doctor's emotions and determine the priority of information. For example, the extraction unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The extraction unit can also input a prompt to the generative AI such as "Determine the priority of information based on the doctor's emotions," and the generative AI will determine the priority of information. Furthermore, the extraction unit can input a prompt to the generative AI such as "If the doctor is tired, prioritize extracting important information," and the generative AI will determine the priority of information. This enables efficient information extraction by determining the priority of information to extract according to the doctor's emotions.

[0043] The extraction unit can prioritize extracting highly relevant information by considering the patient's geographical location during information extraction. For example, the extraction unit can extract region-specific information based on the patient's place of residence. The extraction unit uses a generation AI to extract information while considering the patient's geographical location. For example, the extraction unit can input a prompt to the generation AI saying, "Please extract information based on the patient's geographical location," and the generation AI will extract the information. Alternatively, the extraction unit can input a prompt to the generation AI saying, "Please extract information based on the patient's place of residence," and the generation AI will extract the information. Furthermore, the extraction unit can input a prompt to the generation AI saying, "Please prioritize extracting highly relevant information by considering the patient's geographical location," and the generation AI will extract the information. This allows for the priority extraction of highly relevant information by considering the patient's geographical location.

[0044] The extraction unit can analyze a patient's social media activity and extract relevant information during information extraction. For example, the extraction unit can extract information about a patient's health status from their social media posts. The extraction unit uses a generative AI to analyze the patient's social media activity and extract information. For example, the extraction unit can input a prompt to the generative AI such as "Analyze the patient's social media activity," and the generative AI will analyze the social media activity. The extraction unit can also input a prompt to the generative AI such as "Extract information from the patient's social media posts," and the generative AI will extract the information. Furthermore, the extraction unit can input a prompt to the generative AI such as "Extract relevant information based on the patient's social media activity," and the generative AI will extract the information. This allows for the efficient extraction of relevant information by analyzing the patient's social media activity.

[0045] The summarization unit can estimate the doctor's emotions and adjust the way the summary is presented based on those emotions. For example, if the doctor is tired, the summarization unit will provide a concise and to-the-point summary. The summarization unit uses generative AI to estimate the doctor's emotions and adjust the way the summary is presented. For example, the summarization unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The summarization unit can also input a prompt to the generative AI such as "Adjust the way the summary is presented based on the doctor's emotions," and the generative AI will adjust the way the summary is presented. Furthermore, the summarization unit can input a prompt to the generative AI such as "If the doctor is tired, provide a concise and to-the-point summary," and the generative AI will adjust the way the summary is presented. This allows for efficient summarization by adjusting the way the summary is presented according to the doctor's emotions.

[0046] The summarization unit can adjust the level of detail in a summary based on the importance of the information during the summarization process. For example, the summarization unit prioritizes summarizing important information and includes it in detail. The summarization unit uses a generation AI to adjust the level of detail in the summary based on the importance of the information. For example, the summarization unit can input a prompt to the generation AI such as "Please evaluate the importance of the information," and the generation AI will evaluate the importance of the information. The summarization unit can also input a prompt to the generation AI such as "Please prioritize summarizing important information," and the generation AI will adjust the level of detail in the summary. Furthermore, the summarization unit can input a prompt to the generation AI such as "Please adjust the level of detail in the summary based on the importance of the information," and the generation AI will adjust the level of detail in the summary. This allows for efficient summarization by adjusting the level of detail in the summary based on the importance of the information.

[0047] The summarization unit can apply different summarization algorithms depending on the information category when generating summaries. For example, the summarization unit applies a diagnostic-specific summarization algorithm to diagnostic information. The summarization unit uses a generation AI to apply summarization algorithms according to the information category. For example, the summarization unit can input a prompt to the generation AI, "Summarize the diagnostic information," and the generation AI will summarize the diagnostic information. The summarization unit can also input a prompt to the generation AI, "Summarize the treatment progress," and the generation AI will summarize the treatment progress. Furthermore, the summarization unit can input a prompt to the generation AI, "Apply a summarization algorithm according to the information category," and the generation AI will apply a summarization algorithm. This allows for efficient summarization by applying different summarization algorithms depending on the information category.

[0048] The summarization unit can estimate the doctor's emotions and adjust the length of the summary based on the estimated emotions. For example, if the doctor is tired, the summarization unit will provide a short, concise summary. The summarization unit uses generative AI to estimate the doctor's emotions and adjust the length of the summary. For example, the summarization unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The summarization unit can also input a prompt to the generative AI such as "Adjust the length of the summary based on the doctor's emotions," and the generative AI will adjust the length of the summary. Furthermore, the summarization unit can input a prompt to the generative AI such as "If the doctor is tired, provide a short, concise summary," and the generative AI will adjust the length of the summary. This allows for efficient summarization by adjusting the length of the summary according to the doctor's emotions.

[0049] The summarization unit can prioritize summaries based on when the information was submitted. For example, the summarization unit prioritizes summarizing information with high urgency. The summarization unit uses a generation AI to determine the priority of summaries based on when the information was submitted. For example, the summarization unit can input a prompt to the generation AI such as "Please evaluate the submission timing of the information," and the generation AI will evaluate the submission timing. The summarization unit can also input a prompt to the generation AI such as "Please prioritize summarizing information with high urgency," and the generation AI will determine the priority of summaries. Furthermore, the summarization unit can input a prompt to the generation AI such as "Please determine the priority of summaries based on when the information was submitted," and the generation AI will determine the priority of summaries. This enables efficient summarization by prioritizing summaries based on when the information was submitted.

[0050] The summarization unit can adjust the order of summaries based on the relevance of the information during the summarization process. For example, the summarization unit prioritizes summarizing highly relevant information. The summarization unit uses a generation AI to adjust the order of summaries based on the relevance of the information. For example, the summarization unit can input a prompt to the generation AI such as "Please evaluate the relevance of the information," and the generation AI will evaluate the relevance of the information. The summarization unit can also input a prompt to the generation AI such as "Please prioritize summarizing highly relevant information," and the generation AI will adjust the order of the summaries. Furthermore, the summarization unit can input a prompt to the generation AI such as "Please adjust the order of summaries based on the relevance of the information," and the generation AI will adjust the order of the summaries. This allows for efficient summarization by adjusting the order of summaries based on the relevance of the information.

[0051] The drafting unit can estimate the doctor's emotions and adjust the draft's presentation based on those emotions. For example, if the doctor is tired, the unit will provide a concise and to-the-point draft. The drafting unit uses generative AI to estimate the doctor's emotions and adjust the draft's presentation. For example, the drafting unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The drafting unit can also input a prompt to the generative AI such as "Adjust the draft's presentation based on the doctor's emotions," and the generative AI will adjust the draft's presentation. Furthermore, the drafting unit can input a prompt to the generative AI such as "If the doctor is tired, provide a concise and to-the-point draft," and the generative AI will adjust the draft's presentation. This allows for efficient draft creation by adjusting the draft's presentation according to the doctor's emotions.

[0052] The drafting unit can adjust the level of detail of a draft based on the importance of the information during the drafting process. For example, the unit prioritizes including important information in the draft. The unit uses a generative AI to adjust the level of detail of the draft based on the importance of the information. For example, the unit can input a prompt to the generative AI such as "Please evaluate the importance of the information," and the generative AI will evaluate the importance of the information. The unit can also input a prompt to the generative AI such as "Please prioritize including important information in the draft," and the generative AI will adjust the level of detail of the draft. Furthermore, the unit can input a prompt to the generative AI such as "Please adjust the level of detail of the draft based on the importance of the information," and the generative AI will adjust the level of detail of the draft. This allows for efficient drafting by adjusting the level of detail of the draft based on the importance of the information.

[0053] The drafting unit can apply different drafting algorithms depending on the information category during draft creation. For example, the unit applies a diagnostic-specific drafting algorithm to diagnostic information. The unit uses a generative AI to apply drafting algorithms according to the information category. For example, the unit can input a prompt to the generative AI, "Please include diagnostic information in the draft," and the generative AI will include the diagnostic information in the draft. The unit can also input a prompt to the generative AI, "Please include treatment progress in the draft," and the generative AI will include treatment progress in the draft. Furthermore, the unit can input a prompt to the generative AI, "Please apply a drafting algorithm according to the information category," and the generative AI will apply a drafting algorithm. This allows for efficient draft creation by applying different drafting algorithms according to the information category.

