System

Abstract

To provide a system which automatically generates a medical information report or a discharge summary.SOLUTION: A system includes: means for extracting information of an electronic chart; means for storing the extracted information into a database; means for generating a prompt which instructs generation of a diagnosis information report or a discharge summary on the basis of stored information regarding a target patient and generating a diagnosis information report or a discharge summary for the target patient by using a generation AI model; and means for presenting the prepared diagnosis information report or discharge summary to a user who is a medical worker and receiving a modification.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Excessive work for doctors has become a social problem, and paperwork accounts for the majority of overtime work. In particular, the creation of "medical information reports" and "discharge summaries" is a simple text summary task, but doctors typically spend more than 30 minutes visually reviewing electronic medical records and cutting and pasting information to create them. [Means for solving the problem]

[0005] This invention is a system that contracts with medical institutions and provides a generative AI service that extracts information from electronic medical records and summarizes the content. This system reduces the burden of document preparation work on doctors and solves the problem of overwork. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 1, a 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.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0018] 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. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention contracts with medical institutions and provides a generation AI service that extracts information from electronic medical records and summarizes the contents. Specifically, it includes a means for extracting necessary information from electronic medical records, a generation AI means for summarizing the extracted information, and a means for providing the summarized contents.

[0029] "Example 2"

[0030] Generative AI is used to create medical information reports and discharge summaries. Specifically, it automatically generates medical information reports and discharge summaries based on information extracted from electronic medical records.

[0031] "Example 3"

[0032] This system is provided under contract with medical institutions. Specifically, based on the contract, it extracts and summarizes information from electronic medical records and provides the summary content. This reduces the burden of document preparation on doctors and solves the problem of overwork.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Sign a contract with the medical institution.

[0036] Step 2: Based on the contract, extract the necessary information from the electronic medical record.

[0037] Step 3: Input the extracted information into the generative AI to generate a summary.

[0038] Step 4: Provide the generated summary to the medical institution.

[0039] "Example 2"

[0040] Step 1: Extract the necessary information from the electronic medical record.

[0041] Step 2: The extracted information is input into the generation AI, and a medical information report and discharge summary are automatically generated.

[0042] Step 3: Provide the generated medical information report and discharge summary to the medical institution.

[0043] "Example 3"

[0044] Step 1: Sign a contract with the medical institution.

[0045] Step 2: Based on the contract, information is extracted from the electronic medical record, summarized, and the summary content is provided.

[0046] Step 3: This will reduce the burden of paperwork on doctors and solve the problem of overwork.

[0047] Example 1

[0048] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0049] Conventional medical institutions rely on electronic medical record systems to manage medical information, but it is difficult to quickly extract and summarize the necessary information from the vast amount of data. Furthermore, the manual task of summarizing information by medical professionals requires time and effort, hindering efficient medical care. Furthermore, because the quality of the summary depends on the skill of the medical professional, it is difficult to provide consistent, high-quality summaries.

[0050] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0051] In this invention, the server includes means for extracting information from electronic medical records, means for preprocessing the extracted information, means for inputting the preprocessed information into a generative AI model to generate a summary, and means for providing the generated summary content. This makes it possible to quickly and accurately extract necessary information from electronic medical records, automatically generate consistent, high-quality summaries using the generative AI model, and provide them to medical professionals.

[0052] An "electronic medical record" is a system that electronically records and manages patient medical information at medical institutions.

[0053] "Means for extracting information" refers to methods and techniques for obtaining necessary medical information from the electronic medical record system.

[0054] "Preprocessing means" refers to methods or techniques for analyzing the extracted information and converting it into a form suitable for generating summaries.

[0055] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to summarize input information.

[0056] A "means for generating a summary" is a method or technology for inputting preprocessed information into a generative AI model and generating a summary.

[0057] The "means for providing summary content" refers to a method or technology for providing the generated summary text to medical professionals.

[0058] "Medical institution" means a facility that provides medical services, such as a hospital, medical office, or clinic.

[0059] A "medical information report" is a document used to provide details of a patient's medical treatment to other medical institutions and medical professionals.

[0060] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient's care, and is created when the patient is discharged from the hospital.

[0061] MODE FOR CARRYING OUT THE INVENTION

[0062] This invention is a system that contracts with medical institutions and provides a generative AI service that extracts information from electronic medical records and summarizes the content. A specific embodiment of this system will be described below.

[0063] System configuration

[0064] The server has the following main functions:

[0065] 1. Information extraction from electronic medical records:

[0066] The server accesses the medical institution's electronic medical record system (e.g., EPIC, Cerner) and extracts necessary data such as patient medical information, test results, and prescription information.

[0067] Specifically, it uses an API to retrieve data from the electronic medical record system.

[0068] 2. Information preprocessing:

[0069] The server preprocesses the acquired medical information.

[0070] Specifically, the server analyzes the acquired data and extracts the necessary information (diagnosis name, test results, prescribed medications, etc.).

[0071] 3. Information summary generation:

[0072] The server inputs the preprocessed information into a generative AI model (e.g., OpenAI's GPT-4) to generate a summary.

[0073] The generative AI model uses natural language processing techniques to summarize the extracted information in a concise, easy-to-understand format.

[0074] 4. Providing Abstract Content:

[0075] The server transmits the generated summary to a terminal at the medical institution.

[0076] The terminal displays the summary to the medical professional.

[0077] Specific examples

[0078] Information extraction from electronic medical records:

[0079] The server retrieves patient A's medical records from the EPIC system via the API.

[0080] The data collected includes diagnosis, test results, and prescription medication information.

[0081] Information preprocessing:

[0082] The server extracts information such as "high blood pressure," "blood pressure measurement result 120 / 80 mmHg," and "losartan 50 mg" from the medical records.

[0083] Generate summary of information:

[0084] The server then feeds the extracted information into a GPT-4 model to generate a summary like this:

[0085] Prompt: "Please summarize the following medical record. Include diagnosis, test results, and prescription information."

[0086] Input data: "Patient A, October 1, 2023, hypertension, blood pressure measurement result 120 / 80 mmHg, losartan 50 mg once daily"

[0087] The generative AI model generates a summary sentence.

[0088] Example: "Patient A is being treated for hypertension diagnosed on October 1, 2023, with their most recent blood pressure reading of 120 / 80 mmHg. They are currently taking Losartan 50 mg once daily."

[0089] Summary content provided by:

[0090] The server transmits the generated summary to a terminal at the medical institution.

[0091] The terminal displays the summary for medical personnel to review.

[0092] In this way, the server extracts information from the electronic medical record, generates a summary using the generative AI model, and provides it to medical professionals via their devices, allowing them to quickly and accurately grasp the patient's medical information and provide efficient medical care.

[0093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0094] Step 1:

[0095] Information extraction from electronic medical records

[0096] The server accesses the medical institution's electronic medical record system. Specifically, the server uses the API key to authenticate to the electronic medical record system, and then sends an API request specifying the patient ID to retrieve the medical record. The input is the patient ID, and the output is the medical record data. The server saves the medical record received as an API response in its database.

[0097] Step 2:

[0098] Preprocessing of extracted information

[0099] The server runs a script to parse the stored medical records. Specifically, the server uses regular expressions and natural language processing techniques to extract necessary information such as diagnosis, test results, and prescription medications. The input is the medical record data, and the output is preprocessed information (diagnosis, test results, prescription medications, etc.).

[0100] Step 3:

[0101] Information summary generation

[0102] The server inputs the preprocessed information into the generative AI model. Specifically, the server converts the preprocessed information into JSON format and sends an API request to the generative AI model. The input is the preprocessed information, and the output is a generated summary. The generative AI model uses natural language processing technology to summarize the input information in a concise, easy-to-understand format.

[0103] Step 4:

[0104] Providing summary content

[0105] The server creates an API response to send the generated summary to the medical institution's terminal. Specifically, the server returns the generated summary to the terminal as an API response. The input is the generated summary, and the output is the API response to the terminal. The terminal executes code to display the received summary on a user interface, and displays the summary so that the medical professional can check it.

[0106] (Application example 1)

[0107] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0108] Conventional electronic medical records management in medical institutions contain a huge amount of information, making it difficult to quickly extract and summarize the necessary information. Furthermore, there was a lack of tools to understand the security status of patient data and take appropriate measures. This meant that medical institution security personnel could not perform their work efficiently, potentially increasing security risks.

[0109] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0110] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI summarizing the extracted information, means for providing the summarized content, means for generating a security report from the extracted information, and means for displaying the generated security report, which enables security personnel at medical institutions to quickly grasp the security status of patient data and take appropriate measures.

[0111] An "electronic medical record" is a system that electronically records and manages patient medical information at medical institutions.

[0112] "Means for extracting information" refers to techniques and methods for automatically extracting necessary information from electronic medical records.

[0113] "Generative AI" is a system that uses artificial intelligence technology to generate new information based on input data.

[0114] "Summarization methods" are techniques or methods for concisely summarizing extracted information.

[0115] "Means of delivery" refers to the technology or method used to display or deliver the summarized information to the user.

[0116] A "security report" is a document that evaluates and reports the security status of patient data based on extracted information.

[0117] "Displaying means" refers to the technology or method for presenting the generated security report in a form that can be viewed by a user.

[0118] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The function of each element will be explained below.

[0119] server

[0120] The server extracts information from the electronic medical records, summarizes that information using generative AI, and generates a security report. Specifically, it performs the following processes:

[0121] 1. Information extraction from electronic medical records:

[0122] The server connects to the medical institution's electronic medical record system and obtains the necessary information through the API. To do this, it uses the requests library to send an HTTP request and obtain the electronic medical record data.

[0123] 2. Summary of information:

[0124] The extracted information is summarized using OpenAI's generative AI model (e.g., GPT-3 (registered trademark)), which extracts key information from the input medical data and generates a concise summary.

[0125] 3. Generate security reports:

[0126] The summarized information is formatted into a security report that assesses the security status of patient data and identifies necessary measures.

[0127] Terminal

[0128] The terminal is responsible for providing the generated security report to the user. Specifically, a device such as a smartphone or tablet is used.

[0129] 1. View the report:

[0130] The device receives the security report sent from the server and displays it in a format that can be viewed by the user, allowing the user to quickly understand the security situation and take necessary measures.

[0131] User

[0132] The user is a security officer at a medical institution, and is responsible for evaluating the security status of patient data based on the generated security report and taking appropriate measures.

[0133] Specific examples

[0134] For example, the following medical data is extracted from electronic medical records:

[0135] Patient ID: 12345

[0136] Medical Record: On October 1, 2023, the patient presented with a headache. An MRI scan confirmed a mild concussion. Prescriptions included pain medication and rest.

[0137] Based on this data, a generative AI model generates a summary like this:

[0138] Patient ID: 12345

[0139] Medical Record Summary: On October 1, 2023, the patient complained of a headache and was diagnosed with a mild concussion. Prescriptions included pain medication and rest.

[0140] Based on this summary, a security report is generated and displayed on the terminal, allowing the user to view the report and take necessary security measures.

[0141] In this way, the server, terminal, and user can work together to quickly and efficiently manage the security status of medical data.

[0142] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0143] Step 1:

[0144] The server connects to the medical institution's electronic medical record system and obtains the necessary information through the API. Specifically, it uses the requests library to send an HTTP request and obtain the electronic medical record data. The input is the API endpoint and authentication token, and the output is the raw data obtained from the electronic medical record.

[0145] Step 2:

[0146] The server formats the acquired raw data to input into the generative AI model. Specifically, it extracts the necessary information and generates prompt sentences. The input is raw data acquired from the electronic medical record, and the output is prompt sentences to input into the generative AI model.

[0147] Step 3:

[0148] The server uses a generative AI model (e.g., GPT-3) to generate a summary based on the prompt. Specifically, it calls the OpenAI API, sends the prompt, and retrieves the summary. The input is the prompt, and the output is the generated summary.

[0149] Step 4:

[0150] The server generates a security report based on the generated summary. Specifically, it applies the summary to a security assessment template to create a report. The input is the generated summary, and the output is the security report.

[0151] Step 5:

[0152] The server sends the generated security report to the terminal. Specifically, it sends the report as an HTTP response. The input is the security report, and the output is the report sent to the terminal.

[0153] Step 6:

[0154] The terminal displays the received security report to the user. Specifically, the report is displayed on the screen of a smartphone or tablet. The input is the security report sent from the server, and the output is the report displayed in a format that can be viewed by the user.

[0155] Step 7:

[0156] Based on the displayed security report, the user evaluates the security status of patient data and takes necessary measures. Specifically, the user checks the contents of the report and implements measures if there are any security risks. The input is the displayed security report, and the output is the security measures taken by the user.

[0157] Example 2

[0158] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] Traditionally, medical professionals have often manually created medical information forms and discharge summaries, which is time-consuming and labor-intensive. Manual input errors and information omissions can occur, creating a risk that patient medical information may not be accurately communicated. Furthermore, the process of extracting information from electronic medical records and generating documents is not automated, resulting in inefficiencies and increasing the burden on medical professionals.

[0160] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0161] In this invention, the server includes: means for extracting information from an electronic medical record; means for storing the extracted information in a database; means for generating a medical information report or discharge summary for the target patient using a prompt statement instructing the user to generate a medical information report or discharge summary based on the stored information about the target patient and a generative AI model; and means for presenting the generated medical information report or discharge summary to a user who is a medical professional and accepting revisions. This automates the process of creating medical information reports and discharge summaries, reducing the burden on medical professionals and enabling accurate and efficient information transmission. The generating means in the server saves the generated medical information report or discharge summary in PDF format or Word format, and the accepting means presents the medical information report or discharge summary saved in PDF format or Word format to the user who is a medical professional and accepting revisions. The extracting means in the server obtains diagnosis, treatment details, test results, and prescription drug data from the electronic medical record.

[0162] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0163] "Means for extracting information" refers to methods and techniques for obtaining necessary medical information from electronic medical records.

[0164] A "database" is a system for systematically storing and managing extracted information.

[0165] A "generative AI model" is a model that uses artificial intelligence to perform natural language processing and generate medical information reports and discharge summaries.

[0166] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[0167] A "medical information report" is a document used to provide a patient's medical information to other medical institutions and doctors.

[0168] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient's care, and is created when the patient is discharged from the hospital.

[0169] "PDF format" is an abbreviation for Portable Document Format, a file format for electronically storing and displaying documents.

[0170] "Word format" is a document file format created with Microsoft (registered trademark) Word.

[0171] A "terminal" is a device such as a computer or tablet used by a user.

[0172] "User" refers to a medical professional who uses this system to check and modify medical information reports and discharge summaries.

[0173] This invention is a system that extracts information from electronic medical records and automatically generates medical information reports and discharge summaries using a generative AI model. Specific embodiments of this system are described below.

[0174] The server accesses an electronic medical record system (e.g., a general electronic medical record system) and extracts the patient's medical information. Specifically, it uses an API to obtain data such as diagnosis, treatment details, test results, and prescribed medications. This data is then stored in a database (e.g., a general database system).