[0054] The drafting unit can estimate the doctor's emotions and adjust the length of the draft based on the estimated emotions. For example, if the doctor is tired, the drafting unit will provide a short, concise draft. The drafting unit uses generative AI to estimate the doctor's emotions and adjust the length of the draft. For example, the drafting unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The drafting unit can also input the prompt "Adjust the length of the draft based on the doctor's emotions" to the generative AI, and the generative AI will adjust the length of the draft. Furthermore, the drafting unit can input the prompt "If the doctor is tired, provide a short, concise draft" to the generative AI, and the generative AI will adjust the length of the draft. This allows for efficient draft creation by adjusting the length of the draft according to the doctor's emotions.

[0055] The drafting team can determine the priority of drafts based on the timing of information submission when creating a draft. For example, the team can prioritize including information with high urgency in the draft. The team uses a generative AI to determine the priority of drafts based on the timing of information submission. For example, the team can input a prompt to the generative AI saying, "Please evaluate the timing of information submission," and the generative AI will evaluate the timing of information submission. The team can also input a prompt to the generative AI saying, "Please prioritize including information with high urgency in the draft," and the generative AI will determine the priority of the draft. Furthermore, the team can input a prompt to the generative AI saying, "Please determine the priority of drafts based on the timing of information submission," and the generative AI will determine the priority of the draft. This enables efficient draft creation by determining the priority of drafts based on the timing of information submission.

[0056] The drafting unit can adjust the order of information in the draft based on its relevance. For example, the unit prioritizes including highly relevant information in the draft. The unit uses a generative AI to adjust the order of information based on its relevance. For example, the unit can input a prompt to the generative AI such as "Please evaluate the relevance of the information," and the generative AI will evaluate the relevance of the information. The unit can also input a prompt to the generative AI such as "Please prioritize including highly relevant information in the draft," and the generative AI will adjust the order of the draft. Furthermore, the unit can input a prompt to the generative AI such as "Please adjust the order of the draft based on the relevance of the information," and the generative AI will adjust the order of the draft. This allows for efficient drafting by adjusting the order of information based on its relevance.

[0057] The verification unit can estimate the doctor's emotions and adjust the timing of the verification based on the estimated emotions. For example, if the doctor is tired, the verification unit will adjust the timing to perform the verification during their break. The verification unit uses generative AI to estimate the doctor's emotions and adjust the timing of the verification. For example, the verification unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The verification unit can also input the prompt "Adjust the timing of the verification based on the doctor's emotions" to the generative AI, and the generative AI will adjust the timing of the verification. Furthermore, the verification unit can input the prompt "If the doctor is tired, perform the verification during their break" to the generative AI, and the generative AI will adjust the timing of the verification. This allows for more efficient verification by adjusting the timing of the verification according to the doctor's emotions.

[0058] The verification unit can select the optimal verification method by referring to past verification history during the verification process. For example, the verification unit can propose the optimal verification method based on past verification history. The verification unit uses a generation AI to refer to past verification history and select a verification method. For example, the verification unit can input the prompt "Please refer to past verification history" to the generation AI, and the generation AI will refer to the verification history. Alternatively, the verification unit can input the prompt "Please select the optimal verification method" to the generation AI, and the generation AI will select a verification method. Furthermore, the verification unit can input the prompt "Please propose the optimal verification method based on past verification history" to the generation AI, and the generation AI will select a verification method. In this way, the optimal verification method can be selected by referring to past verification history.

[0059] The verification unit can estimate the doctor's emotions and determine the priority of verifications based on the estimated emotions. For example, if the doctor is tired, the verification unit will prioritize important verifications. The verification unit uses generative AI to estimate the doctor's emotions and determine the priority of verifications. For example, the verification unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The verification unit can also input the prompt "Determine the priority of verifications based on the doctor's emotions" to the generative AI, and the generative AI will determine the priority of verifications. Furthermore, the verification unit can input the prompt "If the doctor is tired, please prioritize important verifications" to the generative AI, and the generative AI will determine the priority of verifications. This allows for more efficient verifications by determining the priority of verifications according to the doctor's emotions.

[0060] The verification unit can select the optimal verification method by considering the physician's device information during verification. For example, if the physician is using a smartphone, the verification unit will provide a verification method that matches the screen size. The verification unit uses a generation AI to select a verification method that considers the physician's device information. For example, the verification unit can input a prompt to the generation AI saying, "Please consider the physician's device information," and the generation AI will take the device information into account. The verification unit can also input a prompt to the generation AI saying, "Please select the optimal verification method," and the generation AI will select a verification method. Furthermore, the verification unit can input a prompt to the generation AI saying, "If the physician is using a smartphone, please provide a verification method that matches the screen size," and the generation AI will select a verification method. In this way, the optimal verification method can be selected by considering the physician's device information.

[0061] The medical record extraction unit can estimate the doctor's emotions and adjust the timing of medical record extraction based on the estimated emotions. For example, if the doctor is tired, the medical record extraction unit will adjust the extraction timing to coincide with the doctor's break time. The medical record extraction unit uses a generation AI to estimate the doctor's emotions and adjust the timing of medical record extraction. For example, the medical record extraction unit can input a prompt to the generation AI such as "Estimate the doctor's emotions," and the generation AI will estimate the doctor's emotions. The medical record extraction unit can also input a prompt to the generation AI such as "Adjust the timing of medical record extraction based on the doctor's emotions," and the generation AI will adjust the timing of medical record extraction. Furthermore, the medical record extraction unit can input a prompt to the generation AI such as "If the doctor is tired, extract the medical record during their break time," and the generation AI will adjust the timing of medical record extraction. This allows for efficient medical record extraction by adjusting the timing of medical record extraction according to the doctor's emotions.

[0062] The medical record extraction unit can analyze the patient's medical history and select the optimal extraction method during medical record extraction. For example, the medical record extraction unit prioritizes extracting highly relevant information based on the patient's past medical history. The medical record extraction unit uses a generating AI to analyze the patient's medical history and select the extraction method. For example, the medical record extraction unit can input a prompt to the generating AI, such as "Please analyze the patient's medical history," and the generating AI will analyze the medical history. Alternatively, the medical record extraction unit can input a prompt to the generating AI, such as "Please select the optimal extraction method," and the generating AI will select the extraction method. Furthermore, the medical record extraction unit can input a prompt to the generating AI, such as "Please prioritize extracting highly relevant information based on the patient's past medical history," and the generating AI will select the extraction method. In this way, the optimal medical record extraction method can be selected by analyzing the patient's medical history.

[0063] The medical record extraction unit can estimate the doctor's emotions and determine the priority of medical record extraction based on the estimated emotions. For example, if the doctor is tired, the medical record extraction unit will prioritize the extraction of important information. The medical record extraction unit uses a generation AI to estimate the doctor's emotions and determine the priority of medical record extraction. For example, the medical record extraction unit can input a prompt to the generation AI such as "Estimate the doctor's emotions," and the generation AI will estimate the doctor's emotions. The medical record extraction unit can also input a prompt to the generation AI such as "Determine the priority of medical record extraction based on the doctor's emotions," and the generation AI will determine the priority of medical record extraction. Furthermore, the medical record extraction unit can input a prompt to the generation AI such as "If the doctor is tired, prioritize the extraction of important information," and the generation AI will determine the priority of medical record extraction. This enables efficient medical record extraction by determining the priority of medical record extraction according to the doctor's emotions.

[0064] The medical record extraction unit can prioritize the extraction of highly relevant information by considering the patient's geographical location during medical record extraction. For example, the medical record extraction unit can extract region-specific information based on the patient's place of residence. The medical record extraction unit uses a generation AI to extract information while considering the patient's geographical location. For example, the medical record extraction unit can input a prompt to the generation AI saying, "Please extract information based on the patient's geographical location," and the generation AI will extract the information. Alternatively, the medical record extraction unit can input a prompt to the generation AI saying, "Please prioritize the extraction of highly relevant information by considering the patient's geographical location," and the generation AI will extract the information. In this way, by considering the patient's geographical location, highly relevant information can be prioritized for extraction.

[0065] The issuing unit can estimate the doctor's emotions and adjust the timing of document issuance based on the estimated emotions. For example, if the doctor is tired, the issuing unit can adjust the timing to issue the document during their break. The issuing unit uses generative AI to estimate the doctor's emotions and adjust the timing of document issuance. For example, the issuing unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The issuing unit can also input the prompt "Adjust the timing of document issuance based on the doctor's emotions" to the generative AI, and the generative AI will adjust the timing of document issuance. Furthermore, the issuing unit can input the prompt "If the doctor is tired, issue the document during their break" to the generative AI, and the generative AI will adjust the timing of document issuance. This allows for efficient document issuance by adjusting the timing of document issuance according to the doctor's emotions.

[0066] The issuing department can select the optimal issuing method by referring to past issuing history at the time of issuance. For example, the issuing department can propose the optimal issuing method based on past issuing history. The issuing department uses a generation AI to refer to past issuing history and select an issuing method. For example, the issuing department can input the prompt "Please refer to past issuing history" to the generation AI, and the generation AI will refer to the issuing history. Alternatively, the issuing department can input the prompt "Please select the optimal issuing method" to the generation AI, and the generation AI will select an issuing method. Furthermore, the issuing department can input the prompt "Please propose the optimal issuing method based on past issuing history" to the generation AI, and the generation AI will select an issuing method. In this way, the optimal issuing method can be selected by referring to past issuing history.

[0067] The issuing department can estimate a doctor's emotions and determine the priority of issuance based on that estimation. For example, if a doctor is tired, the issuing department will prioritize issuing important documents. The issuing department uses generative AI to estimate a doctor's emotions and determine the priority of issuance. For example, the issuing department can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The issuing department can also input the prompt "Determine the priority of issuance based on the doctor's emotions" to the generative AI, and the generative AI will determine the priority of issuance. Furthermore, the issuing department can input the prompt "If the doctor is tired, prioritize issuing important documents" to the generative AI, and the generative AI will determine the priority of issuance. This enables efficient document issuance by determining the priority of issuance according to the doctor's emotions.

[0068] The issuing unit can select the optimal issuing method when issuing documents, taking into account the physician's device information. For example, if the physician is using a smartphone, the issuing unit will provide an issuing method that matches the screen size. The issuing unit uses a generation AI to select an issuing method that takes the physician's device information into account. For example, the issuing unit can input a prompt to the generation AI saying, "Please consider the physician's device information," and the generation AI will take the device information into account. The issuing unit can also input a prompt to the generation AI saying, "Please select the optimal issuing method," and the generation AI will select an issuing method. Furthermore, the issuing unit can input a prompt to the generation AI saying, "If the physician is using a smartphone, please provide an issuing method that matches the screen size," and the generation AI will select an issuing method. In this way, the optimal issuing method can be selected by taking the physician's device information into account.

[0069] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0070] The document creation support system can also be equipped with a voice input unit. The voice input unit allows doctors to give instructions by voice, and uses speech recognition technology to convert the instructions into text. For example, if a doctor gives the voice instruction, "Extract the patient's diagnosis," the voice input unit converts the instruction into text and sends it to the extraction unit. Also, if a doctor gives the voice input unit, "Create a discharge summary," the voice input unit sends the instruction to the summarization unit, which can create a draft of the discharge summary. Furthermore, if a doctor gives the voice input unit, "Review this draft," the voice input unit sends the instruction to the review unit, which can review the draft. This allows doctors to give instructions by voice without using their hands, improving work efficiency.

[0071] The document creation support system can also include a translation function. This function can translate the created documents into multiple languages. For example, it can translate a medical information report into English. It can also translate a discharge summary into Spanish. Furthermore, the translation function can automatically translate the content of documents using a generative AI. For example, the translation function can input a prompt to the generative AI, such as "Translate this document into English," and the generative AI can translate the document into English. This allows documents to be shared even among international healthcare institutions.

[0072] The document creation support system can also be equipped with an image analysis unit. The image analysis unit can analyze image data contained in electronic medical records and extract necessary information. For example, it can identify abnormal areas from a patient's X-ray image and extract that information. The image analysis unit can also identify the location of a tumor from an MRI image and extract that information. Furthermore, the image analysis unit can analyze image data and extract necessary information using a generation AI. For example, the image analysis unit can input a prompt to the generation AI such as "Identify abnormal areas from this X-ray image," and the generation AI can identify the abnormal areas. This allows for efficient information extraction from image data.

[0073] The document creation support system can also be equipped with a database integration unit. This unit can integrate with other medical databases to retrieve necessary information. For example, it can retrieve a patient's past medical history from another medical institution's database. Furthermore, the database integration unit can retrieve drug information from a drug information database. Additionally, the database integration unit can use a generation AI to integrate with other databases and retrieve necessary information. For example, the database integration unit can input a prompt to the generation AI such as, "Please retrieve the patient's medical history from another medical institution's database," and the generation AI can retrieve the medical history. This allows for the retrieval of more information by integrating with other databases.

[0074] The document creation support system can also be equipped with an alert notification unit. This unit can notify a physician when important information is extracted. For example, it can send an alert to a physician if there is an abnormality in a patient's test results. It can also notify a physician if a patient's condition suddenly changes. Furthermore, the alert notification unit can use a generation AI to detect important information and notify a physician. For example, the alert notification unit can input a prompt to the generation AI such as "Detect important information," and the generation AI can detect the important information and notify the physician. This allows important information to be quickly conveyed to the physician.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The extraction unit extracts information from the electronic medical record. For example, it extracts information such as the patient's diagnosis, treatment progress, and test results. The extraction unit uses a generation AI to automatically extract the necessary information from the electronic medical record. Specifically, prompts such as "Please extract the patient's diagnosis" or "Please extract the treatment progress" are input to the generation AI, and the generation AI extracts the corresponding information. Step 2: The summarization unit summarizes the information extracted by the extraction unit. For example, it creates drafts of "medical information provision reports" and "discharge summaries" based on the extracted information. The summarization unit uses a generation AI to summarize the extracted information. Specifically, prompts such as "Please create a draft of a medical information provision report" or "Please create a draft of a discharge summary" are input to the generation AI, and the generation AI creates the drafts. Step 3: The creation unit creates a draft based on the information summarized by the summarization unit. For example, it creates drafts of a "medical information provision report" and a "discharge summary" based on the summarized information. The creation unit uses a generation AI to create drafts based on the summarized information. Specifically, prompts such as "Please create a draft of the medical information provision report" or "Please create a draft of the discharge summary" are input to the generation AI, and the generation AI creates the drafts. Step 4: The review unit has the physician review the draft created by the creation unit. For example, the physician reviews the created draft and makes revisions as needed. The review unit uses a generation AI to have the physician review the created draft. Specifically, prompts such as "Please review the created draft" or "Please revise the created draft" are input to the generation AI, and the generation AI reviews or revises the draft.

[0077] (Example of form 2) The document creation support system according to an embodiment of the present invention is a tool using generative AI to improve the efficiency of document creation in medical settings. This document creation support system contracts with medical institutions, extracts information from electronic medical records, and the generative AI summarizes the extracted information to create drafts of "medical information provision reports" and "discharge summaries." These drafts are then issued as documents after being reviewed by a physician. This mechanism can significantly reduce the time physicians spend creating documents and alleviate their excessive workload. For example, the document creation support system contracts with medical institutions and extracts information from electronic medical records. In this process, the electronic medical records contain patient medical information and test results, and the generative AI analyzes this information. For example, it can extract information such as the patient's diagnosis, treatment progress, and test results. Next, the generative AI summarizes the extracted information. Based on the extracted information, the generative AI creates drafts of "medical information provision reports" and "discharge summaries." For example, it summarizes the patient's diagnosis, treatment progress, and test results and compiles them into documents. These drafts are then issued as documents after being reviewed by a physician. This mechanism can significantly reduce the time physicians spend creating documents. For example, document creation that previously took more than 30 minutes per document can now be completed in minutes using generative AI. This allows doctors to concentrate on essential tasks, reducing their workload. Furthermore, using generative AI improves document quality. Because generative AI summarizes based on large amounts of data, it reduces information omissions and errors. This enables the creation of accurate and reliable documents. In this way, document creation support tools using generative AI can streamline document creation in medical settings and reduce the workload of doctors. They also contribute to improving document quality and increasing the efficiency of operations in medical settings. As a result, document creation support systems can significantly reduce the time doctors spend creating documents and alleviate their workload.