[0175] Next, the server retrieves the stored data and inputs it into a generative AI model (e.g., a general generative AI model). At this time, it generates a prompt sentence to give the model specific instructions. An example of a prompt sentence is the following format:

[0176] Please prepare a medical information form based on the patient's medical information below. <Patient medical information> Patient name: Taro Yamada Diagnosis: Hypertension Treatment: Administration of antihypertensive drugs Test results: Blood pressure 140 / 90 mmHg Prescription medication: Losartan 50mg

[0177] The generative AI model generates medical information reports and discharge summaries based on the input data. The generated documents are saved in PDF or Word format by the server, and then sent to a device (e.g., a standard computer or tablet).

[0178] The user can review the generated document through the terminal, make corrections or add additional information to the document as needed, and once corrections are complete, save the final document and print it if necessary.

[0179] This system automates the process of creating medical information forms and discharge summaries, reducing the burden on medical professionals and enabling accurate and efficient information transmission.

[0180] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0181] Step 1:

[0182] The server accesses the electronic medical record system and extracts the patient's medical information. Specifically, it uses an API to obtain data such as the diagnosis, treatment, test results, and prescribed medications. The input is the medical information from the electronic medical record system, and the output is the extracted medical information. The server obtains the required data by sending a request such as GET / api / patient / {patient_id} / records.

[0183] Step 2:

[0184] The server saves the extracted medical information in a database. The input is the extracted medical information, and the output is the information saved in the database. Specifically, it executes the following SQL query: INSERT INTO patient_records (patient_id, diagnosis, treatment, test_results, medications) VALUES (?, ?, ?, ?, ?).

[0185] Step 3:

[0186] The server retrieves the necessary data from the database and inputs it into the generative AI model. The input is the medical information retrieved from the database, and the output is the prompt statement to be input into the generative AI model. Specifically, it executes the SQL query SELECT diagnosis, treatment, test_results, medications FROM patient_records WHERE patient_id = ? and embeds the retrieved data into the prompt statement.

[0187] Step 4:

[0188] The server uses a generative AI model to generate medical information reports and discharge summaries. The input is a prompt and medical information, and the output is the generated document. The generative AI model is sent a prompt like this:

[0189] Please prepare a medical information form based on the patient's medical information below. <Patient medical information> Patient name: Taro Yamada Diagnosis: Hypertension Treatment: Administration of antihypertensive drugs Test results: Blood pressure 140 / 90 mmHg Prescription medication: Losartan 50mg

[0190] Step 5:

[0191] The server saves the generated document in PDF or Word format. The input is the generated document, and the output is a PDF or Word file. Specifically, a library (e.g., iText, Apache (registered trademark) POI) is used to generate the document and save it in the file system.

[0192] Step 6:

[0193] The server sends the generated document to the terminal. The input is a PDF or Word file, and the output is the document sent to the terminal. Specifically, the document is sent as an HTTP response, and the header Content-Disposition: attachment; filename="report.pdf" is set.

[0194] Step 7:

[0195] The user opens the received document on the terminal and checks its contents. The input is the document sent to the terminal and the output is the checked document. The user uses a text editor (e.g., a standard text editor) to enter corrections and additional information into the document as needed. Once corrections are complete, the user saves the final document and prints it if necessary.

[0196] (Application example 2)

[0197] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0198] In conventional medical systems, the task of extracting information from electronic medical records and creating medical information reports and discharge summaries is done manually, which is time-consuming and labor-intensive. Similarly, in security systems, the analysis of log data and video data and the creation of reports are done manually, making it difficult to respond quickly. To solve these problems, a system that automates information extraction, summarization, and report generation is needed.

[0199] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0200] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for extracting log data and video data collected from a security system, means for generating AI to summarize the extracted log data and video data, means for generating a security report based on the summarized log data and video data, and means for providing the generated security report. This not only enables the automatic generation of medical information notification forms and discharge summaries, but also enables the rapid generation and provision of security reports.

[0201] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0202] "Means for extracting information" refers to the technology and devices used to extract necessary data from electronic medical records and security systems.

[0203] "Generative AI" is a system that uses artificial intelligence technology to summarize data and automatically generate reports and documents.

[0204] A "summarization means" is a technique or device for concisely summarizing extracted information.

[0205] "Means of delivery" refers to the technology or device used to communicate the generated summary or report to the user.

[0206] A "security system" is a monitoring and defense mechanism for ensuring the safety of facilities and information systems.

[0207] "Log data" is data that records system operations and access history.

[0208] "Video data" refers to video information captured by a surveillance camera or the like.

[0209] A "security report" is a report prepared based on data collected from a security system.

[0210] To put the present invention into practice, it is necessary to build a system in which the elements of the server, terminal, and user work together. A specific embodiment of this system is shown below.

[0211] Server Roles

[0212] The server extracts information from electronic medical records and summarizes it using generative AI. It also extracts log data and video data collected from security systems and summarizes them to generate security reports. The server uses the following hardware and software:

[0213] Hardware: Powerful processor, ample memory, and storage

[0214] Software: Python, OpenAI API

[0215] Device Role

[0216] The terminal provides an interface for providing the generated summaries and reports to the user. The terminal is a mobile device such as a smartphone or tablet, and is designed for easy user access.

[0217] User Roles

[0218] Users check the summaries and reports provided through the terminal and take action as necessary. For example, medical institution staff check the medical information form and discharge summary and explain the situation to the patient. Security personnel also check the security report and take necessary measures.

[0219] Data processing and calculation

[0220] The server extracts data from electronic medical records and security systems and summarizes it using a generative AI model, which uses prompts like the following to input data:

[0221] Prompt Sentence Examples

[0222] Please create a security report using the following information:

[0223] Summary of log data:

[0224] 2023-10-01 12:00:00 - Unauthorized access detected

[0225] Video data summary:

[0226] 2023-10-01 12:05:00 - Suspicious person entered building

[0227] Based on this prompt, the generative AI model generates a security report, which is then provided to the user via their device.

[0228] Specific examples

[0229] For example, in medical institutions, generation AI can automatically generate medical information forms and discharge summaries based on patient medical information extracted from electronic medical records, reducing the burden on medical staff and enabling them to provide information quickly and accurately.

[0230] Additionally, security systems can detect suspicious activity from log data and video data and generate security reports summarizing the details, allowing security personnel to quickly take countermeasures.

[0231] In this way, the present invention automates the extraction, summarization, and provision of information in the medical and security fields, thereby realizing efficient business operations.

[0232] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0233] Step 1:

[0234] The server extracts information from the electronic medical record.

[0235] Input: Electronic medical record data

[0236] Output: Extracted medical information

[0237] Specific operation: The server accesses the electronic medical record system and obtains the patient's medical information, such as medical records, test results, and prescription information.

[0238] Step 2:

[0239] The server inputs the extracted medical information into a generative AI model to generate a summary.

[0240] Input: Extracted medical information

[0241] Output: Summarized medical information

[0242] Specific operation: The server creates a prompt for the generative AI model and instructs it to summarize the medical information. The generative AI model generates a medical information report and discharge summary based on the input information.

[0243] Step 3:

[0244] The server transmits the generated summary to the terminal.

[0245] Input: Summarized medical information

[0246] Output: Summary information sent to the terminal

[0247] Specific operation: The server sends the generated medical information report and discharge summary to the terminal so that medical staff can check them.

[0248] Step 4:

[0249] The server extracts log data and video data from the security system.

[0250] Input: Security system log data and video data

[0251] Output: Extracted log data and video data

[0252] Specific operation: The server accesses the security system and obtains log data and video data from surveillance cameras.

[0253] Step 5:

[0254] The server inputs the extracted log data and video data into a generative AI model to generate a summary.

[0255] Input: Extracted log data and video data

[0256] Output: Summarized log data and video data

[0257] Specific operation: The server creates prompts for the generative AI model and instructs it to summarize the log data and video data. The generative AI model then generates a security report based on the input information.

[0258] Step 6:

[0259] The server transmits the generated security report to the terminal.

[0260] Input: Summarized log data and video data

[0261] Output: Security report sent to the device

[0262] Specific operation: The server sends the generated security report to the terminal so that the security officer can check it.

[0263] Step 7:

[0264] The user checks the summary and report provided through the terminal and takes any necessary action.

[0265] Input: Summary information and security reports sent to the terminal

[0266] Output: User's response action

[0267] Specific operations: The user checks the medical information form, discharge summary, and security report displayed on the terminal, and provides explanations to the patient or takes security measures as necessary.

[0268] Example 3

[0269] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0270] In medical institutions, the burden of creating medical records is heavy for doctors, resulting in excessive work. In addition, creating medical information forms and discharge summaries requires a lot of time and effort, reducing the efficiency of doctors' work. This has led to problems such as a decline in the quality of medical care and fatigue among doctors.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0272] In this invention, the server includes means for extracting information from electronic medical records, means for storing the extracted information in a database, means for inputting the stored information into a generative AI model to generate a summary, and means for providing the generated summary to a user, thereby enabling doctors to quickly summarize medical records and efficiently create medical information reports and discharge summaries.

[0273] An "electronic medical record" is a system for electronically managing patient medical records.

[0274] "Means of extracting information" refers to the methods and techniques used to extract the necessary data from electronic medical records.

[0275] A "database" is a collection of data that stores information systematically and can be retrieved as needed.

[0276] A "generative AI model" is an algorithm or system that uses artificial intelligence to process data and perform summarization or generation.

[0277] A "means for generating a summary" is a method or technology that uses a generative AI model to concisely summarize extracted information.

[0278] "Means for providing to users" refers to methods and techniques for providing the generated summary to doctors and other medical professionals in an easy-to-view format.

[0279] A "medical information report" is a document used to communicate the details of a patient's medical treatment to other medical institutions and doctors.

[0280] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient when they are discharged from the hospital.

[0281] A "medical institution" is a facility that provides medical services, such as a hospital or clinic.

[0282] This invention is a system provided under a contract with a medical institution, which extracts information from electronic medical records, generates summaries, and provides them to users. A specific embodiment of this system will be described below.

[0283] The server first extracts information from the electronic medical record system. To do this, the server uses specific software (e.g., Apache Kafka) to obtain the necessary data from the electronic medical record. The obtained data is then stored in a database (e.g., MySQL (registered trademark)).

[0284] Next, the server inputs the stored data into a generative AI model to generate a summary. OpenAI's GPT-4 is used for the generative AI model. Specifically, the server retrieves medical records from the database and sends a prompt to the generative AI model. For example, the server sends a prompt such as, "Please summarize the patient's medical record. Please include the following information: patient's name, age, diagnosis, prescribed medications, and next appointment date."

[0285] The generated summary is provided to the user. The user can view the summary through a dedicated interface (e.g., a web application). The server updates the page using HTML and JavaScript (registered trademark) to display the generated summary in the web application interface. The user views the summary through a web browser.

[0286] As a concrete example, consider the following scenario.

[0287] scenario:

[0288] A user (doctor) wants to summarize a patient's medical record. The user accesses the electronic medical record system and inputs the medical record. The server retrieves the medical record and generates a summary.

[0289] Example prompt sentence:

[0290] "Please summarize the patient's medical record. Include the following information: patient's name, age, diagnosis, prescribed medications, and next appointment."

[0291] This system allows doctors to quickly obtain summaries of medical records and reduces the burden of paperwork. This solves the problem of doctors' overwork and contributes to improving the quality of medical care. The flow of the identification process in Example 3 will be explained using Figure 15.

[0292] Step 1:

[0293] A user enters medical records into an electronic medical record system.

[0294] Input: Patient medical information (name, age, diagnosis, prescribed medications, next appointment, etc.)

[0295] Output: Medical records stored in the electronic medical record system

[0296] Specific operation: The user enters the required information into the input form of the electronic medical record system and clicks the "Save" button.

[0297] Step 2:

[0298] The server retrieves medical records from the electronic medical record system.

[0299] Input: Medical records stored in the electronic medical record system

[0300] Output: Medical records retrieved to the server

[0301] Specific operation: The server sends a request to the electronic medical record system via the API to obtain new medical records.

[0302] Step 3:

[0303] The server stores the acquired medical records in a database.

[0304] Input: Medical records retrieved on the server

[0305] Output: Medical records stored in a database

[0306] Specific operation: The server inserts the retrieved medical records into the database using an SQL query.

[0307] Step 4:

[0308] The server inputs the stored data into a generative AI model to generate a summary.

[0309] Input: Medical records stored in a database

[0310] Output: The summary generated by the generative AI model

[0311] How it works: The server retrieves medical records from the database and sends a prompt to the generative AI model, such as "Please summarize the patient's medical record. Please include the following information: patient name, age, diagnosis, prescribed medications, and next appointment date."

[0312] Step 5:

[0313] The server provides the generated summary to the user.

[0314] Input: A summary generated by a generative AI model

[0315] Output: Summary provided to the user

[0316] Specific operation: The server updates the page using HTML and JavaScript to display the generated summary in the web application interface. The user can then view the summary through their web browser.

[0317] (Application example 3)

[0318] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0319] Conventional document preparation work in medical institutions places a heavy burden on doctors and causes excessive work. In factories, data management for manufacturing processes is also complicated, making efficient management difficult. To solve these issues, a system is needed that automates the extraction and summarization of information and provides it efficiently.

[0320] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0321] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for collecting manufacturing process data, means for generating AI to summarize the collected manufacturing process data, and means for providing the summarized manufacturing process data. This reduces the burden of document preparation work at medical institutions and enables efficient management of manufacturing process data at factories.

[0322] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0323] "Means for extracting information" refers to the technology and equipment used to extract necessary information from electronic medical records and manufacturing process data.

[0324] "Generative AI" is a technology that uses artificial intelligence to summarize and generate information.

[0325] "Means of summarization" refers to techniques or devices for concisely summarizing extracted information.

[0326] A "means for providing summarized content" is a technique or device for providing summarized information to a user.

[0327] "Manufacturing process data" refers to data related to the manufacturing process in a factory.

[0328] "Means of collection" refers to technologies and devices for collecting manufacturing process data in real time.

[0329] The "means for providing summarized manufacturing process data" refers to a technique or device for providing summarized manufacturing process data to a manager.

[0330] In order to implement this invention, the server, terminal, and user must fulfill their respective roles. A specific embodiment will be described below.

[0331] Server Roles

[0332] The server extracts information from electronic medical records and summarizes it using a generative AI model. It also collects manufacturing process data from factories and summarizes it using a generative AI model. This summarized information is then provided to users.

[0333] The server uses the following hardware and software:

[0334] Hardware: powerful processor, sufficient memory, storage devices

[0335] Software: Python, Transformers library, Requests library

[0336] Device Role

[0337] The terminal receives the summary information provided by the server and displays it to the user. The terminal can be a smartphone, tablet, or PC.

[0338] User Roles

[0339] Users check the summary information provided through the terminal and take necessary actions. The main users are doctors at medical institutions and factory managers.

[0340] Data processing and calculation

[0341] The server extracts necessary information from electronic medical records and manufacturing process data and summarizes it using a generative AI model. Specifically, the following prompt sentence is input to the generative AI model:

[0342] Prompt Sentence Examples

[0343] "Please summarize the following manufacturing process data:

[0344] Machine 1 is in operation, has an output of 100, and has 2 errors.

[0345] Machine 2 is in a stopped state, with an output of 50 and 5 errors.

[0346] Machine 3's status is UP, output is 200, and there is 1 error.

[0347] A generative AI model summarizes this data and outputs a summary such as:

[0348] "Currently, two of the three machines are operational with a total output of 350. There have been a total of eight errors."

[0349] The server sends this summary information to the terminal, which then displays it to the user, allowing the user to quickly understand the situation and take appropriate action.