[0078] The document creation support system according to this embodiment comprises an extraction unit, a summarization unit, a creation unit, and a verification unit. The extraction unit extracts information from the electronic medical record. The extraction unit can extract information such as the patient's diagnosis, treatment progress, and test results. The extraction unit automatically extracts the necessary information from the electronic medical record using a generation AI. For example, the extraction unit inputs a prompt to the generation AI, "Please extract the patient's diagnosis," and the generation AI extracts the diagnosis. The extraction unit can also input a prompt to the generation AI, "Please extract the treatment progress," and the generation AI can extract the treatment progress. Furthermore, the extraction unit can input a prompt to the generation AI, "Please extract the test results," and the generation AI can extract the test results. The summarization unit summarizes the information extracted by the extraction unit. The summarization unit, for example, creates a draft of a "medical information provision document" or a "discharge summary" based on the extracted information. The summarization unit summarizes the extracted information using a generation AI. For example, the summarization unit prompts the generation AI with "Create a draft of the medical information report," and the generation AI creates the draft. The summarization unit can also prompt the generation AI with "Create a draft of the discharge summary," and the generation AI can create the draft. Furthermore, the summarization unit can prompt the generation AI with "Summarize the extracted information," and the generation AI can summarize the information. The creation unit creates a draft based on the information summarized by the summarization unit. For example, the creation unit creates drafts of "medical information reports" and "discharge summaries" based on the summarized information. The creation unit uses the generation AI to create drafts based on the summarized information. For example, the creation unit prompts the generation AI with "Create a draft of the medical information report," and the generation AI creates the draft. Furthermore, the creation unit can prompt the generation AI with "Create a draft of the discharge summary," and the generation AI can create the draft. Furthermore, the creation unit can prompt the generation AI with "Create a draft based on the summarized information," and the generation AI can create the draft. The verification department has doctors review the draft created by the creation department.The verification unit, for example, allows a physician to review the generated draft and make corrections as needed. The verification unit uses a generation AI to allow the physician to review the generated draft. For example, the verification unit inputs a prompt to the generation AI, "Please review the generated draft," and the generation AI reviews the draft. The verification unit can also input a prompt to the generation AI, "Please revise the generated draft," and the generation AI can revise the draft. Furthermore, the verification unit can input a prompt to the generation AI, "Please have the physician review the generated draft," and the generation AI reviews the draft. As a result, the document creation support system according to this embodiment can significantly reduce the time physicians spend creating documents and alleviate their workload.

[0079] The extraction unit extracts information from electronic medical records. For example, it can extract information such as a patient's diagnosis, treatment progress, and test results. Specifically, it utilizes generative AI to automatically extract necessary information from text and structured data within the electronic medical record. The generative AI employs natural language processing technology to analyze the contents of the electronic medical record and accurately extract the specified information. For example, if the prompt "Extract the patient's diagnosis" is entered into the generative AI, the AI ​​will identify and extract text related to the diagnosis within the medical record. Similarly, if the prompt "Extract the treatment progress" is entered, the AI ​​will extract text containing information about the progress of treatment and procedures. Furthermore, if the prompt "Extract the test results" is entered, the AI ​​will extract details such as the type of test, results, and date. This allows the extraction unit to quickly and accurately obtain the necessary information, saving doctors and medical staff the trouble of manually searching for information. The extracted information is then sent to the next steps, the summarization and creation units, where it is used as basic data for document creation. The extraction unit regularly updates the training data for the generating AI, ensuring that it can always extract information with high accuracy by adapting to the latest medical terminology and clinical guidelines.

[0080] The summarization unit summarizes the information extracted by the extraction unit. For example, the summarization unit creates drafts of "medical information provision reports" and "discharge summaries" based on the extracted information. Specifically, it uses a generation AI to summarize the extracted information and create draft documents. The generation AI analyzes the extracted information, extracts important points, and generates a summary. For example, if the prompt "Create a draft medical information provision report" is entered into the generation AI, the AI ​​combines information such as diagnosis, treatment progress, and test results to create a draft medical information provision report. Similarly, if the prompt "Create a draft discharge summary" is entered, the AI ​​summarizes the patient's condition at discharge, treatment details, and future follow-up plan to create a draft discharge summary. Furthermore, if the prompt "Summarize the extracted information" is entered, the AI ​​summarizes all the extracted information and generates a concise and easy-to-understand summary. The summarization unit optimizes the generation AI's summarization algorithm and performs summarization tailored to the characteristics of medical documents, enabling doctors and medical staff to quickly grasp the information. The summarized information is sent to the next step, the drafting department, where it is used to create the final document draft.

[0081] The creation unit creates drafts based on the information summarized by the summarization unit. For example, the creation unit creates drafts of "medical information provision reports" and "discharge summaries" based on the summarized information. Specifically, it uses a generation AI to create drafts based on the summarized information. The generation AI generates drafts according to the document structure and format based on the summarized information. For example, if the prompt "Create a draft of a medical information provision report" is entered into the generation AI, the AI ​​will create a draft according to the standard format of a medical information provision report, appropriately arranging information such as the diagnosis, treatment progress, and test results. Similarly, if the prompt "Create a draft of a discharge summary" is entered, the AI ​​will create a draft according to the standard format of a discharge summary, appropriately arranging information such as the patient's condition at discharge, treatment details, and future follow-up plan. Furthermore, if the prompt "Create a draft based on the summarized information" is entered, the AI ​​will create a draft of the specified document based on the summarized information. The creation unit optimizes the document generation algorithm of the generation AI and creates drafts tailored to the characteristics of medical documents, enabling doctors and medical staff to complete documents quickly. The created draft is sent to the next step, the review section, where it undergoes final verification and revisions.

[0082] The verification unit allows physicians to review drafts created by the creation unit. Specifically, the verification unit uses a generation AI to allow physicians to review the drafts. The generation AI analyzes the draft content, detects grammatical and terminological errors, and suggests revisions. For example, if the prompt "Please review the generated draft" is entered into the generation AI, the AI ​​checks the draft content and points out errors and inappropriate expressions. If the prompt "Please revise the generated draft" is entered, the AI ​​corrects the identified errors and suggests revisions. Furthermore, if the prompt "Please have the physician review the generated draft" is entered, the AI ​​analyzes the draft content and highlights points that the physician should review. The verification unit optimizes the generation AI's verification algorithm and performs verification work tailored to the characteristics of medical documents, enabling physicians and medical staff to quickly review and revise documents. This allows the verification unit to significantly reduce the time physicians spend creating documents and alleviate their workload. Finally, the reviewed documents are stored as official medical records and used to assist in patient care.

[0083] The medical record extraction unit extracts information from electronic medical records. For example, it can extract information such as the patient's diagnosis, treatment progress, and test results. The medical record extraction unit uses a generation AI to automatically extract the necessary information from the electronic medical records. For example, the medical record extraction unit can input a prompt to the generation AI, such as "Please extract the patient's diagnosis," and the generation AI will extract the diagnosis. The medical record extraction unit can also input a prompt to the generation AI, such as "Please extract the treatment progress," and the generation AI will extract the treatment progress. Furthermore, the medical record extraction unit can input a prompt to the generation AI, such as "Please extract the test results," and the generation AI will extract the test results. This allows for efficient information extraction from electronic medical records.

[0084] The issuing department issues summarized information as a document. For example, the issuing department can issue a "medical information provision form" or a "discharge summary" based on the summarized information. The issuing department can also issue summarized information as a document using a generative AI. For example, the issuing department can input the prompt "Please issue a medical information provision form" to the generative AI, and the generative AI will issue the medical information provision form. The issuing department can also input the prompt "Please issue a discharge summary" to the generative AI, and the generative AI will issue a discharge summary. Furthermore, the issuing department can input the prompt "Please issue a document based on the summarized information" to the generative AI, and the generative AI will issue a document. This allows for the rapid issuance of summarized information as a document.

[0085] The extraction unit can extract information such as the patient's diagnosis, treatment history, and test results. For example, the extraction unit can extract the patient's diagnosis. The extraction unit uses a generation AI to automatically extract the patient's diagnosis. For example, the extraction unit can input a prompt to the generation AI, "Please extract the patient's diagnosis," and the generation AI will extract the diagnosis. The extraction unit can also extract the treatment history. The extraction unit uses a generation AI to automatically extract the treatment history. For example, the extraction unit can input a prompt to the generation AI, "Please extract the treatment history," and the generation AI will extract the treatment history. Furthermore, the extraction unit can also extract test results. The extraction unit uses a generation AI to automatically extract test results. For example, the extraction unit can input a prompt to the generation AI, "Please extract the test results," and the generation AI will extract the test results. This allows for the efficient extraction of information such as the patient's diagnosis, treatment history, and test results.

[0086] The summarization unit can create drafts of "medical information provision reports" and "discharge summaries" based on the extracted information. For example, the summarization unit can create a draft of a "medical information provision report" based on the extracted information. The summarization unit uses a generative AI to create drafts based on the extracted information. For example, the summarization unit can input a prompt to the generative AI, such as "Please create a draft of a medical information provision report," and the generative AI will create the draft. The summarization unit can also create drafts of "discharge summaries." The summarization unit uses a generative AI to create drafts based on the extracted information. For example, the summarization unit can input a prompt to the generative AI, such as "Please create a draft of a discharge summary," and the generative AI will create the draft. Furthermore, the summarization unit can also create drafts based on the extracted information. The summarization unit uses a generative AI to create drafts based on the extracted information. For example, the summarization unit can input a prompt to the generative AI, such as "Please create a draft based on the extracted information," and the generative AI will create the draft. This allows for efficient draft creation based on the extracted information.

[0087] The review unit allows physicians to review the generated draft. For example, the review unit allows physicians to review the generated draft and make corrections as needed. The review unit can also use a generation AI to allow physicians to review the generated draft. For example, the review unit can input a prompt to the generation AI such as "Please review the generated draft," and the generation AI will review the draft. The review unit can also input a prompt to the generation AI such as "Please revise the generated draft," and the generation AI will revise the draft. Furthermore, the review unit can input a prompt to the generation AI such as "Please have the physician review the generated draft," and the generation AI will review the draft. This ensures the accuracy of the document by allowing physicians to review the generated draft.

[0088] The extraction unit can estimate the doctor's emotions and adjust the timing of information extraction based on the estimated emotions. For example, if the doctor is tired, the extraction unit will adjust the timing to extract information during break times. The extraction unit uses a generation AI to estimate the doctor's emotions and adjust the timing of information extraction. For example, the extraction unit can input a prompt to the generation AI such as "Estimate the doctor's emotions," and the generation AI will estimate the doctor's emotions. The extraction unit can also input a prompt to the generation AI such as "Adjust the timing of information extraction based on the doctor's emotions," and the generation AI will adjust the timing of information extraction. Furthermore, the extraction unit can input a prompt to the generation AI such as "If the doctor is tired, extract information during break times," and the generation AI will adjust the timing of information extraction. This allows for efficient information extraction by adjusting the timing of information extraction according to the doctor's emotions.

[0089] The extraction unit can analyze a patient's medical history and select the optimal information extraction method. For example, the extraction unit can prioritize extracting highly relevant information based on the patient's past medical history. The extraction unit uses a generating AI to analyze the patient's medical history and select the optimal information extraction method. For example, the extraction unit can input a prompt to the generating AI, such as "Please analyze the patient's medical history," and the generating AI will analyze the medical history. Alternatively, the extraction unit can input a prompt to the generating AI, such as "Please select the optimal information extraction method," and the generating AI will select an information extraction method. Furthermore, the extraction unit can input a prompt to the generating AI, such as "Please prioritize extracting highly relevant information based on the patient's past medical history," and the generating AI will select an information extraction method. In this way, the optimal information extraction method can be selected by analyzing the patient's medical history.

[0090] The extraction unit can filter information based on the patient's current medical condition and treatment plan during the information extraction process. For example, the extraction unit can extract only relevant information based on the patient's current medical condition. The extraction unit uses a generation AI to perform filtering based on the patient's current medical condition and treatment plan. For example, the extraction unit can input a prompt to the generation AI saying, "Please filter the information based on the patient's current medical condition," and the generation AI will filter the information. Alternatively, the extraction unit can input a prompt to the generation AI saying, "Please filter the information based on the patient's treatment plan," and the generation AI will filter the information. Furthermore, the extraction unit can input a prompt to the generation AI saying, "Please filter based on the patient's current medical condition and treatment plan," and the generation AI will filter the information. This allows for the extraction of only relevant information by filtering based on the patient's current medical condition and treatment plan.

[0091] The extraction unit can estimate the doctor's emotions and determine the priority of information to extract based on the estimated emotions. For example, if the doctor is tired, the extraction unit will prioritize extracting important information. The extraction unit uses a generative AI to estimate the doctor's emotions and determine the priority of information. For example, the extraction unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The extraction unit can also input a prompt to the generative AI such as "Determine the priority of information based on the doctor's emotions," and the generative AI will determine the priority of information. Furthermore, the extraction unit can input a prompt to the generative AI such as "If the doctor is tired, prioritize extracting important information," and the generative AI will determine the priority of information. This enables efficient information extraction by determining the priority of information to extract according to the doctor's emotions.

[0092] The extraction unit can prioritize extracting highly relevant information by considering the patient's geographical location during information extraction. For example, the extraction unit can extract region-specific information based on the patient's place of residence. The extraction unit uses a generation AI to extract information while considering the patient's geographical location. For example, the extraction unit can input a prompt to the generation AI saying, "Please extract information based on the patient's geographical location," and the generation AI will extract the information. Alternatively, the extraction unit can input a prompt to the generation AI saying, "Please extract information based on the patient's place of residence," and the generation AI will extract the information. Furthermore, the extraction unit can input a prompt to the generation AI saying, "Please prioritize extracting highly relevant information by considering the patient's geographical location," and the generation AI will extract the information. This allows for the priority extraction of highly relevant information by considering the patient's geographical location.

[0093] The extraction unit can analyze a patient's social media activity and extract relevant information during information extraction. For example, the extraction unit can extract information about a patient's health status from their social media posts. The extraction unit uses a generative AI to analyze the patient's social media activity and extract information. For example, the extraction unit can input a prompt to the generative AI such as "Analyze the patient's social media activity," and the generative AI will analyze the social media activity. The extraction unit can also input a prompt to the generative AI such as "Extract information from the patient's social media posts," and the generative AI will extract the information. Furthermore, the extraction unit can input a prompt to the generative AI such as "Extract relevant information based on the patient's social media activity," and the generative AI will extract the information. This allows for the efficient extraction of relevant information by analyzing the patient's social media activity.

[0094] The summarization unit can estimate the doctor's emotions and adjust the way the summary is presented based on those emotions. For example, if the doctor is tired, the summarization unit will provide a concise and to-the-point summary. The summarization unit uses generative AI to estimate the doctor's emotions and adjust the way the summary is presented. For example, the summarization unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The summarization unit can also input a prompt to the generative AI such as "Adjust the way the summary is presented based on the doctor's emotions," and the generative AI will adjust the way the summary is presented. Furthermore, the summarization unit can input a prompt to the generative AI such as "If the doctor is tired, provide a concise and to-the-point summary," and the generative AI will adjust the way the summary is presented. This allows for efficient summarization by adjusting the way the summary is presented according to the doctor's emotions.

[0095] The summarization unit can adjust the level of detail in a summary based on the importance of the information during the summarization process. For example, the summarization unit prioritizes summarizing important information and includes it in detail. The summarization unit uses a generation AI to adjust the level of detail in the summary based on the importance of the information. For example, the summarization unit can input a prompt to the generation AI such as "Please evaluate the importance of the information," and the generation AI will evaluate the importance of the information. The summarization unit can also input a prompt to the generation AI such as "Please prioritize summarizing important information," and the generation AI will adjust the level of detail in the summary. Furthermore, the summarization unit can input a prompt to the generation AI such as "Please adjust the level of detail in the summary based on the importance of the information," and the generation AI will adjust the level of detail in the summary. This allows for efficient summarization by adjusting the level of detail in the summary based on the importance of the information.

[0096] The summarization unit can apply different summarization algorithms depending on the information category when generating summaries. For example, the summarization unit applies a diagnostic-specific summarization algorithm to diagnostic information. The summarization unit uses a generation AI to apply summarization algorithms according to the information category. For example, the summarization unit can input a prompt to the generation AI, "Summarize the diagnostic information," and the generation AI will summarize the diagnostic information. The summarization unit can also input a prompt to the generation AI, "Summarize the treatment progress," and the generation AI will summarize the treatment progress. Furthermore, the summarization unit can input a prompt to the generation AI, "Apply a summarization algorithm according to the information category," and the generation AI will apply a summarization algorithm. This allows for efficient summarization by applying different summarization algorithms depending on the information category.

[0097] The summarization unit can estimate the doctor's emotions and adjust the length of the summary based on the estimated emotions. For example, if the doctor is tired, the summarization unit will provide a short, concise summary. The summarization unit uses generative AI to estimate the doctor's emotions and adjust the length of the summary. For example, the summarization unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The summarization unit can also input a prompt to the generative AI such as "Adjust the length of the summary based on the doctor's emotions," and the generative AI will adjust the length of the summary. Furthermore, the summarization unit can input a prompt to the generative AI such as "If the doctor is tired, provide a short, concise summary," and the generative AI will adjust the length of the summary. This allows for efficient summarization by adjusting the length of the summary according to the doctor's emotions.

[0098] The summarization unit can prioritize summaries based on when the information was submitted. For example, the summarization unit prioritizes summarizing information with high urgency. The summarization unit uses a generation AI to determine the priority of summaries based on when the information was submitted. For example, the summarization unit can input a prompt to the generation AI such as "Please evaluate the submission timing of the information," and the generation AI will evaluate the submission timing. The summarization unit can also input a prompt to the generation AI such as "Please prioritize summarizing information with high urgency," and the generation AI will determine the priority of summaries. Furthermore, the summarization unit can input a prompt to the generation AI such as "Please determine the priority of summaries based on when the information was submitted," and the generation AI will determine the priority of summaries. This enables efficient summarization by prioritizing summaries based on when the information was submitted.