[0350] In this way, the burden of paperwork at medical institutions is reduced and efficient management of manufacturing process data at factories is achieved.

[0351] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0352] Step 1:

[0353] The server extracts information from the electronic medical record.

[0354] Input: Electronic medical record data

[0355] Output: Extracted medical information

[0356] Specific operation: The server accesses the electronic medical record system and obtains the patient's medical information, such as medical records and test results.

[0357] Step 2:

[0358] The server inputs the extracted medical information into a generative AI model to generate a summary.

[0359] Input: Extracted medical information

[0360] Output: Summarized medical information

[0361] Specific operation: The server converts the extracted medical information into text format and inputs it as a prompt to the generative AI model. The generative AI model summarizes the input information and generates concise medical information.

[0362] Step 3:

[0363] The server transmits the summarized medical information to the terminal.

[0364] Input: Summarized medical information

[0365] Output: Summary information sent to the terminal

[0366] Specific operation: The server transmits data over the network to send the generated summary information to the terminal, which receives the information and displays it to the user.

[0367] Step 4:

[0368] The server collects manufacturing process data within the factory.

[0369] Input: Manufacturing process data

[0370] Output: Collected manufacturing process data

[0371] Specific operation: The server collects data in real time from each machine in the factory, such as the machine's operating status, output, and error information.

[0372] Step 5:

[0373] The server inputs the collected manufacturing process data into a generative AI model to generate a summary.

[0374] Input: Collected manufacturing process data

[0375] Output: Summarized manufacturing process data

[0376] Specific operation: The server converts the collected manufacturing process data into text format and inputs it as a prompt to the generative AI model. The generative AI model summarizes the input information and generates concise manufacturing process data.

[0377] Step 6:

[0378] The server transmits the summarized manufacturing process data to the terminal.

[0379] Input: Summarized manufacturing process data

[0380] Output: Summary information sent to the terminal

[0381] Specific operation: The server transmits data over the network to send the generated summary information to the terminal, which receives the information and displays it to the user.

[0382] Step 7:

[0383] The user checks the summary information provided through the terminal and takes necessary actions.

[0384] Input: Summary information displayed on terminal

[0385] Output: User action

[0386] Specific operations: The user checks the summary information displayed on the terminal and decides on a patient's treatment plan based on the medical information, or takes action to optimize factory operations based on manufacturing process data.

[0387] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0388] "Example 1"

[0389] One embodiment of the present invention provides a system incorporating an emotion engine. This system includes a generation AI means for extracting information from electronic medical records and summarizing the extracted information, and a means for providing the summarized content. It also includes an emotion engine that recognizes the user's emotions. Specifically, the system recognizes emotions from the user's tone of voice and facial expressions, and adjusts the output of the generation AI according to those emotions. For example, if the user feels stressed, the generation AI takes that information into account and adjusts to provide a more concise summary.

[0390] "Example 2"

[0391] In another embodiment, a system is provided in which an emotion engine is used to create medical information reports and discharge summaries. This system extracts information from electronic medical records and inputs the extracted information into a generation AI to automatically generate medical information reports and discharge summaries. The system also includes an emotion engine that recognizes the user's emotions. Specifically, the system recognizes emotions from the user's tone of voice and facial expressions and adjusts the output of the generation AI according to those emotions. For example, if the system senses that the user is feeling happy, the generation AI takes that information into account and adjusts to provide a more detailed medical information report and discharge summary.

[0392] "Example 3"

[0393] In yet another embodiment, a system is provided in which an emotion engine is provided under a contract with a medical institution. This system extracts information from electronic medical records, inputs the extracted information into a generation AI to generate a summary, and provides the summary to the medical institution. Furthermore, an emotion engine that recognizes the user's emotions is also included. Specifically, the system recognizes emotions from the user's tone of voice and facial expressions, and then calculates the emotion.

[0394] For example, if the AI ​​senses that the user is feeling anxious, it will take that information into account and adjust its output to provide a more thoughtful summary.

[0395] The processing flow of each embodiment will be described below.

[0396] "Example 1"

[0397] Step 1: The system extracts information from the electronic medical record.

[0398] Step 2: The extracted information is input into the generative AI, which generates a summary.

[0399] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[0400] Step 4: The output of the generative AI is adjusted depending on the recognized emotion.

[0401] "Example 2"

[0402] Step 1: The system extracts information from the electronic medical record.

[0403] Step 2: The extracted information is input into the generation AI, and a medical information report and discharge summary are automatically generated.

[0404] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[0405] Step 4: The output of the generative AI is adjusted depending on the recognized emotion.

[0406] "Example 3"

[0407] Step 1: The system extracts information from the electronic medical record.

[0408] Step 2: The extracted information is input into the generative AI, which generates a summary.

[0409] Step 3: The generated summary is provided to the medical institution.

[0410] Step 4: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[0411] Step 5: The output of the generative AI is adjusted depending on the recognized emotion.

[0412] Example 1

[0413] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0414] Conventional electronic medical record systems have difficulty efficiently summarizing vast amounts of medical information and providing it to medical professionals. Furthermore, because they provide information without considering the user's feelings, they are unable to provide appropriate information to users who are stressed. This has led to issues such as reduced efficiency in medical settings and reduced user satisfaction.

[0415] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0416] In this invention, the server includes a means for extracting information from electronic medical records, a generating AI means for summarizing the extracted information, a means for providing the summarized content, a means for recognizing the user's emotion, and a means for adjusting the output of the generating AI based on the recognized emotion. This makes it possible to efficiently extract information from electronic medical records and provide appropriate summary information according to the user's emotion.

[0417] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0418] "Means of extracting information" refers to the functions and technologies used to extract the necessary information from electronic medical records.

[0419] "Generative AI" is a system that uses artificial intelligence technology to summarize input information.

[0420] "Means of summarization" refers to functions and technologies for concisely summarizing information extracted using generative AI.

[0421] "Means of providing" refers to the functions and technologies for displaying or conveying summarized information to the user.

[0422] "Means for recognizing emotions" refers to functions and technologies for determining emotions from the user's tone of voice, facial expressions, etc.

[0423] "Means for adjusting output" refers to functions and technologies that appropriately modify the summary results of the generative AI based on the recognized emotions.

[0424] MODE FOR CARRYING OUT THE INVENTION

[0425] This invention is a system that contracts with medical institutions and provides a generative AI service that extracts information from electronic medical records and summarizes that content. Specifically, it includes means for extracting necessary information from electronic medical records, generative AI means for summarizing the extracted information, means for providing the summarized content, means for recognizing user emotions, and means for adjusting the output of the generative AI based on the recognized emotions.

[0426] Hardware and software used

[0427] The server uses hardware and software to extract information from electronic medical record systems (e.g., EPIC, Cerner). The extracted information is sent to a generative AI model (e.g., OpenAI's GPT-4). The generative AI model uses natural language processing techniques to summarize the information. The summarized information is then sent to the device to be provided to the user.

[0428] Furthermore, an emotion engine (e.g., Affectiva, Microsoft Azure® Emotion API) is used to recognize emotions from the user's tone of voice and facial expressions. The emotion information recognized by the emotion engine is fed back to the generative AI model via the server. The generative AI model adjusts the content of the summary based on this feedback.

[0429] Specific examples

[0430] The user logs in to a medical institution's terminal and enters the patient ID "12345." The server extracts the medical records of patient "12345" from the electronic medical record system. The extracted information is sent to the generative AI model and summarized. The summarized information is displayed on the terminal for the user to review. If the emotion engine recognizes that the user is feeling stressed from their tone of voice or facial expression, the server sends that information to the generative AI model. The generative AI model adjusts the summary to make it more concise and sends it back to the terminal via the server. The user then reviews the final summary.

[0431] Prompt Sentence Examples

[0432] "Please summarize the medical record for patient ID: 12345. If the user is stressed, please keep the summary brief."

[0433] In this way, the system can extract information from a medical institution's electronic medical records, summarize it using a generative AI model, and adjust the output according to the user's emotions.

[0434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] A user logs in to a terminal.

[0437] The user logs in by entering their user ID and password into the medical institution's terminal. The entered user ID and password are sent from the terminal to the server for authentication. If authentication is successful, the user is able to access the system.

[0438] Step 2:

[0439] The user enters the patient ID.

[0440] The user inputs the ID of the patient they wish to summarize into the terminal. The input patient ID is sent from the terminal to the server. The server then searches the electronic medical record system for the corresponding patient's medical records based on this patient ID.

[0441] Step 3:

[0442] The server extracts information from the electronic medical record system.

[0443] The server accesses the electronic medical record system using the patient ID and extracts the medical records of the corresponding patient. The extracted medical records are temporarily stored on the server. The input is the patient ID and the output is the medical records.

[0444] Step 4:

[0445] The server sends the extracted information to the generative AI model.

[0446] The server sends the extracted medical records to the generative AI model, which receives the medical records and begins processing the data for summarization. The input is the medical records, and the output is the summary results.

[0447] Step 5:

[0448] A generative AI model summarizes the information.

[0449] The generative AI model summarizes the received medical records using natural language processing techniques. The summarized information is sent back to the server. The input is the medical records, and the output is the summarized information.

[0450] Step 6:

[0451] The server sends the summarized information to the terminal.

[0452] The server sends the summary information received from the generative AI model to the terminal, which displays the summary information to the user. The input is the summarized information, and the output is the display on the terminal.

[0453] Step 7:

[0454] The user reviews the summarized information.

[0455] The user checks the summary information displayed on the terminal. The user decides the next action based on the summary information. The input is the summarized information, and the output is the user's confirmation.

[0456] Step 8:

[0457] The emotion engine recognizes the user's emotions.

[0458] The emotion engine analyzes the user's tone of voice and facial expression to recognize the user's emotion. The recognized emotion information is sent to the server. The input is the user's tone of voice and facial expression, and the output is emotion information.

[0459] Step 9:

[0460] The server sends the emotion engine feedback to the generative AI model.

[0461] The server sends the emotion information received from the emotion engine to the generative AI model, which then adjusts the summary content based on this feedback. The input is emotion information, and the output is adjustment instructions.

[0462] Step 10:

[0463] A generative AI model refines the summary.

[0464] The generative AI model adjusts the content of the summary based on feedback from the emotion engine. For example, if the user is feeling stressed, the summary will be made more concise. The adjusted summary is then sent back to the server. The input is emotion information, and the output is the adjusted summary.

[0465] Step 11:

[0466] The server sends the adjusted summary to the terminal.

[0467] The server sends the adjusted summary received from the generative AI model to the device, which then displays the adjusted summary to the user. The input is the adjusted summary, and the output is the display on the device.

[0468] Step 12:

[0469] The user confirms the final summary.

[0470] The user confirms the final summary displayed on the terminal. The user decides the next action based on the final summary. The input is the adjusted summary, and the output is the user's confirmation.

[0471] (Application example 1)

[0472] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0473] Conventional electronic medical record systems require medical professionals to manually organize and summarize vast amounts of information, which is time-consuming and labor-intensive. Furthermore, they often provide information without considering the user's feelings, which can be stressful. This can lead to reduced efficiency in medical settings and delayed responses to patients.

[0474] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for extracting information from the electronic medical record, means for generating AI to summarize the extracted information, means for providing the summarized content, means for recognizing the user's emotion, and means for adjusting the output of the generating AI according to the recognized emotion. This makes it possible to efficiently summarize the information in the electronic medical record and provide appropriate information according to the user's emotion.

[0475] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0476] "Means for extracting information" refers to a device or program that has the function of automatically extracting necessary information from electronic medical records.

[0477] "Generative AI" is a system that uses artificial intelligence technology to summarize and generate input information.

[0478] A "summarizing means" is a device or program that has the function of concisely summarizing extracted information.

[0479] The "means for providing" is a device or program that has the function of displaying or transmitting the summarized information to the user.

[0480] The "means for recognizing emotions" is a device or program that has the function of detecting emotions from the user's tone of voice, facial expression, etc.

[0481] A "means for adjusting output" is a device or program that has the function of changing the output content of the generating AI based on the recognized emotion.

[0482] A system for carrying out this invention has the following configuration: The system includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for recognizing a user's emotion, and means for adjusting the output of the generating AI in accordance with the recognized emotion.

[0483] Hardware and software used

[0484] Hardware: Smartphone

[0485] Software: OpenAI API, emotion_recognition library, electronic medical record data management system

[0486] Data processing and calculation

[0487] Information extraction from electronic medical records

[0488] The server uses the electronic medical record data management system to extract the necessary information from the electronic medical record. This extraction process is performed using the API of the electronic medical record data management system.

[0489] emotion recognition

[0490] The device uses the emotion_recognition library to recognize emotions from the user's tone of voice and facial expressions. This library takes audio and image data as input and classifies the emotion.

[0491] Generative AI summarization

[0492] The server uses the OpenAI API to summarize the extracted information. Depending on the user's emotions, the prompt sentence is adjusted and input to the generation AI. For example, if the user is feeling stressed, the prompt sentence will be "Please briefly summarize the following information:"

[0493] Specific examples

[0494] Electronic medical record data

[0495] Input data: "Patient's electronic medical record data"

[0496] User voice and facial expression data

[0497] Input data: "Audio data of the user feeling stressed"

[0498] Prompt Sentence Examples

[0499] If you're feeling stressed: "Please provide a brief summary of the following information: Patient's electronic medical record data"

[0500] Typical: "Please provide a detailed summary of the following information: Patient's electronic medical record data"

[0501] In this way, the system can efficiently summarize information from electronic medical records and provide appropriate information based on the user's emotions, which is expected to improve efficiency in medical settings and enable faster responses to patients.

[0502] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0503] Step 1:

[0504] The server uses the electronic medical record data management system to extract the necessary information from the electronic medical record. The input is the electronic medical record data, and the output is the extracted information. Specifically, it uses an API to obtain the patient's medical information and extracts the necessary data fields.

[0505] Step 2:

[0506] The device uses the emotion_recognition library to recognize emotions from the user's tone of voice and facial expressions. The input is the user's voice data or image data, and the output is the recognized emotion. Specifically, the voice data or image data is input into the library, and an emotion classification algorithm is applied to identify the emotion.

[0507] Step 3:

[0508] The server uses the OpenAI API to summarize the extracted information. The input is the extracted information and the recognized emotion, and the output is the summarized information. Specifically, the prompt sentence is adjusted according to the recognized emotion and input to the generation AI. For example, if the user is feeling stressed, the prompt sentence will be "Please briefly summarize the following information:"

[0509] Step 4:

[0510] The server sends the generated summary information to the terminal and provides it to the user. The input is the summarized information, and the output is the information displayed to the user. Specifically, the summary information is sent to the terminal and displayed on the terminal screen.

[0511] Step 5:

[0512] The user checks the provided summary information and performs additional operations as necessary. The input is the summary information, and the output is the user's feedback or additional operations. Specifically, the user checks the summary information and requests detailed information or provides feedback as necessary.

[0513] Example 2

[0514] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0515] Conventional systems for creating medical information reports and discharge summaries take time to extract and summarize information from electronic medical records, making efficient operation difficult. Furthermore, they lack the flexibility to consider user emotions, which can lead to a decline in user satisfaction. To solve these issues, a system is needed that integrates information extraction from electronic medical records, summarization using generative AI, and recognition and reflection of user emotions.

[0516] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0517] In this invention, the server includes a means for extracting information from electronic medical records, a generating AI means for summarizing the extracted information, a means for providing the summarized content, a means for recognizing the user's emotion, and a means for adjusting the output of the generating AI based on the recognized emotion. This enables efficient information extraction and summarization, and also enables flexible responses according to the user's emotion.

[0518] An "electronic medical record" is a system that electronically manages patient medical records, test results, prescription information, etc.

[0519] "Means of extracting information" refers to the methods and techniques used to obtain the necessary data from the electronic medical record system.

[0520] "Generative AI" is a system that uses artificial intelligence technology to generate summaries and sentences in natural language based on input data.

[0521] "Means of summarization" refers to methods and techniques for concisely summarizing information extracted using generative AI.

[0522] "Means for providing" refers to the methods and techniques for displaying the generated summary or text to the user or saving it.

[0523] "Means for recognizing user emotions" refers to methods and techniques for determining emotions by analyzing the user's tone of voice and facial expressions.

[0524] "Means for adjusting the output of the generative AI based on emotions" refers to methods or technologies for changing the output content of the generative AI based on the recognized emotional information of the user.

[0525] A "medical information report" is a document used to provide information about a patient's medical treatment and progress to other medical institutions and doctors.

[0526] A "discharge summary" is a document that summarizes the patient's treatment progress and future treatment plan when the patient is discharged from the hospital.

[0527] This invention is a system that extracts information from electronic medical records and automatically generates medical information reports and discharge summaries using a generation AI. It also has the ability to recognize the user's emotions and adjust the output of the generation AI based on those emotions.

[0528] Server Roles

[0529] The server accesses an electronic medical record system (e.g., a general electronic medical record system) to retrieve patient medical records, test results, prescription information, etc. Specifically, it queries the required data using an API and retrieves the data in JSON format. The server then inputs the extracted information into a generative AI model (e.g., a general generative AI model) to automatically generate medical information reports and discharge summaries. This generation process uses natural language processing technology to convert the extracted data into an appropriate format.

[0530] Device Role

[0531] The device is equipped with an emotion engine that detects the user's tone of voice and facial expressions. Specifically, it analyzes the user's voice and facial expressions in real time using a microphone and camera. The emotion engine (e.g., a general emotion recognition engine) recognizes the user's emotions based on this data and sends that information to a server.

[0532] User Roles

[0533] When requesting the generation of a medical information report or discharge summary, the user speaks into the device. The emotion engine analyzes the user's tone of voice and facial expressions, and the results are sent to the server. The server then adjusts the output of the generative AI model taking into account the user's emotional information. For example, if the user is feeling happy, the generative AI model will be adjusted to generate a medical information report or discharge summary that includes more detailed information.

[0534] Specific examples

[0535] Example prompts to input to the generative AI model

[0536] "Please prepare a medical information form based on the patient's medical record. Include the following information: patient profile, diagnosis, treatment, prescribed medications, and next appointment."

[0537] Example

[0538] 1. Server process:

[0539] The server extracts the patient's medical records using the API of a common electronic medical record system.

[0540] The extracted information is input into a general generative AI model to generate a medical information report.

[0541] 2. Terminal processing:

[0542] The device uses a microphone and camera to sense the user's tone of voice and facial expressions in real time.

[0543] The emotion engine analyzes the user's emotions and sends the results to the server.

[0544] 3. User Action:

[0545] The user speaks to the terminal, saying, "Please create a medical information report."

[0546] The user's emotions are analyzed and sent to the server.

[0547] 4. Final output:

[0548] The server takes into account the user's emotional information and adjusts the output of the generative AI model.

[0549] A more detailed medical report is generated and provided to the user.

[0550] This system will streamline the creation of medical information forms and discharge summaries, and will enable flexible responses based on the user's emotions.

[0551] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0552] Step 1:

[0553] The server accesses the electronic medical record system to retrieve the patient's medical records, test results, prescription information, etc. Specifically, it queries the required data using an API and retrieves the data in JSON format. The input is the patient ID, and the output is the patient's medical record data.

[0554] Step 2:

[0555] The server converts the extracted information into an appropriate format and inputs it into the generative AI model. Specifically, it converts the medical records into text format and generates a prompt. The input is the medical record data, and the output is the prompt to be input into the generative AI model.

[0556] Step 3:

[0557] The server receives the output from the generative AI model and generates the medical information report and discharge summary. Specifically, it formats the generated text and saves it in PDF or Word format. The input is the prompt text, and the output is the generated medical information report and discharge summary.

[0558] Step 4:

[0559] The device is equipped with an emotion engine that detects the user's tone of voice and facial expressions. Specifically, it analyzes the user's voice and facial expressions in real time using a microphone and camera. The input is the user's voice data and video data, and the output is analyzed emotional data.

[0560] Step 5:

[0561] The device uses an emotion engine to analyze the user's emotions. Specifically, it analyzes changes in voice tone and facial expressions to generate emotion data. The input is audio data and video data, and the output is emotion data.

[0562] Step 6:

[0563] When requesting the creation of a medical information report or discharge summary, the user speaks to the terminal. Specifically, the user says, "Please create a medical information report." The input is the user's voice instruction, and the output is the collection of voice data by the terminal.

[0564] Step 7:

[0565] The device sends the analyzed emotion information to the server. Specifically, the emotion data is sent to the server in JSON format. The input is emotion data, and the output is the emotion data sent to the server.

[0566] Step 8:

[0567] The server adjusts the output of the generative AI model based on the received emotional information. Specifically, if the user feels joy, the generative AI model adjusts the prompt sentence to include more detailed information. The input is emotional data, and the output is the adjusted prompt sentence.

[0568] Step 9:

[0569] The server then inputs the adjusted prompts back into the generative AI model to generate the final medical information report or discharge summary. Specifically, it formats the generated text and provides it to the user. The input is the adjusted prompts, and the output is the final medical information report or discharge summary.

[0570] (Application example 2)

[0571] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0572] Conventional systems for creating medical information reports and discharge summaries simply extract and summarize information from electronic medical records, and are unable to adjust the output to take the user's emotions into account, making it difficult to respond to the needs of individual patients and customers. Furthermore, when dealing with customers in physical stores, there is also the problem of being unable to recognize the customer's emotions and provide optimal customer service methods or product suggestions accordingly.

[0573] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0574] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for recognizing a user's emotion, means for adjusting the output of the generating AI based on the recognized emotion, and means for supporting customer service in physical stores. This makes it possible to create medical information reports and discharge summaries that take the user's emotion into consideration, and also enables optimal customer service methods and product suggestions in physical stores according to the customer's emotion.

[0575] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0576] "Means for extracting information" refers to the technology or equipment used to extract the necessary information from electronic medical records.

[0577] "Generative AI" is a technology that uses artificial intelligence to generate text and data based on input information.

[0578] A "summarization means" is a technique or device for concisely summarizing extracted information.

[0579] "Means for providing" refers to the technology or device for presenting the summarized information to the user.

[0580] "Means for recognizing user emotions" refers to technology or devices for determining emotions from the user's tone of voice, facial expressions, etc.

[0581] "Means for adjusting output" refers to technologies or devices that change the output content of the generative AI based on recognized emotions.

[0582] "Means for supporting customer service in brick-and-mortar stores" refer to technologies and devices for supporting dialogue with customers and the provision of services in brick-and-mortar stores.

[0583] The system for implementing this invention has the functions of extracting information from electronic medical records, summarizing it using generative AI, and adjusting the output by recognizing the user's emotions. Specific embodiments of this system are described below.

[0584] First, the server extracts information from the electronic medical record. The electronic medical record contains detailed records of the patient's medical history, and technology and devices are used to extract the necessary information based on this information. Specifically, an electronic medical record information extraction module is used.

[0585] Next, the extracted information is input into generative AI, a technology that uses artificial intelligence to generate text and data based on the input information. OpenAI's API is used here. The generative AI summarizes the extracted information and generates medical information reports and discharge summaries.

[0586] Furthermore, an emotion recognition engine is used to recognize the user's emotions. An emotion recognition engine is a technology or device that determines emotions from the user's tone of voice, facial expressions, etc. Specifically, the Emotion Engine is used. Once the user's emotions are recognized, the output content of the generation AI is adjusted based on those emotions.

[0587] Finally, a means will be provided to support customer service in physical stores. In physical stores, when a store clerk interacts with a customer, the AI ​​recognizes the customer's emotions and generates optimal customer service methods and product suggestions in real time based on those emotions. For this purpose, mobile devices such as smartphones and tablets are used.

[0588] As a specific example, a medical information report can be generated by inputting the following prompt sentence into a generative AI model.

[0589] Please generate a medical information form based on the information below.

[0590] Information: The patient is a 45-year-old man with diabetes and hypertension. Recent laboratory results show high blood sugar and elevated blood pressure.

[0591] User Emotion: Delight

[0592] Using this prompt, the AI ​​can generate a detailed medical information report for the patient.

[0593] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0594] Step 1:

[0595] The server extracts information from the electronic medical record. Specifically, it uses an electronic medical record information extraction module to extract the patient's medical information. The input for this process is the electronic medical record data, and the output is the extracted medical information.

[0596] Step 2:

[0597] The server inputs the extracted information into the generation AI, which uses OpenAI's API to generate a medical information report and discharge summary based on the input information. The input for this process is the extracted medical information, and the output is the generated medical information report and discharge summary.

[0598] Step 3:

[0599] The device recognizes the user's emotions. Specifically, it uses the Emotion Engine to determine emotions from the user's tone of voice and facial expressions. The input for this process is the user's voice data and facial data, and the output is the recognized emotion.

[0600] Step 4:

[0601] The server adjusts the output of the generation AI based on the recognized emotion. Specifically, it generates a prompt sentence according to the emotion and inputs it back into the generation AI. The inputs to this process are the recognized emotion and the initial output of the generation AI, and the output is an adjusted medical information form or discharge summary.

[0602] Step 5:

[0603] The terminal supports customer service in physical stores. Specifically, it provides optimal customer service methods and product suggestions in real time based on the adjusted medical information report and discharge summary. The input for this process is the adjusted medical information report and discharge summary, and the output is the customer service methods and product suggestions provided to the customer.

[0604] Example 3

[0605] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0606] The document preparation work of doctors in medical institutions is very time-consuming and labor-intensive, contributing to overwork. Furthermore, doctors may feel emotional stress when summarizing patients' medical records. This can lead to reduced efficiency and delayed responses to patients. Furthermore, because the summary content is uniform, it is difficult for doctors to respond flexibly according to their emotions and circumstances.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0608] In this invention, the server includes means for extracting information from electronic medical records, means for a generative AI model that summarizes the extracted information, means for providing the summarized content, means for an emotion engine that recognizes the user's emotions, and means for adjusting the output of the generative AI model based on information from the emotion engine. This reduces the burden on doctors in document preparation work and enables flexible summaries to be provided according to emotions.

[0609] An "electronic medical record" is a system that electronically manages medical information such as patient medical records, test results, and prescription information.

[0610] "Means of extracting information" refers to the methods and techniques used to obtain the necessary data from electronic medical records.

[0611] A "generative AI model" is an artificial intelligence algorithm or system that generates summaries or other text based on input information.

[0612] "Means for providing summarized content" refers to the methods and techniques for displaying the generated summary to a user or transmitting it to another system.

[0613] The "emotion engine" is a system that recognizes emotions from the user's tone of voice, facial expressions, etc., and analyzes that information.

[0614] "Means for adjusting the output of a generative AI model based on information from an emotion engine" refers to methods and technologies for changing the output content of a generative AI model in accordance with the emotional state of a user recognized by the emotion engine.

[0615] MODE FOR CARRYING OUT THE INVENTION

[0616] This invention is a system that extracts information from electronic medical records at medical institutions and summarizes that information. It also has the function of recognizing the user's emotions and adjusting the summary content accordingly. A specific embodiment of this system is described below.

[0617] server

[0618] The server accesses the medical institution's electronic medical record system and extracts the necessary information. Specifically, the server uses the API of the electronic medical record system (e.g., EPIC, Cerner) to obtain data such as patient medical records, test results, and prescription information. The obtained data is input into a generative AI model (e.g., OpenAI's GPT-4).

[0619] The server creates a prompt for the generative AI model and requests it to generate a summary. For example, the server sends the following prompt to the generative AI model:

[0620] "Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu"

[0621] The generative AI model generates a summary based on the input information and returns the summary to the server, which then sends the generated summary to the medical institution's terminal.

[0622] Terminal

[0623] The terminal is a computer or tablet used within the medical institution. The terminal receives the summary sent from the server and displays it on the screen. The doctor can check the summary through the terminal and enter corrections or additional information as necessary.

[0624] The device is also equipped with an emotion engine that uses a camera and microphone to recognize the user's tone of voice and facial expressions. The emotion engine analyzes the user's emotional state and sends that information to the server. For example, if the user looks anxious, the emotion engine sends that information to the server.

[0625] User

[0626] The user (doctor) uses a terminal to check the summary of the electronic medical record. If the user feels anxious or stressed, the emotion engine recognizes that emotion and notifies the server. The server adjusts the output of the generative AI model based on the information from the emotion engine, providing a more detailed and easy-to-understand summary.

[0627] For example, send the following prompt to the generative AI model:

[0628] "Please provide a clear and concise explanation as users are feeling anxious. Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu."

[0629] In this way, the system can improve the efficiency of document preparation work by doctors and provide flexible responses according to the user's feelings. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0630] Step 1:

[0631] The server accesses the medical institution's electronic medical record system and extracts the necessary information. Specifically, the server uses the electronic medical record system's API to obtain data such as patient medical records, test results, and prescription information. The input is data from the electronic medical record system, and the output is the extracted patient information.

[0632] Step 2:

[0633] The server inputs the extracted information into the generative AI model. Specifically, the server creates a prompt sentence based on the extracted data and sends it to the generative AI model. The input is the extracted patient information, and the output is the prompt sentence sent to the generative AI model. For example, the following prompt sentence is generated:

[0634] "Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu"

[0635] Step 3:

[0636] The generative AI model generates a summary based on the input prompt. The input is the prompt, and the output is the generated summary. The generated summary is returned to the server.

[0637] Step 4:

[0638] The server sends the generated summary to the medical institution's terminal. Specifically, the server sends the generated summary to the terminal in JSON format. The input is the generated summary, and the output is the summary data sent to the terminal.

[0639] Step 5:

[0640] The terminal receives the summary sent from the server and displays it on the screen. The input is the summary data sent from the server, and the output is the summary content displayed on the screen. The doctor can check the summary through the terminal and enter corrections or additional information as necessary.

[0641] Step 6:

[0642] The device uses a camera and microphone to recognize the doctor's tone of voice and facial expressions. Specifically, the device analyzes the data acquired from the camera and microphone in real time to determine the doctor's emotional state. The input is data from the camera and microphone, and the output is the analyzed emotional state.

[0643] Step 7:

[0644] The emotion engine sends the analyzed emotional state to the server. The input is the analyzed emotional state and the output is the emotion data sent to the server.

[0645] Step 8:

[0646] The server adjusts the output of the generative AI model based on information from the emotion engine. Specifically, the server creates and sends a new prompt to the generative AI model. The input is emotion data from the emotion engine, and the output is the adjusted prompt. For example, the server generates the following prompt:

[0647] "Please provide a clear and concise explanation as users are feeling anxious. Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu."