[0099] The summarization unit can adjust the order of summaries based on the relevance of the information during the summarization process. For example, the summarization unit prioritizes summarizing highly relevant information. The summarization unit uses a generation AI to adjust the order of summaries based on the relevance of the information. For example, the summarization unit can input a prompt to the generation AI such as "Please evaluate the relevance of the information," and the generation AI will evaluate the relevance of the information. The summarization unit can also input a prompt to the generation AI such as "Please prioritize summarizing highly relevant information," and the generation AI will adjust the order of the summaries. Furthermore, the summarization unit can input a prompt to the generation AI such as "Please adjust the order of summaries based on the relevance of the information," and the generation AI will adjust the order of the summaries. This allows for efficient summarization by adjusting the order of summaries based on the relevance of the information.

[0100] The drafting unit can estimate the doctor's emotions and adjust the draft's presentation based on those emotions. For example, if the doctor is tired, the unit will provide a concise and to-the-point draft. The drafting unit uses generative AI to estimate the doctor's emotions and adjust the draft's presentation. For example, the drafting unit can input a prompt to the generative AI such as "Estimate the doctor's emotions," and the generative AI will estimate the doctor's emotions. The drafting unit can also input a prompt to the generative AI such as "Adjust the draft's presentation based on the doctor's emotions," and the generative AI will adjust the draft's presentation. Furthermore, the drafting unit can input a prompt to the generative AI such as "If the doctor is tired, provide a concise and to-the-point draft," and the generative AI will adjust the draft's presentation. This allows for efficient draft creation by adjusting the draft's presentation according to the doctor's emotions.

[0101] The drafting unit can adjust the level of detail of a draft based on the importance of the information during the drafting process. For example, the unit prioritizes including important information in the draft. The unit uses a generative AI to adjust the level of detail of the draft based on the importance of the information. For example, the unit can input a prompt to the generative AI such as "Please evaluate the importance of the information," and the generative AI will evaluate the importance of the information. The unit can also input a prompt to the generative AI such as "Please prioritize including important information in the draft," and the generative AI will adjust the level of detail of the draft. Furthermore, the unit can input a prompt to the generative AI such as "Please adjust the level of detail of the draft based on the importance of the information," and the generative AI will adjust the level of detail of the draft. This allows for efficient drafting by adjusting the level of detail of the draft based on the importance of the information.

[0102] The drafting unit can apply different drafting algorithms depending on the information category during draft creation. For example, the unit applies a diagnostic-specific drafting algorithm to diagnostic information. The unit uses a generative AI to apply drafting algorithms according to the information category. For example, the unit can input a prompt to the generative AI, "Please include diagnostic information in the draft," and the generative AI will include the diagnostic information in the draft. The unit can also input a prompt to the generative AI, "Please include treatment progress in the draft," and the generative AI will include treatment progress in the draft. Furthermore, the unit can input a prompt to the generative AI, "Please apply a drafting algorithm according to the information category," and the generative AI will apply a drafting algorithm. This allows for efficient draft creation by applying different drafting algorithms according to the information category.

[0103] The drafting unit can estimate the doctor's emotions and adjust the length of the draft based on the estimated emotions. For example, if the doctor is tired, the drafting unit will provide a short, concise draft. The drafting unit uses generative AI to estimate the doctor's emotions and adjust the length of the draft. For example, the drafting unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The drafting unit can also input the prompt "Adjust the length of the draft based on the doctor's emotions" to the generative AI, and the generative AI will adjust the length of the draft. Furthermore, the drafting unit can input the prompt "If the doctor is tired, provide a short, concise draft" to the generative AI, and the generative AI will adjust the length of the draft. This allows for efficient draft creation by adjusting the length of the draft according to the doctor's emotions.

[0104] The drafting team can determine the priority of drafts based on the timing of information submission when creating a draft. For example, the team can prioritize including information with high urgency in the draft. The team uses a generative AI to determine the priority of drafts based on the timing of information submission. For example, the team can input a prompt to the generative AI saying, "Please evaluate the timing of information submission," and the generative AI will evaluate the timing of information submission. The team can also input a prompt to the generative AI saying, "Please prioritize including information with high urgency in the draft," and the generative AI will determine the priority of the draft. Furthermore, the team can input a prompt to the generative AI saying, "Please determine the priority of drafts based on the timing of information submission," and the generative AI will determine the priority of the draft. This enables efficient draft creation by determining the priority of drafts based on the timing of information submission.

[0105] The drafting unit can adjust the order of information in the draft based on its relevance. For example, the unit prioritizes including highly relevant information in the draft. The unit uses a generative AI to adjust the order of information based on its relevance. For example, the unit can input a prompt to the generative AI such as "Please evaluate the relevance of the information," and the generative AI will evaluate the relevance of the information. The unit can also input a prompt to the generative AI such as "Please prioritize including highly relevant information in the draft," and the generative AI will adjust the order of the draft. Furthermore, the unit can input a prompt to the generative AI such as "Please adjust the order of the draft based on the relevance of the information," and the generative AI will adjust the order of the draft. This allows for efficient drafting by adjusting the order of information based on its relevance.

[0106] The verification unit can estimate the doctor's emotions and adjust the timing of the verification based on the estimated emotions. For example, if the doctor is tired, the verification unit will adjust the timing to perform the verification during their break. The verification unit uses generative AI to estimate the doctor's emotions and adjust the timing of the verification. For example, the verification unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The verification unit can also input the prompt "Adjust the timing of the verification based on the doctor's emotions" to the generative AI, and the generative AI will adjust the timing of the verification. Furthermore, the verification unit can input the prompt "If the doctor is tired, perform the verification during their break" to the generative AI, and the generative AI will adjust the timing of the verification. This allows for more efficient verification by adjusting the timing of the verification according to the doctor's emotions.

[0107] The verification unit can select the optimal verification method by referring to past verification history during the verification process. For example, the verification unit can propose the optimal verification method based on past verification history. The verification unit uses a generation AI to refer to past verification history and select a verification method. For example, the verification unit can input the prompt "Please refer to past verification history" to the generation AI, and the generation AI will refer to the verification history. Alternatively, the verification unit can input the prompt "Please select the optimal verification method" to the generation AI, and the generation AI will select a verification method. Furthermore, the verification unit can input the prompt "Please propose the optimal verification method based on past verification history" to the generation AI, and the generation AI will select a verification method. In this way, the optimal verification method can be selected by referring to past verification history.

[0108] The verification unit can estimate the doctor's emotions and determine the priority of verifications based on the estimated emotions. For example, if the doctor is tired, the verification unit will prioritize important verifications. The verification unit uses generative AI to estimate the doctor's emotions and determine the priority of verifications. For example, the verification unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The verification unit can also input the prompt "Determine the priority of verifications based on the doctor's emotions" to the generative AI, and the generative AI will determine the priority of verifications. Furthermore, the verification unit can input the prompt "If the doctor is tired, please prioritize important verifications" to the generative AI, and the generative AI will determine the priority of verifications. This allows for more efficient verifications by determining the priority of verifications according to the doctor's emotions.

[0109] The verification unit can select the optimal verification method by considering the physician's device information during verification. For example, if the physician is using a smartphone, the verification unit will provide a verification method that matches the screen size. The verification unit uses a generation AI to select a verification method that considers the physician's device information. For example, the verification unit can input a prompt to the generation AI saying, "Please consider the physician's device information," and the generation AI will take the device information into account. The verification unit can also input a prompt to the generation AI saying, "Please select the optimal verification method," and the generation AI will select a verification method. Furthermore, the verification unit can input a prompt to the generation AI saying, "If the physician is using a smartphone, please provide a verification method that matches the screen size," and the generation AI will select a verification method. In this way, the optimal verification method can be selected by considering the physician's device information.

[0110] The medical record extraction unit can estimate the doctor's emotions and adjust the timing of medical record extraction based on the estimated emotions. For example, if the doctor is tired, the medical record extraction unit will adjust the extraction timing to coincide with the doctor's break time. The medical record extraction unit uses a generation AI to estimate the doctor's emotions and adjust the timing of medical record extraction. For example, the medical record extraction unit can input a prompt to the generation AI such as "Estimate the doctor's emotions," and the generation AI will estimate the doctor's emotions. The medical record extraction unit can also input a prompt to the generation AI such as "Adjust the timing of medical record extraction based on the doctor's emotions," and the generation AI will adjust the timing of medical record extraction. Furthermore, the medical record extraction unit can input a prompt to the generation AI such as "If the doctor is tired, extract the medical record during their break time," and the generation AI will adjust the timing of medical record extraction. This allows for efficient medical record extraction by adjusting the timing of medical record extraction according to the doctor's emotions.