[0648] Step 9:

[0649] The generative AI model generates a new summary based on the adjusted prompt. The input is the adjusted prompt, and the output is the newly generated summary. The generated summary is returned to the server.

[0650] Step 10:

[0651] The server sends the newly generated summary to the terminal. The input is the newly generated summary, and the output is the summary data sent to the terminal. The terminal receives the new summary sent from the server and displays it on the screen. The doctor can check the new summary through the terminal and enter corrections or additional information as necessary.

[0652] In this way, the system can streamline doctors' paperwork and provide flexible responses that respond to users' emotions.

[0653] (Application example 3)

[0654] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0655] Traditional document preparation work in medical institutions places a heavy burden on doctors and causes excessive work. In factories, the collection and summarization of work data and the provision of feedback based on workers' emotions are not efficiently carried out, resulting in reduced work efficiency and increased worker stress. To solve these issues, a system that integrates information extraction and summarization with emotion recognition is needed.

[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0657] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for collecting work data, means for generating AI to summarize the collected data, means for recognizing the emotions of workers, and means for adjusting the output of the generating AI according to the emotions. This reduces the burden of document preparation work at medical institutions, improves work efficiency in factories, and reduces worker stress.

[0658] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0659] "Means of extracting information" refers to the technology and equipment used to extract the necessary data from electronic medical records and sensors.

[0660] "Generative AI" is a technology that uses artificial intelligence to summarize and generate input data.

[0661] A "summarization means" is a technique or device for concisely summarizing extracted information.

[0662] The "means for providing the summarized content" refers to a technique or device for providing the generated summary to the user.

[0663] "Work data" refers to various data related to work within a factory.

[0664] "Means for collecting work data" refers to technologies and devices that collect work data using sensors and cameras within the factory.

[0665] "Means for recognizing the emotions of workers" refers to technology or devices that analyze the tone of voice and facial expressions of workers to recognize their emotions.

[0666] "Means for adjusting the output of the generative AI according to emotions" refers to technology or devices that change the output content of the generative AI based on recognized emotions.

[0667] The system for implementing this invention has the functions of extracting information from electronic medical records, generating summaries using generative AI, and providing those summaries. It also includes the functions of collecting work data in a factory, generating summaries, and recognizing the emotions of workers and adjusting feedback accordingly.

[0668] Hardware and software used

[0669] Hardware:

[0670] Camera: Used to capture the facial expressions of the workers.

[0671] Microphone: Used to capture the worker's tone of voice.

[0672] Sensors: Used to collect operational data within the factory.

[0673] software:

[0674] OpenCV: Used to process camera images.

[0675] transformers: Used to run generative AI models.

[0676] emotion_recognition: Used as an emotion recognition engine.

[0677] Data processing and calculation

[0678] The server first collects data from electronic medical records and sensors in the factory. The collected data is input into a generative AI model to generate a summary. Next, a camera and microphone are used to capture the worker's facial expressions and tone of voice, which are then analyzed by an emotion recognition engine. Based on the recognized emotions, the generative AI's output is adjusted, and final feedback is provided to the worker.

[0679] Specific examples

[0680] For example, work data in a factory, such as temperature, humidity, and machine operation status, is collected. This data is input into a generative AI model, which summarizes the progress and problems of the work. If a worker is feeling anxious, the emotion recognition engine will recognize that emotion, and the generative AI will be adjusted to provide more considerate feedback.

[0681] Prompt Sentence Examples

[0682] "Summarize the work data from within the factory. If workers are feeling uneasy, provide polite feedback."

[0683] In this way, the burden of paperwork at medical institutions can be reduced, and work efficiency at factories can be improved and stress on workers can be reduced.

[0684] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0685] Step 1:

[0686] The server collects data from electronic medical records and sensors in the factory. The electronic medical records provide patient medical information, while the sensors provide operational data such as temperature, humidity, and machine operation status in the factory. This data is then input into the server.

[0687] Step 2:

[0688] The server inputs the collected data into a generative AI model to generate summaries. Medical information reports and discharge summaries are generated from electronic medical record data, while summaries of work progress and issues are generated from factory work data. The generated summaries are output to the server.

[0689] Step 3:

[0690] The server uses a camera and microphone to capture the facial expressions and tone of voice of the worker, and this data is input into the server.

[0691] Step 4:

[0692] The server inputs the captured facial expression and tone data into an emotion recognition engine to recognize the worker's emotions. The emotion recognition engine analyzes the input data and outputs the worker's emotions (e.g., anxiety, joy, anger, etc.).

[0693] Step 5:

[0694] The server adjusts the output of the AI ​​based on the recognized emotion. For example, if the worker is feeling anxious, the AI ​​will be adjusted to provide more polite feedback. This adjusted feedback is output to the server.

[0695] Step 6:

[0696] The server provides the adjusted feedback to the worker, which is displayed on the worker's device or transmitted via voice, allowing the worker to receive appropriate instructions and feedback.

[0697] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0698] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0699] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0700] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0701] [Second embodiment]

[0702] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0703] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0704] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0705] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0706] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0707] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0708] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0709] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0710] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0711] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0712] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0713] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0714] "Example 1"

[0715] The system of the present invention contracts with medical institutions and provides a generation AI service that extracts information from electronic medical records and summarizes the contents. Specifically, it includes a means for extracting necessary information from electronic medical records, a generation AI means for summarizing the extracted information, and a means for providing the summarized contents.

[0716] "Example 2"

[0717] Generative AI is used to create medical information reports and discharge summaries. Specifically, it automatically generates medical information reports and discharge summaries based on information extracted from electronic medical records.

[0718] "Example 3"

[0719] This system is provided under contract with medical institutions. Specifically, based on the contract, it extracts and summarizes information from electronic medical records and provides the summary content. This reduces the burden of document preparation on doctors and solves the problem of overwork.

[0720] The processing flow of each embodiment will be described below.

[0721] "Example 1"

[0722] Step 1: Sign a contract with the medical institution.

[0723] Step 2: Based on the contract, extract the necessary information from the electronic medical record.

[0724] Step 3: Input the extracted information into the generative AI to generate a summary.

[0725] Step 4: Provide the generated summary to the medical institution.

[0726] "Example 2"

[0727] Step 1: Extract the necessary information from the electronic medical record.

[0728] Step 2: The extracted information is input into the generation AI, and a medical information report and discharge summary are automatically generated.

[0729] Step 3: Provide the generated medical information report and discharge summary to the medical institution.

[0730] "Example 3"

[0731] Step 1: Sign a contract with the medical institution.

[0732] Step 2: Based on the contract, information is extracted from the electronic medical record, summarized, and the summary content is provided.

[0733] Step 3: This will reduce the burden of paperwork on doctors and solve the problem of overwork.

[0734] Example 1

[0735] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0736] Conventional medical institutions rely on electronic medical record systems to manage medical information, but it is difficult to quickly extract and summarize the necessary information from the vast amount of data. Furthermore, the manual task of summarizing information by medical professionals requires time and effort, hindering efficient medical care. Furthermore, because the quality of the summary depends on the skill of the medical professional, it is difficult to provide consistent, high-quality summaries.

[0737] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0738] In this invention, the server includes means for extracting information from electronic medical records, means for preprocessing the extracted information, means for inputting the preprocessed information into a generative AI model to generate a summary, and means for providing the generated summary content. This makes it possible to quickly and accurately extract necessary information from electronic medical records, automatically generate consistent, high-quality summaries using the generative AI model, and provide them to medical professionals.

[0739] An "electronic medical record" is a system that electronically records and manages patient medical information at medical institutions.

[0740] "Means for extracting information" refers to methods and techniques for obtaining necessary medical information from the electronic medical record system.

[0741] "Preprocessing means" refers to methods or techniques for analyzing the extracted information and converting it into a form suitable for generating summaries.

[0742] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to summarize input information.

[0743] A "means for generating a summary" is a method or technology for inputting preprocessed information into a generative AI model and generating a summary.

[0744] The "means for providing summary content" refers to a method or technology for providing the generated summary text to medical professionals.

[0745] "Medical institution" means a facility that provides medical services, such as a hospital, medical office, or clinic.

[0746] A "medical information report" is a document used to provide details of a patient's medical treatment to other medical institutions and medical professionals.

[0747] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient's care, and is created when the patient is discharged from the hospital.

[0748] MODE FOR CARRYING OUT THE INVENTION

[0749] This invention is a system that contracts with medical institutions and provides a generative AI service that extracts information from electronic medical records and summarizes the content. A specific embodiment of this system will be described below.

[0750] System configuration

[0751] The server has the following main functions:

[0752] 1. Information extraction from electronic medical records:

[0753] The server accesses the medical institution's electronic medical record system (e.g., EPIC, Cerner) and extracts necessary data such as patient medical information, test results, and prescription information.

[0754] Specifically, it uses an API to retrieve data from the electronic medical record system.

[0755] 2. Information preprocessing:

[0756] The server preprocesses the acquired medical information.

[0757] Specifically, the server analyzes the acquired data and extracts the necessary information (diagnosis name, test results, prescribed medications, etc.).

[0758] 3. Information summary generation:

[0759] The server inputs the preprocessed information into a generative AI model (e.g., OpenAI's GPT-4) to generate a summary.

[0760] The generative AI model uses natural language processing techniques to summarize the extracted information in a concise, easy-to-understand format.

[0761] 4. Providing Abstract Content:

[0762] The server transmits the generated summary to a terminal at the medical institution.

[0763] The terminal displays the summary to the medical professional.

[0764] Specific examples

[0765] Information extraction from electronic medical records:

[0766] The server retrieves patient A's medical records from the EPIC system via the API.

[0767] The data collected includes diagnosis, test results, and prescription medication information.

[0768] Information preprocessing:

[0769] The server extracts information such as "high blood pressure," "blood pressure measurement result 120 / 80 mmHg," and "losartan 50 mg" from the medical records.

[0770] Generate summary of information:

[0771] The server then feeds the extracted information into a GPT-4 model to generate a summary like this:

[0772] Prompt: "Please summarize the following medical record. Include diagnosis, test results, and prescription information."

[0773] Input data: "Patient A, October 1, 2023, hypertension, blood pressure measurement result 120 / 80 mmHg, losartan 50 mg once daily"

[0774] The generative AI model generates a summary sentence.

[0775] Example: "Patient A is being treated for hypertension diagnosed on October 1, 2023, with their most recent blood pressure reading of 120 / 80 mmHg. They are currently taking Losartan 50 mg once daily."

[0776] Summary content provided by:

[0777] The server transmits the generated summary to a terminal at the medical institution.

[0778] The terminal displays the summary for medical personnel to review.

[0779] In this way, the server extracts information from the electronic medical record, generates a summary using the generative AI model, and provides it to medical professionals via their devices, allowing them to quickly and accurately grasp the patient's medical information and provide efficient medical care.

[0780] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0781] Step 1:

[0782] Information extraction from electronic medical records

[0783] The server accesses the medical institution's electronic medical record system. Specifically, the server uses the API key to authenticate to the electronic medical record system, and then sends an API request specifying the patient ID to retrieve the medical record. The input is the patient ID, and the output is the medical record data. The server saves the medical record received as an API response in its database.

[0784] Step 2:

[0785] Preprocessing of extracted information

[0786] The server runs a script to parse the stored medical records. Specifically, the server uses regular expressions and natural language processing techniques to extract necessary information such as diagnosis, test results, and prescription medications. The input is the medical record data, and the output is preprocessed information (diagnosis, test results, prescription medications, etc.).

[0787] Step 3:

[0788] Information summary generation

[0789] The server inputs the preprocessed information into the generative AI model. Specifically, the server converts the preprocessed information into JSON format and sends an API request to the generative AI model. The input is the preprocessed information, and the output is a generated summary. The generative AI model uses natural language processing technology to summarize the input information in a concise, easy-to-understand format.

[0790] Step 4:

[0791] Providing summary content

[0792] The server creates an API response to send the generated summary to the medical institution's terminal. Specifically, the server returns the generated summary to the terminal as an API response. The input is the generated summary, and the output is the API response to the terminal. The terminal executes code to display the received summary on a user interface, and displays the summary so that the medical professional can check it.

[0793] (Application example 1)

[0794] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0795] Conventional electronic medical records management in medical institutions contain a huge amount of information, making it difficult to quickly extract and summarize the necessary information. Furthermore, there was a lack of tools to understand the security status of patient data and take appropriate measures. This meant that medical institution security personnel could not perform their work efficiently, potentially increasing security risks.

[0796] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0797] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI summarizing the extracted information, means for providing the summarized content, means for generating a security report from the extracted information, and means for displaying the generated security report, which enables security personnel at medical institutions to quickly grasp the security status of patient data and take appropriate measures.

[0798] An "electronic medical record" is a system that electronically records and manages patient medical information at medical institutions.

[0799] "Means for extracting information" refers to techniques and methods for automatically extracting necessary information from electronic medical records.

[0800] "Generative AI" is a system that uses artificial intelligence technology to generate new information based on input data.

[0801] "Summarization methods" are techniques or methods for concisely summarizing extracted information.

[0802] "Means of delivery" refers to the technology or method used to display or deliver the summarized information to the user.

[0803] A "security report" is a document that evaluates and reports the security status of patient data based on extracted information.

[0804] "Displaying means" refers to the technology or method for presenting the generated security report in a form that can be viewed by a user.

[0805] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The function of each element will be explained below.

[0806] server

[0807] The server extracts information from the electronic medical records, summarizes that information using generative AI, and generates a security report. Specifically, it performs the following processes:

[0808] 1. Information extraction from electronic medical records:

[0809] The server connects to the medical institution's electronic medical record system and obtains the necessary information through the API. To do this, it uses the requests library to send an HTTP request and obtain the electronic medical record data.

[0810] 2. Summary of information:

[0811] The extracted information is then summarized using OpenAI's generative AI model (e.g., GPT-3), which extracts key information from the input medical data and generates a concise summary.

[0812] 3. Generate security reports:

[0813] The summarized information is formatted into a security report that assesses the security status of patient data and identifies necessary measures.

[0814] Terminal

[0815] The terminal is responsible for providing the generated security report to the user. Specifically, a device such as a smartphone or tablet is used.

[0816] 1. View the report:

[0817] The device receives the security report sent from the server and displays it in a format that can be viewed by the user, allowing the user to quickly understand the security situation and take necessary measures.

[0818] User

[0819] The user is a security officer at a medical institution, and is responsible for evaluating the security status of patient data based on the generated security report and taking appropriate measures.

[0820] Specific examples

[0821] For example, the following medical data is extracted from electronic medical records:

[0822] Patient ID: 12345

[0823] Medical Record: On October 1, 2023, the patient presented with a headache. An MRI scan confirmed a mild concussion. Prescriptions included pain medication and rest.

[0824] Based on this data, a generative AI model generates a summary like this:

[0825] Patient ID: 12345

[0826] Medical Record Summary: On October 1, 2023, the patient complained of a headache and was diagnosed with a mild concussion. Prescriptions included pain medication and rest.

[0827] Based on this summary, a security report is generated and displayed on the terminal, allowing the user to view the report and take necessary security measures.

[0828] In this way, the server, terminal, and user can work together to quickly and efficiently manage the security status of medical data.

[0829] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0830] Step 1:

[0831] The server connects to the medical institution's electronic medical record system and obtains the necessary information through the API. Specifically, it uses the requests library to send an HTTP request and obtain the electronic medical record data. The input is the API endpoint and authentication token, and the output is the raw data obtained from the electronic medical record.

[0832] Step 2:

[0833] The server formats the acquired raw data to input into the generative AI model. Specifically, it extracts the necessary information and generates prompt sentences. The input is raw data acquired from the electronic medical record, and the output is prompt sentences to input into the generative AI model.

[0834] Step 3:

[0835] The server uses a generative AI model (e.g., GPT-3) to generate a summary based on the prompt. Specifically, it calls the OpenAI API, sends the prompt, and retrieves the summary. The input is the prompt, and the output is the generated summary.

[0836] Step 4:

[0837] The server generates a security report based on the generated summary. Specifically, it applies the summary to a security assessment template to create a report. The input is the generated summary, and the output is the security report.

[0838] Step 5:

[0839] The server sends the generated security report to the terminal. Specifically, it sends the report as an HTTP response. The input is the security report, and the output is the report sent to the terminal.

[0840] Step 6:

[0841] The terminal displays the received security report to the user. Specifically, the report is displayed on the screen of a smartphone or tablet. The input is the security report sent from the server, and the output is the report displayed in a format that can be viewed by the user.

[0842] Step 7:

[0843] Based on the displayed security report, the user evaluates the security status of patient data and takes necessary measures. Specifically, the user checks the contents of the report and implements measures if there are any security risks. The input is the displayed security report, and the output is the security measures taken by the user.

[0844] Example 2

[0845] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0846] Traditionally, medical professionals have often manually created medical information forms and discharge summaries, which is time-consuming and labor-intensive. Manual input errors and information omissions can occur, creating a risk that patient medical information may not be accurately communicated. Furthermore, the process of extracting information from electronic medical records and generating documents is not automated, resulting in inefficiencies and increasing the burden on medical professionals.

[0847] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0848] In this invention, the server includes: means for extracting information from an electronic medical record; means for storing the extracted information in a database; means for generating a medical information report or discharge summary for the target patient using a prompt statement instructing the user to generate a medical information report or discharge summary based on the stored information about the target patient and a generative AI model; and means for presenting the generated medical information report or discharge summary to a user who is a medical professional and accepting revisions. This automates the process of creating medical information reports and discharge summaries, reducing the burden on medical professionals and enabling accurate and efficient information transmission. The generating means in the server saves the generated medical information report or discharge summary in PDF format or Word format, and the accepting means presents the medical information report or discharge summary saved in PDF format or Word format to the user who is a medical professional and accepting revisions. The extracting means in the server obtains diagnosis, treatment details, test results, and prescription drug data from the electronic medical record.

[0849] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0850] "Means for extracting information" refers to methods and techniques for obtaining necessary medical information from electronic medical records.

[0851] A "database" is a system for systematically storing and managing extracted information.

[0852] A "generative AI model" is a model that uses artificial intelligence to perform natural language processing and generate medical information reports and discharge summaries.

[0853] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[0854] A "medical information report" is a document used to provide a patient's medical information to other medical institutions and doctors.

[0855] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient's care, and is created when the patient is discharged from the hospital.

[0856] "PDF format" is an abbreviation for Portable Document Format, a file format for electronically storing and displaying documents.

[0857] "Word format" is a document file format created with Microsoft (registered trademark) Word.

[0858] A "terminal" is a device such as a computer or tablet used by a user.

[0859] "User" refers to a medical professional who uses this system to check and modify medical information reports and discharge summaries.

[0860] This invention is a system that extracts information from electronic medical records and automatically generates medical information reports and discharge summaries using a generative AI model. Specific embodiments of this system are described below.

[0861] The server accesses an electronic medical record system (e.g., a general electronic medical record system) and extracts the patient's medical information. Specifically, it uses an API to obtain data such as diagnosis, treatment details, test results, and prescribed medications. This data is then stored in a database (e.g., a general database system).

[0862] Next, the server retrieves the stored data and inputs it into a generative AI model (e.g., a general generative AI model). At this time, it generates a prompt sentence to give the model specific instructions. An example of a prompt sentence is the following format:

[0863] Please prepare a medical information form based on the patient's medical information below. <Patient medical information> Patient name: Taro Yamada Diagnosis: Hypertension Treatment: Administration of antihypertensive drugs Test results: Blood pressure 140 / 90 mmHg Prescription medication: Losartan 50mg

[0864] The generative AI model generates medical information reports and discharge summaries based on the input data. The generated documents are saved in PDF or Word format by the server, and then sent to a device (e.g., a standard computer or tablet).

[0865] The user can review the generated document through the terminal, make corrections or add additional information to the document as needed, and once corrections are complete, save the final document and print it if necessary.

[0866] This system automates the process of creating medical information forms and discharge summaries, reducing the burden on medical professionals and enabling accurate and efficient information transmission.

[0867] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0868] Step 1:

[0869] The server accesses the electronic medical record system and extracts the patient's medical information. Specifically, it uses an API to obtain data such as the diagnosis, treatment, test results, and prescribed medications. The input is the medical information from the electronic medical record system, and the output is the extracted medical information. The server obtains the required data by sending a request such as GET / api / patient / {patient_id} / records.

[0870] Step 2:

[0871] The server saves the extracted medical information in a database. The input is the extracted medical information, and the output is the information saved in the database. Specifically, it executes the following SQL query: INSERT INTO patient_records (patient_id, diagnosis, treatment, test_results, medications) VALUES (?, ?, ?, ?, ?).

[0872] Step 3:

[0873] The server retrieves the necessary data from the database and inputs it into the generative AI model. The input is the medical information retrieved from the database, and the output is the prompt statement to be input into the generative AI model. Specifically, it executes the SQL query SELECT diagnosis, treatment, test_results, medications FROM patient_records WHERE patient_id = ? and embeds the retrieved data into the prompt statement.

[0874] Step 4:

[0875] The server uses a generative AI model to generate medical information reports and discharge summaries. The input is a prompt and medical information, and the output is the generated document. The generative AI model is sent a prompt like this:

[0876] Please prepare a medical information form based on the patient's medical information below. <Patient medical information> Patient name: Taro Yamada Diagnosis: Hypertension Treatment: Administration of antihypertensive drugs Test results: Blood pressure 140 / 90 mmHg Prescription medication: Losartan 50mg

[0877] Step 5:

[0878] The server saves the generated document in PDF or Word format. The input is the generated document, and the output is a PDF or Word file. Specifically, a library (e.g., iText, Apache (registered trademark) POI) is used to generate the document and save it in the file system.

[0879] Step 6:

[0880] The server sends the generated document to the terminal. The input is a PDF or Word file, and the output is the document sent to the terminal. Specifically, the document is sent as an HTTP response, and the header Content-Disposition: attachment; filename="report.pdf" is set.

[0881] Step 7:

[0882] The user opens the received document on the terminal and checks its contents. The input is the document sent to the terminal and the output is the checked document. The user uses a text editor (e.g., a standard text editor) to enter corrections and additional information into the document as needed. Once corrections are complete, the user saves the final document and prints it if necessary.

[0883] (Application example 2)

[0884] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0885] In conventional medical systems, the task of extracting information from electronic medical records and creating medical information reports and discharge summaries is done manually, which is time-consuming and labor-intensive. Similarly, in security systems, the analysis of log data and video data and the creation of reports are done manually, making it difficult to respond quickly. To solve these problems, a system that automates information extraction, summarization, and report generation is needed.

[0886] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0887] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for extracting log data and video data collected from a security system, means for generating AI to summarize the extracted log data and video data, means for generating a security report based on the summarized log data and video data, and means for providing the generated security report. This not only enables the automatic generation of medical information notification forms and discharge summaries, but also enables the rapid generation and provision of security reports.

[0888] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[0889] "Means for extracting information" refers to the technology and devices used to extract necessary data from electronic medical records and security systems.

[0890] "Generative AI" is a system that uses artificial intelligence technology to summarize data and automatically generate reports and documents.

[0891] A "summarization means" is a technique or device for concisely summarizing extracted information.

[0892] "Means of delivery" refers to the technology or device used to communicate the generated summary or report to the user.

[0893] A "security system" is a monitoring and defense mechanism for ensuring the safety of facilities and information systems.

[0894] "Log data" is data that records system operations and access history.

[0895] "Video data" refers to video information captured by a surveillance camera or the like.

[0896] A "security report" is a report prepared based on data collected from a security system.

[0897] To put the present invention into practice, it is necessary to build a system in which the elements of the server, terminal, and user work together. A specific embodiment of this system is shown below.

[0898] Server Roles

[0899] The server extracts information from electronic medical records and summarizes it using generative AI. It also extracts log data and video data collected from security systems and summarizes them to generate security reports. The server uses the following hardware and software:

[0900] Hardware: Powerful processor, ample memory, and storage

[0901] Software: Python, OpenAI API

[0902] Device Role

[0903] The terminal provides an interface for providing the generated summaries and reports to the user. The terminal is a mobile device such as a smartphone or tablet, and is designed for easy user access.

[0904] User Roles

[0905] Users check the summaries and reports provided through the terminal and take action as necessary. For example, medical institution staff check the medical information form and discharge summary and explain the situation to the patient. Security personnel also check the security report and take necessary measures.

[0906] Data processing and calculation

[0907] The server extracts data from electronic medical records and security systems and summarizes it using a generative AI model, which uses prompts like the following to input data:

[0908] Prompt Sentence Examples

[0909] Please create a security report using the following information:

[0910] Summary of log data:

[0911] 2023-10-01 12:00:00 - Unauthorized access detected

[0912] Video data summary:

[0913] 2023-10-01 12:05:00 - Suspicious person entered building

[0914] Based on this prompt, the generative AI model generates a security report, which is then provided to the user via their device.

[0915] Specific examples

[0916] For example, in medical institutions, generation AI can automatically generate medical information forms and discharge summaries based on patient medical information extracted from electronic medical records, reducing the burden on medical staff and enabling them to provide information quickly and accurately.

[0917] Additionally, security systems can detect suspicious activity from log data and video data and generate security reports summarizing the details, allowing security personnel to quickly take countermeasures.

[0918] In this way, the present invention automates the extraction, summarization, and provision of information in the medical and security fields, thereby realizing efficient business operations.

[0919] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0920] Step 1:

[0921] The server extracts information from the electronic medical record.

[0922] Input: Electronic medical record data

[0923] Output: Extracted medical information

[0924] Specific operation: The server accesses the electronic medical record system and obtains the patient's medical information, such as medical records, test results, and prescription information.

[0925] Step 2:

[0926] The server inputs the extracted medical information into a generative AI model to generate a summary.

[0927] Input: Extracted medical information

[0928] Output: Summarized medical information

[0929] Specific operation: The server creates a prompt for the generative AI model and instructs it to summarize the medical information. The generative AI model generates a medical information report and discharge summary based on the input information.

[0930] Step 3:

[0931] The server transmits the generated summary to the terminal.

[0932] Input: Summarized medical information

[0933] Output: Summary information sent to the terminal

[0934] Specific operation: The server sends the generated medical information report and discharge summary to the terminal so that medical staff can check them.

[0935] Step 4:

[0936] The server extracts log data and video data from the security system.

[0937] Input: Security system log data and video data

[0938] Output: Extracted log data and video data

[0939] Specific operation: The server accesses the security system and obtains log data and video data from surveillance cameras.

[0940] Step 5:

[0941] The server inputs the extracted log data and video data into a generative AI model to generate a summary.

[0942] Input: Extracted log data and video data

[0943] Output: Summarized log data and video data

[0944] Specific operation: The server creates prompts for the generative AI model and instructs it to summarize the log data and video data. The generative AI model then generates a security report based on the input information.

[0945] Step 6:

[0946] The server transmits the generated security report to the terminal.

[0947] Input: Summarized log data and video data

[0948] Output: Security report sent to the device

[0949] Specific operation: The server sends the generated security report to the terminal so that the security officer can check it.

[0950] Step 7:

[0951] The user checks the summary and report provided through the terminal and takes any necessary action.

[0952] Input: Summary information and security reports sent to the terminal

[0953] Output: User's response action

[0954] Specific operations: The user checks the medical information form, discharge summary, and security report displayed on the terminal, and provides explanations to the patient or takes security measures as necessary.

[0955] Example 3

[0956] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0957] In medical institutions, the burden of creating medical records is heavy for doctors, resulting in excessive work. In addition, creating medical information forms and discharge summaries requires a lot of time and effort, reducing the efficiency of doctors' work. This has led to problems such as a decline in the quality of medical care and fatigue among doctors.

[0958] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0959] In this invention, the server includes means for extracting information from electronic medical records, means for storing the extracted information in a database, means for inputting the stored information into a generative AI model to generate a summary, and means for providing the generated summary to a user, thereby enabling doctors to quickly summarize medical records and efficiently create medical information reports and discharge summaries.

[0960] An "electronic medical record" is a system for electronically managing patient medical records.

[0961] "Means of extracting information" refers to the methods and techniques used to extract the necessary data from electronic medical records.

[0962] A "database" is a collection of data that stores information systematically and can be retrieved as needed.

[0963] A "generative AI model" is an algorithm or system that uses artificial intelligence to process data and perform summarization or generation.

[0964] A "means for generating a summary" is a method or technology that uses a generative AI model to concisely summarize extracted information.

[0965] "Means for providing to users" refers to methods and techniques for providing the generated summary to doctors and other medical professionals in an easy-to-view format.

[0966] A "medical information report" is a document used to communicate the details of a patient's medical treatment to other medical institutions and doctors.

[0967] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient when they are discharged from the hospital.

[0968] A "medical institution" is a facility that provides medical services, such as a hospital or clinic.

[0969] This invention is a system provided under a contract with a medical institution, which extracts information from electronic medical records, generates summaries, and provides them to users. A specific embodiment of this system will be described below.

[0970] The server first extracts information from the electronic medical record system. To do this, the server uses specific software (e.g., Apache Kafka) to retrieve the necessary data from the electronic medical record. The retrieved data is then stored in a database (e.g., MySQL).

[0971] Next, the server inputs the stored data into a generative AI model to generate a summary. OpenAI's GPT-4 is used for the generative AI model. Specifically, the server retrieves medical records from the database and sends a prompt to the generative AI model. For example, the server sends a prompt such as, "Please summarize the patient's medical record. Please include the following information: patient's name, age, diagnosis, prescribed medications, and next appointment date."

[0972] The generated summary is provided to the user, who can view the summary through a dedicated interface (e.g., a web application). The server updates the page using HTML and JavaScript to display the generated summary in the web application interface. The user then views the summary through a web browser.

[0973] As a concrete example, consider the following scenario.

[0974] scenario:

[0975] A user (doctor) wants to summarize a patient's medical record. The user accesses the electronic medical record system and inputs the medical record. The server retrieves the medical record and generates a summary.

[0976] Example prompt sentence:

[0977] "Please summarize the patient's medical record. Include the following information: patient's name, age, diagnosis, prescribed medications, and next appointment."

[0978] This system allows doctors to quickly obtain summaries of medical records and reduces the burden of paperwork. This solves the problem of doctors' overwork and contributes to improving the quality of medical care. The flow of the identification process in Example 3 will be explained using Figure 15.