[0111] The medical record extraction unit can analyze the patient's medical history and select the optimal extraction method during medical record extraction. For example, the medical record extraction unit prioritizes extracting highly relevant information based on the patient's past medical history. The medical record extraction unit uses a generating AI to analyze the patient's medical history and select the extraction method. For example, the medical record extraction unit can input a prompt to the generating AI, such as "Please analyze the patient's medical history," and the generating AI will analyze the medical history. Alternatively, the medical record extraction unit can input a prompt to the generating AI, such as "Please select the optimal extraction method," and the generating AI will select the extraction method. Furthermore, the medical record extraction unit can input a prompt to the generating AI, such as "Please prioritize extracting highly relevant information based on the patient's past medical history," and the generating AI will select the extraction method. In this way, the optimal medical record extraction method can be selected by analyzing the patient's medical history.

[0112] The medical record extraction unit can estimate the doctor's emotions and determine the priority of medical record extraction based on the estimated emotions. For example, if the doctor is tired, the medical record extraction unit will prioritize the extraction of important information. The medical record extraction unit uses a generation AI to estimate the doctor's emotions and determine the priority of medical record extraction. For example, the medical record extraction unit can input a prompt to the generation AI such as "Estimate the doctor's emotions," and the generation AI will estimate the doctor's emotions. The medical record extraction unit can also input a prompt to the generation AI such as "Determine the priority of medical record extraction based on the doctor's emotions," and the generation AI will determine the priority of medical record extraction. Furthermore, the medical record extraction unit can input a prompt to the generation AI such as "If the doctor is tired, prioritize the extraction of important information," and the generation AI will determine the priority of medical record extraction. This enables efficient medical record extraction by determining the priority of medical record extraction according to the doctor's emotions.

[0113] The medical record extraction unit can prioritize the extraction of highly relevant information by considering the patient's geographical location during medical record extraction. For example, the medical record extraction unit can extract region-specific information based on the patient's place of residence. The medical record extraction unit uses a generation AI to extract information while considering the patient's geographical location. For example, the medical record extraction unit can input a prompt to the generation AI saying, "Please extract information based on the patient's geographical location," and the generation AI will extract the information. Alternatively, the medical record extraction unit can input a prompt to the generation AI saying, "Please prioritize the extraction of highly relevant information by considering the patient's geographical location," and the generation AI will extract the information. In this way, by considering the patient's geographical location, highly relevant information can be prioritized for extraction.

[0114] The issuing unit can estimate the doctor's emotions and adjust the timing of document issuance based on the estimated emotions. For example, if the doctor is tired, the issuing unit can adjust the timing to issue the document during their break. The issuing unit uses generative AI to estimate the doctor's emotions and adjust the timing of document issuance. For example, the issuing unit can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The issuing unit can also input the prompt "Adjust the timing of document issuance based on the doctor's emotions" to the generative AI, and the generative AI will adjust the timing of document issuance. Furthermore, the issuing unit can input the prompt "If the doctor is tired, issue the document during their break" to the generative AI, and the generative AI will adjust the timing of document issuance. This allows for efficient document issuance by adjusting the timing of document issuance according to the doctor's emotions.

[0115] The issuing department can select the optimal issuing method by referring to past issuing history at the time of issuance. For example, the issuing department can propose the optimal issuing method based on past issuing history. The issuing department uses a generation AI to refer to past issuing history and select an issuing method. For example, the issuing department can input the prompt "Please refer to past issuing history" to the generation AI, and the generation AI will refer to the issuing history. Alternatively, the issuing department can input the prompt "Please select the optimal issuing method" to the generation AI, and the generation AI will select an issuing method. Furthermore, the issuing department can input the prompt "Please propose the optimal issuing method based on past issuing history" to the generation AI, and the generation AI will select an issuing method. In this way, the optimal issuing method can be selected by referring to past issuing history.

[0116] The issuing department can estimate a doctor's emotions and determine the priority of issuance based on that estimation. For example, if a doctor is tired, the issuing department will prioritize issuing important documents. The issuing department uses generative AI to estimate a doctor's emotions and determine the priority of issuance. For example, the issuing department can input the prompt "Estimate the doctor's emotions" to the generative AI, and the generative AI will estimate the doctor's emotions. The issuing department can also input the prompt "Determine the priority of issuance based on the doctor's emotions" to the generative AI, and the generative AI will determine the priority of issuance. Furthermore, the issuing department can input the prompt "If the doctor is tired, prioritize issuing important documents" to the generative AI, and the generative AI will determine the priority of issuance. This enables efficient document issuance by determining the priority of issuance according to the doctor's emotions.

[0117] The issuing unit can select the optimal issuing method when issuing documents, taking into account the physician's device information. For example, if the physician is using a smartphone, the issuing unit will provide an issuing method that matches the screen size. The issuing unit uses a generation AI to select an issuing method that takes the physician's device information into account. For example, the issuing unit can input a prompt to the generation AI saying, "Please consider the physician's device information," and the generation AI will take the device information into account. The issuing unit can also input a prompt to the generation AI saying, "Please select the optimal issuing method," and the generation AI will select an issuing method. Furthermore, the issuing unit can input a prompt to the generation AI saying, "If the physician is using a smartphone, please provide an issuing method that matches the screen size," and the generation AI will select an issuing method. In this way, the optimal issuing method can be selected by taking the physician's device information into account.

[0118] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0119] The document creation support system can also be equipped with a voice input unit. The voice input unit allows doctors to give instructions by voice, and uses speech recognition technology to convert the instructions into text. For example, if a doctor gives the voice instruction, "Extract the patient's diagnosis," the voice input unit converts the instruction into text and sends it to the extraction unit. Also, if a doctor gives the voice input unit, "Create a discharge summary," the voice input unit sends the instruction to the summarization unit, which can create a draft of the discharge summary. Furthermore, if a doctor gives the voice input unit, "Review this draft," the voice input unit sends the instruction to the review unit, which can review the draft. This allows doctors to give instructions by voice without using their hands, improving work efficiency.

[0120] The document creation support system can also include a translation function. This function can translate the created documents into multiple languages. For example, it can translate a medical information report into English. It can also translate a discharge summary into Spanish. Furthermore, the translation function can automatically translate the content of documents using a generative AI. For example, the translation function can input a prompt to the generative AI, such as "Translate this document into English," and the generative AI can translate the document into English. This allows documents to be shared even among international healthcare institutions.

[0121] The document creation support system can also be equipped with an image analysis unit. The image analysis unit can analyze image data contained in electronic medical records and extract necessary information. For example, it can identify abnormal areas from a patient's X-ray image and extract that information. The image analysis unit can also identify the location of a tumor from an MRI image and extract that information. Furthermore, the image analysis unit can analyze image data and extract necessary information using a generation AI. For example, the image analysis unit can input a prompt to the generation AI such as "Identify abnormal areas from this X-ray image," and the generation AI can identify the abnormal areas. This allows for efficient information extraction from image data.

[0122] The document creation support system can also be equipped with a database integration unit. This unit can integrate with other medical databases to retrieve necessary information. For example, it can retrieve a patient's past medical history from another medical institution's database. Furthermore, the database integration unit can retrieve drug information from a drug information database. Additionally, the database integration unit can use a generation AI to integrate with other databases and retrieve necessary information. For example, the database integration unit can input a prompt to the generation AI such as, "Please retrieve the patient's medical history from another medical institution's database," and the generation AI can retrieve the medical history. This allows for the retrieval of more information by integrating with other databases.

[0123] The document creation support system can also be equipped with an alert notification unit. This unit can notify a physician when important information is extracted. For example, it can send an alert to a physician if there is an abnormality in a patient's test results. It can also notify a physician if a patient's condition suddenly changes. Furthermore, the alert notification unit can use a generation AI to detect important information and notify a physician. For example, the alert notification unit can input a prompt to the generation AI such as "Detect important information," and the generation AI can detect the important information and notify the physician. This allows important information to be quickly conveyed to the physician.

[0124] The document creation support system can further adjust the tone of a document based on the doctor's emotions using an emotion estimation function. For example, if the doctor is tired, the tone of the document can be softened. Similarly, if the doctor is stressed, the tone can be calmed. Furthermore, by using the emotion estimation function to adjust the tone of the document based on the doctor's emotions, the system can estimate the doctor's feelings and adjust the tone accordingly. This allows for a reduction in the doctor's burden by adjusting the tone of the document according to their emotions.

[0125] The document creation support system can further adjust the document content based on the doctor's emotions using an emotion estimation function. For example, if the doctor is tired, the document content can be made more concise. Similarly, if the doctor is stressed, the document content can be narrowed down to only the essential points. Furthermore, by using the emotion estimation function to adjust the document content based on the doctor's emotions, the burden on the doctor can be reduced.