[0979] Step 1:

[0980] A user enters medical records into an electronic medical record system.

[0981] Input: Patient medical information (name, age, diagnosis, prescribed medications, next appointment, etc.)

[0982] Output: Medical records stored in the electronic medical record system

[0983] Specific operation: The user enters the required information into the input form of the electronic medical record system and clicks the "Save" button.

[0984] Step 2:

[0985] The server retrieves medical records from the electronic medical record system.

[0986] Input: Medical records stored in the electronic medical record system

[0987] Output: Medical records retrieved to the server

[0988] Specific operation: The server sends a request to the electronic medical record system via the API to obtain new medical records.

[0989] Step 3:

[0990] The server stores the acquired medical records in a database.

[0991] Input: Medical records retrieved on the server

[0992] Output: Medical records stored in a database

[0993] Specific operation: The server inserts the retrieved medical records into the database using an SQL query.

[0994] Step 4:

[0995] The server inputs the stored data into a generative AI model to generate a summary.

[0996] Input: Medical records stored in a database

[0997] Output: The summary generated by the generative AI model

[0998] How it works: The server retrieves medical records from the database and sends a prompt to the generative AI model, such as "Please summarize the patient's medical record. Please include the following information: patient name, age, diagnosis, prescribed medications, and next appointment date."

[0999] Step 5:

[1000] The server provides the generated summary to the user.

[1001] Input: A summary generated by a generative AI model

[1002] Output: Summary provided to the user

[1003] Specific operation: The server updates the page using HTML and JavaScript to display the generated summary in the web application interface. The user can then view the summary through their web browser.

[1004] (Application example 3)

[1005] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1006] Conventional document preparation work in medical institutions places a heavy burden on doctors and causes excessive work. In factories, data management for manufacturing processes is also complicated, making efficient management difficult. To solve these issues, a system is needed that automates the extraction and summarization of information and provides it efficiently.

[1007] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1008] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for collecting manufacturing process data, means for generating AI to summarize the collected manufacturing process data, and means for providing the summarized manufacturing process data. This reduces the burden of document preparation work at medical institutions and enables efficient management of manufacturing process data at factories.

[1009] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1010] "Means for extracting information" refers to the technology and equipment used to extract necessary information from electronic medical records and manufacturing process data.

[1011] "Generative AI" is a technology that uses artificial intelligence to summarize and generate information.

[1012] "Means of summarization" refers to techniques or devices for concisely summarizing extracted information.

[1013] A "means for providing summarized content" is a technique or device for providing summarized information to a user.

[1014] "Manufacturing process data" refers to data related to the manufacturing process in a factory.

[1015] "Means of collection" refers to technologies and devices for collecting manufacturing process data in real time.

[1016] The "means for providing summarized manufacturing process data" refers to a technique or device for providing summarized manufacturing process data to a manager.

[1017] In order to implement this invention, the server, terminal, and user must fulfill their respective roles. A specific embodiment will be described below.

[1018] Server Roles

[1019] The server extracts information from electronic medical records and summarizes it using a generative AI model. It also collects manufacturing process data from factories and summarizes it using a generative AI model. This summarized information is then provided to users.

[1020] The server uses the following hardware and software:

[1021] Hardware: powerful processor, sufficient memory, storage devices

[1022] Software: Python, Transformers library, Requests library

[1023] Device Role

[1024] The terminal receives the summary information provided by the server and displays it to the user. The terminal can be a smartphone, tablet, or PC.

[1025] User Roles

[1026] Users check the summary information provided through the terminal and take necessary actions. The main users are doctors at medical institutions and factory managers.

[1027] Data processing and calculation

[1028] The server extracts necessary information from electronic medical records and manufacturing process data and summarizes it using a generative AI model. Specifically, the following prompt sentence is input to the generative AI model:

[1029] Prompt Sentence Examples

[1030] "Please summarize the following manufacturing process data:

[1031] Machine 1 is in operation, has an output of 100, and has 2 errors.

[1032] Machine 2 is in a stopped state, with an output of 50 and 5 errors.

[1033] Machine 3's status is UP, output is 200, and there is 1 error.

[1034] A generative AI model summarizes this data and outputs a summary such as:

[1035] "Currently, two of the three machines are operational with a total output of 350. There have been a total of eight errors."

[1036] The server sends this summary information to the terminal, which then displays it to the user, allowing the user to quickly understand the situation and take appropriate action.

[1037] In this way, the burden of paperwork at medical institutions is reduced and efficient management of manufacturing process data at factories is achieved.

[1038] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1039] Step 1:

[1040] The server extracts information from the electronic medical record.

[1041] Input: Electronic medical record data

[1042] Output: Extracted medical information

[1043] Specific operation: The server accesses the electronic medical record system and obtains the patient's medical information, such as medical records and test results.

[1044] Step 2:

[1045] The server inputs the extracted medical information into a generative AI model to generate a summary.

[1046] Input: Extracted medical information

[1047] Output: Summarized medical information

[1048] Specific operation: The server converts the extracted medical information into text format and inputs it as a prompt to the generative AI model. The generative AI model summarizes the input information and generates concise medical information.

[1049] Step 3:

[1050] The server transmits the summarized medical information to the terminal.

[1051] Input: Summarized medical information

[1052] Output: Summary information sent to the terminal

[1053] Specific operation: The server transmits data over the network to send the generated summary information to the terminal, which receives the information and displays it to the user.

[1054] Step 4:

[1055] The server collects manufacturing process data within the factory.

[1056] Input: Manufacturing process data

[1057] Output: Collected manufacturing process data

[1058] Specific operation: The server collects data in real time from each machine in the factory, such as the machine's operating status, output, and error information.

[1059] Step 5:

[1060] The server inputs the collected manufacturing process data into a generative AI model to generate a summary.

[1061] Input: Collected manufacturing process data

[1062] Output: Summarized manufacturing process data

[1063] Specific operation: The server converts the collected manufacturing process data into text format and inputs it as a prompt to the generative AI model. The generative AI model summarizes the input information and generates concise manufacturing process data.

[1064] Step 6:

[1065] The server transmits the summarized manufacturing process data to the terminal.

[1066] Input: Summarized manufacturing process data

[1067] Output: Summary information sent to the terminal

[1068] Specific operation: The server transmits data over the network to send the generated summary information to the terminal, which receives the information and displays it to the user.

[1069] Step 7:

[1070] The user checks the summary information provided through the terminal and takes necessary actions.

[1071] Input: Summary information displayed on terminal

[1072] Output: User action

[1073] Specific operations: The user checks the summary information displayed on the terminal and decides on a patient's treatment plan based on the medical information, or takes action to optimize factory operations based on manufacturing process data.

[1074] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1075] "Example 1"

[1076] One embodiment of the present invention provides a system incorporating an emotion engine. This system includes a generation AI means for extracting information from electronic medical records and summarizing the extracted information, and a means for providing the summarized content. It also includes an emotion engine that recognizes the user's emotions. Specifically, the system recognizes emotions from the user's tone of voice and facial expressions, and adjusts the output of the generation AI according to those emotions. For example, if the user feels stressed, the generation AI takes that information into account and adjusts to provide a more concise summary.

[1077] "Example 2"

[1078] In another embodiment, a system is provided in which the emotion engine is used to create medical information reports and discharge summaries. This system extracts information from electronic medical records and inputs the extracted information into a generation AI to automatically generate medical information reports and discharge summaries. Furthermore, the system can automatically generate the user's emotions.

[1079] It also includes an emotion recognition engine. Specifically, it recognizes emotions from the user's tone of voice and facial expressions and adjusts the output of the generation AI accordingly. For example, if the generation AI senses that the user is feeling happy, it will take that information into account and adjust to provide more detailed medical information forms and discharge summaries.

[1080] "Example 3"

[1081] In yet another embodiment, a system is provided in which an emotion engine is provided under a contract with a medical institution. This system extracts information from electronic medical records, inputs the extracted information into a generation AI to generate a summary, and provides the summary to the medical institution. It also includes an emotion engine that recognizes the user's emotions. Specifically, it recognizes emotions from the user's tone of voice and facial expressions and adjusts the output of the generation AI according to those emotions. For example, if the system senses that the user is feeling anxious, the generation AI takes that information into account and adjusts to provide a more detailed summary.

[1082] The processing flow of each embodiment will be described below.

[1083] "Example 1"

[1084] Step 1: The system extracts information from the electronic medical record.

[1085] Step 2: The extracted information is input into the generative AI, which generates a summary.

[1086] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[1087] Step 4: The output of the generative AI is adjusted depending on the recognized emotion.

[1088] "Example 2"

[1089] Step 1: The system extracts information from the electronic medical record.

[1090] Step 2: The extracted information is input into the generation AI, and a medical information report and discharge summary are automatically generated.

[1091] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[1092] Step 4: The output of the generative AI is adjusted depending on the recognized emotion.

[1093] "Example 3"

[1094] Step 1: The system extracts information from the electronic medical record.

[1095] Step 2: The extracted information is input into the generative AI, which generates a summary.

[1096] Step 3: The generated summary is provided to the medical institution.

[1097] Step 4: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[1098] Step 5: The output of the generative AI is adjusted depending on the recognized emotion.

[1099] Example 1

[1100] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1101] Conventional electronic medical record systems have difficulty efficiently summarizing vast amounts of medical information and providing it to medical professionals. Furthermore, because they provide information without considering the user's feelings, they are unable to provide appropriate information to users who are stressed. This has led to issues such as reduced efficiency in medical settings and reduced user satisfaction.

[1102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1103] In this invention, the server includes a means for extracting information from electronic medical records, a generating AI means for summarizing the extracted information, a means for providing the summarized content, a means for recognizing the user's emotion, and a means for adjusting the output of the generating AI based on the recognized emotion. This makes it possible to efficiently extract information from electronic medical records and provide appropriate summary information according to the user's emotion.

[1104] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1105] "Means of extracting information" refers to the functions and technologies used to extract the necessary information from electronic medical records.

[1106] "Generative AI" is a system that uses artificial intelligence technology to summarize input information.

[1107] "Means of summarization" refers to functions and technologies for concisely summarizing information extracted using generative AI.

[1108] "Means of providing" refers to the functions and technologies for displaying or conveying summarized information to the user.

[1109] "Means for recognizing emotions" refers to functions and technologies for determining emotions from the user's tone of voice, facial expressions, etc.

[1110] "Means for adjusting output" refers to functions and technologies that appropriately modify the summary results of the generative AI based on the recognized emotions.

[1111] MODE FOR CARRYING OUT THE INVENTION

[1112] This invention is a system that contracts with medical institutions and provides a generative AI service that extracts information from electronic medical records and summarizes that content. Specifically, it includes means for extracting necessary information from electronic medical records, generative AI means for summarizing the extracted information, means for providing the summarized content, means for recognizing user emotions, and means for adjusting the output of the generative AI based on the recognized emotions.

[1113] Hardware and software used

[1114] The server uses hardware and software to extract information from electronic medical record systems (e.g., EPIC, Cerner). The extracted information is sent to a generative AI model (e.g., OpenAI's GPT-4). The generative AI model uses natural language processing techniques to summarize the information. The summarized information is then sent to the device to be provided to the user.

[1115] Furthermore, an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API) is used to recognize emotions from the user's tone of voice and facial expressions. The emotion information recognized by the emotion engine is fed back to the generative AI model via the server. The generative AI model adjusts the content of the summary based on this feedback.

[1116] Specific examples

[1117] The user logs in to a medical institution's terminal and enters the patient ID "12345." The server extracts the medical records of patient "12345" from the electronic medical record system. The extracted information is sent to the generative AI model and summarized. The summarized information is displayed on the terminal for the user to review. If the emotion engine recognizes that the user is feeling stressed from their tone of voice or facial expression, the server sends that information to the generative AI model. The generative AI model adjusts the summary to make it more concise and sends it back to the terminal via the server. The user then reviews the final summary.

[1118] Prompt Sentence Examples

[1119] "Please summarize the medical record for patient ID: 12345. If the user is stressed, please keep the summary brief."

[1120] In this way, the system can extract information from a medical institution's electronic medical records, summarize it using a generative AI model, and adjust the output according to the user's emotions.

[1121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1122] Step 1:

[1123] A user logs in to a terminal.

[1124] The user logs in by entering their user ID and password into the medical institution's terminal. The entered user ID and password are sent from the terminal to the server for authentication. If authentication is successful, the user is able to access the system.

[1125] Step 2:

[1126] The user enters the patient ID.

[1127] The user inputs the ID of the patient they wish to summarize into the terminal. The input patient ID is sent from the terminal to the server. The server then searches the electronic medical record system for the corresponding patient's medical records based on this patient ID.

[1128] Step 3:

[1129] The server extracts information from the electronic medical record system.

[1130] The server accesses the electronic medical record system using the patient ID and extracts the medical records of the corresponding patient. The extracted medical records are temporarily stored on the server. The input is the patient ID and the output is the medical records.

[1131] Step 4:

[1132] The server sends the extracted information to the generative AI model.

[1133] The server sends the extracted medical records to the generative AI model, which receives the medical records and begins processing the data for summarization. The input is the medical records, and the output is the summary results.

[1134] Step 5:

[1135] A generative AI model summarizes the information.

[1136] The generative AI model summarizes the received medical records using natural language processing techniques. The summarized information is sent back to the server. The input is the medical records, and the output is the summarized information.

[1137] Step 6:

[1138] The server sends the summarized information to the terminal.

[1139] The server sends the summary information received from the generative AI model to the terminal, which displays the summary information to the user. The input is the summarized information, and the output is the display on the terminal.

[1140] Step 7:

[1141] The user reviews the summarized information.

[1142] The user checks the summary information displayed on the terminal. The user decides the next action based on the summary information. The input is the summarized information, and the output is the user's confirmation.

[1143] Step 8:

[1144] The emotion engine recognizes the user's emotions.

[1145] The emotion engine analyzes the user's tone of voice and facial expression to recognize the user's emotion. The recognized emotion information is sent to the server. The input is the user's tone of voice and facial expression, and the output is emotion information.

[1146] Step 9:

[1147] The server sends the emotion engine feedback to the generative AI model.

[1148] The server sends the emotion information received from the emotion engine to the generative AI model, which then adjusts the summary content based on this feedback. The input is emotion information, and the output is adjustment instructions.

[1149] Step 10:

[1150] A generative AI model refines the summary.

[1151] The generative AI model adjusts the content of the summary based on feedback from the emotion engine. For example, if the user is feeling stressed, the summary will be made more concise. The adjusted summary is then sent back to the server. The input is emotion information, and the output is the adjusted summary.

[1152] Step 11:

[1153] The server sends the adjusted summary to the terminal.

[1154] The server sends the adjusted summary received from the generative AI model to the device, which then displays the adjusted summary to the user. The input is the adjusted summary, and the output is the display on the device.

[1155] Step 12:

[1156] The user confirms the final summary.

[1157] The user confirms the final summary displayed on the terminal. The user decides the next action based on the final summary. The input is the adjusted summary, and the output is the user's confirmation.

[1158] (Application example 1)

[1159] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1160] Conventional electronic medical record systems require medical professionals to manually organize and summarize vast amounts of information, which is time-consuming and labor-intensive. Furthermore, they often provide information without considering the user's feelings, which can be stressful. This can lead to reduced efficiency in medical settings and delayed responses to patients.