[0126] The document creation support system can further adjust the document layout based on the doctor's emotions using an emotion estimation function. For example, if the doctor is tired, the document layout can be simplified. Conversely, if the doctor is stressed, the document layout can be made easier to read. Furthermore, by using the emotion estimation function to adjust the document layout based on the doctor's emotions, the burden on the doctor can be reduced.

[0127] The document creation support system can further adjust the font size of a document based on the doctor's emotions using an emotion estimation function. For example, if the doctor is tired, the font size can be increased. Also, if the doctor is stressed, the font size can be made easier to read. Furthermore, by using the emotion estimation function to adjust the font size based on the doctor's emotions, the system can estimate the doctor's emotions and adjust the font size accordingly. This reduces the burden on the doctor by adjusting the font size according to their emotions.

[0128] The document creation support system can further adjust the document's color scheme based on the doctor's emotions using an emotion estimation function. For example, if the doctor is tired, the document's color scheme can be changed to a calmer tone. Similarly, if the doctor is stressed, the document's color scheme can be changed to a softer tone. Furthermore, by using the emotion estimation function to adjust the document's color scheme based on the doctor's emotions, the system can estimate the doctor's emotions and adjust the document's color scheme accordingly. This allows the system to reduce the doctor's burden by adjusting the document's color scheme according to their emotions.

[0129] The following briefly describes the processing flow for example form 2.

[0130] Step 1: The extraction unit extracts information from the electronic medical record. For example, it extracts information such as the patient's diagnosis, treatment progress, and test results. The extraction unit uses a generation AI to automatically extract the necessary information from the electronic medical record. Specifically, prompts such as "Please extract the patient's diagnosis" or "Please extract the treatment progress" are input to the generation AI, and the generation AI extracts the corresponding information. Step 2: The summarization unit summarizes the information extracted by the extraction unit. For example, it creates drafts of "medical information provision reports" and "discharge summaries" based on the extracted information. The summarization unit uses a generation AI to summarize the extracted information. Specifically, prompts such as "Please create a draft of a medical information provision report" or "Please create a draft of a discharge summary" are input to the generation AI, and the generation AI creates the drafts. Step 3: The creation unit creates a draft based on the information summarized by the summarization unit. For example, it creates drafts of a "medical information provision report" and a "discharge summary" based on the summarized information. The creation unit uses a generation AI to create drafts based on the summarized information. Specifically, prompts such as "Please create a draft of the medical information provision report" or "Please create a draft of the discharge summary" are input to the generation AI, and the generation AI creates the drafts. Step 4: The review unit has the physician review the draft created by the creation unit. For example, the physician reviews the created draft and makes revisions as needed. The review unit uses a generation AI to have the physician review the created draft. Specifically, prompts such as "Please review the created draft" or "Please revise the created draft" are input to the generation AI, and the generation AI reviews or revises the draft.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the extraction unit, summarization unit, creation unit, and verification unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the extraction unit is implemented by the control unit 46A of the smart device 14 and extracts information from the electronic medical record. The summarization unit is implemented by the specific processing unit 290 of the data processing device 12 and summarizes the extracted information. The creation unit is implemented by the control unit 46A of the smart device 14 and creates a draft based on the summarized information. The verification unit is implemented by the specific processing unit 290 of the data processing device 12 and the physician verifies the created draft. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0135] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the extraction unit, summarization unit, creation unit, and verification unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the extraction unit is implemented by the control unit 46A of the smart glasses 214 and extracts information from the electronic medical record. The summarization unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and summarizes the extracted information. The creation unit is implemented, for example, by the control unit 46A of the smart glasses 214 and creates a draft based on the summarized information. The verification unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and the physician verifies the created draft. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0151] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the extraction unit, summarization unit, creation unit, and verification unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the extraction unit is implemented by the control unit 46A of the headset terminal 314 and extracts information from the electronic medical record. The summarization unit is implemented by the specific processing unit 290 of the data processing device 12 and summarizes the extracted information. The creation unit is implemented by the control unit 46A of the headset terminal 314 and creates a draft based on the summarized information. The verification unit is implemented by the specific processing unit 290 of the data processing device 12 and the physician verifies the created draft. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0167] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.).

[0180] 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.

[0181] 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.

[0182] 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.

[0183] Each of the multiple elements described above, including the extraction unit, summarization unit, creation unit, and verification unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the robot 414 and extracts information from the electronic medical record. The summarization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and summarizes the extracted information. The creation unit is implemented by, for example, the control unit 46A of the robot 414 and creates a draft based on the summarized information. The verification unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and the physician verifies the created draft. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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."

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] (Note 1) An extraction unit that extracts information from electronic medical records, A summarization unit that summarizes the information extracted by the extraction unit, A drafting unit that creates a draft based on the information summarized by the summarizing unit, The system includes a confirmation unit for a physician to review the draft created by the creation unit. A system characterized by the following features. (Note 2) It is equipped with a medical record extraction unit that extracts information from electronic medical records. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a publishing unit that issues summarized information as a document. The system described in Appendix 1, characterized by the features described herein. (Note 4) The extraction unit is Extract information such as the patient's diagnosis, treatment history, and test results. The system described in Appendix 1, characterized by the features described herein. (Note 5) The summary section above is, Based on the extracted information, drafts of "Medical Information Provision Forms" and "Discharge Summaries" are created. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned verification unit is The doctor reviews the draft that was created. The system described in Appendix 1, characterized by the features described herein. (Note 7) The extraction unit is The system estimates the doctor's emotions and adjusts the timing of information extraction based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The extraction unit is Analyze the patient's medical history and select the optimal method for extracting information. The system described in Appendix 1, characterized by the features described herein. (Note 9) The extraction unit is During information extraction, filtering is performed based on the patient's current medical condition and treatment plan. The system described in Appendix 1, characterized by the features described herein. (Note 10) The extraction unit is The system estimates the doctor's emotions and prioritizes the information to extract based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The extraction unit is When extracting information, the system prioritizes extracting highly relevant information by considering the patient's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The extraction unit is During information extraction, the patient's social media activity is analyzed to extract relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The summary section above is, The system estimates the doctor'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 14) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The summary section above is, Estimate the doctor's emotions and adjust the length of the summary based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The summary section above is, When generating summaries, prioritize summaries based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The summary section above is, When generating summaries, adjust the order of the summaries based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned creation unit, Estimate the doctor's emotions and adjust the wording of the draft based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned creation unit, When drafting, adjust the level of detail in the draft based on the importance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned creation unit, When creating a draft, different drafting algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned creation unit, Estimate the doctor's emotions and adjust the length of the draft based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned creation unit, When drafting, prioritize the drafts based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned creation unit, When creating a draft, adjust the order of the drafts based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned verification unit is The system estimates the doctor's emotions and adjusts the timing of follow-up based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned verification unit is During verification, the system will refer to past verification history to select the most suitable verification method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned verification unit is The system estimates the doctor's emotions and determines the priority of checks based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned verification unit is During verification, the optimal verification method will be selected, taking into account the physician's device information. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned medical record extraction unit is The system estimates the doctor's emotions and adjusts the timing of medical record extraction based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned medical record extraction unit is When extracting medical records, the patient's medical history is analyzed to select the optimal extraction method. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned medical record extraction unit is The system estimates the emotions of the doctors and determines the priority of medical record extraction based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned medical record extraction unit is When extracting medical records, the system prioritizes extracting highly relevant information by considering the patient's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned issuing department, We estimate the doctor's emotions and adjust the timing of document issuance based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned issuing department, When issuing, the optimal issuance method is selected by referring to past issuance history. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned issuing department, The system estimates the physician's emotions and determines the priority of issuance based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned issuing department, When issuing a document, the optimal issuance method is selected, taking into account the physician's device information. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0203] 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. An extraction unit that extracts information from electronic medical records, A summarization unit that summarizes the information extracted by the extraction unit, A drafting unit that creates a draft based on the information summarized by the summarizing unit, The system includes a confirmation unit for a physician to review the draft created by the creation unit. A system characterized by the following features.

2. It is equipped with a medical record extraction unit that extracts information from electronic medical records. The system according to feature 1.

3. It has a publishing unit that issues summarized information as a document. The system according to feature 1.

4. The extraction unit is Extract information such as the patient's diagnosis, treatment history, and test results. The system according to feature 1.

5. The summary section above is, Based on the extracted information, drafts of medical referral letters and discharge summaries are created. The system according to feature 1.

6. The aforementioned verification unit is The doctor reviews the draft that was created. The system according to feature 1.

Images