[1161] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for extracting information from the electronic medical record, means for generating AI to summarize the extracted information, means for providing the summarized content, means for recognizing the user's emotion, and means for adjusting the output of the generating AI according to the recognized emotion. This makes it possible to efficiently summarize the information in the electronic medical record and provide appropriate information according to the user's emotion.

[1162] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1163] "Means for extracting information" refers to a device or program that has the function of automatically extracting necessary information from electronic medical records.

[1164] "Generative AI" is a system that uses artificial intelligence technology to summarize and generate input information.

[1165] A "summarizing means" is a device or program that has the function of concisely summarizing extracted information.

[1166] The "means for providing" is a device or program that has the function of displaying or transmitting the summarized information to the user.

[1167] The "means for recognizing emotions" is a device or program that has the function of detecting emotions from the user's tone of voice, facial expression, etc.

[1168] A "means for adjusting output" is a device or program that has the function of changing the output content of the generating AI based on the recognized emotion.

[1169] A system for carrying out this invention has the following configuration: The system includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for recognizing a user's emotion, and means for adjusting the output of the generating AI in accordance with the recognized emotion.

[1170] Hardware and software used

[1171] Hardware: Smartphone

[1172] Software: OpenAI API, emotion_recognition library, electronic medical record data management system

[1173] Data processing and calculation

[1174] Information extraction from electronic medical records

[1175] The server uses the electronic medical record data management system to extract the necessary information from the electronic medical record. This extraction process is performed using the API of the electronic medical record data management system.

[1176] emotion recognition

[1177] The device uses the emotion_recognition library to recognize emotions from the user's tone of voice and facial expressions. This library takes audio and image data as input and classifies the emotion.

[1178] Generative AI summarization

[1179] The server uses the OpenAI API to summarize the extracted information. Depending on the user's emotions, the prompt sentence is adjusted and input to the generation AI. For example, if the user is feeling stressed, the prompt sentence will be "Please briefly summarize the following information:"

[1180] Specific examples

[1181] Electronic medical record data

[1182] Input data: "Patient's electronic medical record data"

[1183] User voice and facial expression data

[1184] Input data: "Audio data of the user feeling stressed"

[1185] Prompt Sentence Examples

[1186] If you're feeling stressed: "Please provide a brief summary of the following information: Patient's electronic medical record data"

[1187] Typical: "Please provide a detailed summary of the following information: Patient's electronic medical record data"

[1188] In this way, the system can efficiently summarize information from electronic medical records and provide appropriate information based on the user's emotions, which is expected to improve efficiency in medical settings and enable faster responses to patients.

[1189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1190] Step 1:

[1191] The server uses the electronic medical record data management system to extract the necessary information from the electronic medical record. The input is the electronic medical record data, and the output is the extracted information. Specifically, it uses an API to obtain the patient's medical information and extracts the necessary data fields.

[1192] Step 2:

[1193] The device uses the emotion_recognition library to recognize emotions from the user's tone of voice and facial expressions. The input is the user's voice data or image data, and the output is the recognized emotion. Specifically, the voice data or image data is input into the library, and an emotion classification algorithm is applied to identify the emotion.

[1194] Step 3:

[1195] The server uses the OpenAI API to summarize the extracted information. The input is the extracted information and the recognized emotion, and the output is the summarized information. Specifically, the prompt sentence is adjusted according to the recognized emotion and input to the generation AI. For example, if the user is feeling stressed, the prompt sentence will be "Please briefly summarize the following information:"

[1196] Step 4:

[1197] The server sends the generated summary information to the terminal and provides it to the user. The input is the summarized information, and the output is the information displayed to the user. Specifically, the summary information is sent to the terminal and displayed on the terminal screen.

[1198] Step 5:

[1199] The user checks the provided summary information and performs additional operations as necessary. The input is the summary information, and the output is the user's feedback or additional operations. Specifically, the user checks the summary information and requests detailed information or provides feedback as necessary.

[1200] Example 2

[1201] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1202] Conventional systems for creating medical information reports and discharge summaries take time to extract and summarize information from electronic medical records, making efficient operation difficult. Furthermore, they lack the flexibility to consider user emotions, which can lead to a decline in user satisfaction. To solve these issues, a system is needed that integrates information extraction from electronic medical records, summarization using generative AI, and recognition and reflection of user emotions.

[1203] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1204] In this invention, the server includes a means for extracting information from electronic medical records, a generating AI means for summarizing the extracted information, a means for providing the summarized content, a means for recognizing the user's emotion, and a means for adjusting the output of the generating AI based on the recognized emotion. This enables efficient information extraction and summarization, and also enables flexible responses according to the user's emotion.

[1205] An "electronic medical record" is a system that electronically manages patient medical records, test results, prescription information, etc.

[1206] "Means of extracting information" refers to the methods and techniques used to obtain the necessary data from the electronic medical record system.

[1207] "Generative AI" is a system that uses artificial intelligence technology to generate summaries and sentences in natural language based on input data.

[1208] "Means of summarization" refers to methods and techniques for concisely summarizing information extracted using generative AI.

[1209] "Means for providing" refers to the methods and techniques for displaying the generated summary or text to the user or saving it.

[1210] "Means for recognizing user emotions" refers to methods and techniques for determining emotions by analyzing the user's tone of voice and facial expressions.

[1211] "Means for adjusting the output of the generative AI based on emotions" refers to methods or technologies for changing the output content of the generative AI based on the recognized emotional information of the user.

[1212] A "medical information report" is a document used to provide information about a patient's medical treatment and progress to other medical institutions and doctors.

[1213] A "discharge summary" is a document that summarizes the patient's treatment progress and future treatment plan when the patient is discharged from the hospital.

[1214] This invention is a system that extracts information from electronic medical records and automatically generates medical information reports and discharge summaries using a generation AI. It also has the ability to recognize the user's emotions and adjust the output of the generation AI based on those emotions.

[1215] Server Roles

[1216] The server accesses an electronic medical record system (e.g., a general electronic medical record system) to retrieve patient medical records, test results, prescription information, etc. Specifically, it queries the required data using an API and retrieves the data in JSON format. The server then inputs the extracted information into a generative AI model (e.g., a general generative AI model) to automatically generate medical information reports and discharge summaries. This generation process uses natural language processing technology to convert the extracted data into an appropriate format.

[1217] Device Role

[1218] The device is equipped with an emotion engine that detects the user's tone of voice and facial expressions. Specifically, it analyzes the user's voice and facial expressions in real time using a microphone and camera. The emotion engine (e.g., a general emotion recognition engine) recognizes the user's emotions based on this data and sends that information to a server.

[1219] User Roles

[1220] When requesting the generation of a medical information report or discharge summary, the user speaks into the device. The emotion engine analyzes the user's tone of voice and facial expressions, and the results are sent to the server. The server then adjusts the output of the generative AI model taking into account the user's emotional information. For example, if the user is feeling happy, the generative AI model will be adjusted to generate a medical information report or discharge summary that includes more detailed information.

[1221] Specific examples

[1222] Example prompts to input to the generative AI model

[1223] "Please prepare a medical information form based on the patient's medical record. Include the following information: patient profile, diagnosis, treatment, prescribed medications, and next appointment."

[1224] Example

[1225] 1. Server process:

[1226] The server extracts the patient's medical records using the API of a common electronic medical record system.

[1227] The extracted information is input into a general generative AI model to generate a medical information report.

[1228] 2. Terminal processing:

[1229] The device uses a microphone and camera to sense the user's tone of voice and facial expressions in real time.

[1230] The emotion engine analyzes the user's emotions and sends the results to the server.

[1231] 3. User Action:

[1232] The user speaks to the terminal, saying, "Please create a medical information report."

[1233] The user's emotions are analyzed and sent to the server.

[1234] 4. Final output:

[1235] The server takes into account the user's emotional information and adjusts the output of the generative AI model.

[1236] A more detailed medical report is generated and provided to the user.

[1237] This system will streamline the creation of medical information forms and discharge summaries, and will enable flexible responses based on the user's emotions.

[1238] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1239] Step 1:

[1240] The server accesses the electronic medical record system to retrieve the patient's medical records, test results, prescription information, etc. Specifically, it queries the required data using an API and retrieves the data in JSON format. The input is the patient ID, and the output is the patient's medical record data.

[1241] Step 2:

[1242] The server converts the extracted information into an appropriate format and inputs it into the generative AI model. Specifically, it converts the medical records into text format and generates a prompt. The input is the medical record data, and the output is the prompt to be input into the generative AI model.

[1243] Step 3:

[1244] The server receives the output from the generative AI model and generates the medical information report and discharge summary. Specifically, it formats the generated text and saves it in PDF or Word format. The input is the prompt text, and the output is the generated medical information report and discharge summary.

[1245] Step 4:

[1246] The device is equipped with an emotion engine that detects the user's tone of voice and facial expressions. Specifically, it analyzes the user's voice and facial expressions in real time using a microphone and camera. The input is the user's voice data and video data, and the output is analyzed emotional data.

[1247] Step 5:

[1248] The device uses an emotion engine to analyze the user's emotions. Specifically, it analyzes changes in voice tone and facial expressions to generate emotion data. The input is audio data and video data, and the output is emotion data.

[1249] Step 6:

[1250] When requesting the creation of a medical information report or discharge summary, the user speaks to the terminal. Specifically, the user says, "Please create a medical information report." The input is the user's voice instruction, and the output is the collection of voice data by the terminal.

[1251] Step 7:

[1252] The device sends the analyzed emotion information to the server. Specifically, the emotion data is sent to the server in JSON format. The input is emotion data, and the output is the emotion data sent to the server.

[1253] Step 8:

[1254] The server adjusts the output of the generative AI model based on the received emotional information. Specifically, if the user feels joy, the generative AI model adjusts the prompt sentence to include more detailed information. The input is emotional data, and the output is the adjusted prompt sentence.

[1255] Step 9:

[1256] The server then inputs the adjusted prompts back into the generative AI model to generate the final medical information report or discharge summary. Specifically, it formats the generated text and provides it to the user. The input is the adjusted prompts, and the output is the final medical information report or discharge summary.

[1257] (Application example 2)

[1258] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1259] Conventional systems for creating medical information reports and discharge summaries simply extract and summarize information from electronic medical records, and are unable to adjust the output to take the user's emotions into account, making it difficult to respond to the needs of individual patients and customers. Furthermore, when dealing with customers in physical stores, there is also the problem of being unable to recognize the customer's emotions and provide optimal customer service methods or product suggestions accordingly.

[1260] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1261] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for recognizing a user's emotion, means for adjusting the output of the generating AI based on the recognized emotion, and means for supporting customer service in physical stores. This makes it possible to create medical information reports and discharge summaries that take the user's emotion into consideration, and also enables optimal customer service methods and product suggestions in physical stores according to the customer's emotion.

[1262] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1263] "Means for extracting information" refers to the technology or equipment used to extract the necessary information from electronic medical records.

[1264] "Generative AI" is a technology that uses artificial intelligence to generate text and data based on input information.

[1265] A "summarization means" is a technique or device for concisely summarizing extracted information.

[1266] "Means for providing" refers to the technology or device for presenting the summarized information to the user.

[1267] "Means for recognizing user emotions" refers to technology or devices for determining emotions from the user's tone of voice, facial expressions, etc.

[1268] "Means for adjusting output" refers to technologies or devices that change the output content of the generative AI based on recognized emotions.

[1269] "Means for supporting customer service in brick-and-mortar stores" refer to technologies and devices for supporting dialogue with customers and the provision of services in brick-and-mortar stores.

[1270] The system for implementing this invention has the functions of extracting information from electronic medical records, summarizing it using generative AI, and adjusting the output by recognizing the user's emotions. Specific embodiments of this system are described below.

[1271] First, the server extracts information from the electronic medical record. The electronic medical record contains detailed records of the patient's medical history, and technology and devices are used to extract the necessary information based on this information. Specifically, an electronic medical record information extraction module is used.

[1272] Next, the extracted information is input into generative AI, a technology that uses artificial intelligence to generate text and data based on the input information. OpenAI's API is used here. The generative AI summarizes the extracted information and generates medical information reports and discharge summaries.

[1273] Furthermore, an emotion recognition engine is used to recognize the user's emotions. An emotion recognition engine is a technology or device that determines emotions from the user's tone of voice, facial expressions, etc. Specifically, the Emotion Engine is used. Once the user's emotions are recognized, the output content of the generation AI is adjusted based on those emotions.

[1274] Finally, a means will be provided to support customer service in physical stores. In physical stores, when a store clerk interacts with a customer, the AI ​​recognizes the customer's emotions and generates optimal customer service methods and product suggestions in real time based on those emotions. For this purpose, mobile devices such as smartphones and tablets are used.

[1275] As a specific example, a medical information report can be generated by inputting the following prompt sentence into a generative AI model.

[1276] Please generate a medical information form based on the information below.

[1277] Information: The patient is a 45-year-old man with diabetes and hypertension. Recent laboratory results show high blood sugar and elevated blood pressure.

[1278] User Emotion: Delight

[1279] Using this prompt, the AI ​​can generate a detailed medical information report for the patient.

[1280] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1281] Step 1:

[1282] The server extracts information from the electronic medical record. Specifically, it uses an electronic medical record information extraction module to extract the patient's medical information. The input for this process is the electronic medical record data, and the output is the extracted medical information.

[1283] Step 2:

[1284] The server inputs the extracted information into the generation AI, which uses OpenAI's API to generate a medical information report and discharge summary based on the input information. The input for this process is the extracted medical information, and the output is the generated medical information report and discharge summary.

[1285] Step 3:

[1286] The device recognizes the user's emotions. Specifically, it uses the Emotion Engine to determine emotions from the user's tone of voice and facial expressions. The input for this process is the user's voice data and facial data, and the output is the recognized emotion.

[1287] Step 4:

[1288] The server adjusts the output of the generation AI based on the recognized emotion. Specifically, it generates a prompt sentence according to the emotion and inputs it back into the generation AI. The inputs to this process are the recognized emotion and the initial output of the generation AI, and the output is an adjusted medical information form or discharge summary.

[1289] Step 5:

[1290] The terminal supports customer service in physical stores. Specifically, it provides optimal customer service methods and product suggestions in real time based on the adjusted medical information report and discharge summary. The input for this process is the adjusted medical information report and discharge summary, and the output is the customer service methods and product suggestions provided to the customer.

[1291] Example 3

[1292] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1293] The document preparation work of doctors in medical institutions is very time-consuming and labor-intensive, contributing to overwork. Furthermore, doctors may feel emotional stress when summarizing patients' medical records. This can lead to reduced efficiency and delayed responses to patients. Furthermore, because the summary content is uniform, it is difficult for doctors to respond flexibly according to their emotions and circumstances.

[1294] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1295] In this invention, the server includes means for extracting information from electronic medical records, means for a generative AI model that summarizes the extracted information, means for providing the summarized content, means for an emotion engine that recognizes the user's emotions, and means for adjusting the output of the generative AI model based on information from the emotion engine. This reduces the burden on doctors in document preparation work and enables flexible summaries to be provided according to emotions.

[1296] An "electronic medical record" is a system that electronically manages medical information such as patient medical records, test results, and prescription information.

[1297] "Means of extracting information" refers to the methods and techniques used to obtain the necessary data from electronic medical records.

[1298] A "generative AI model" is an artificial intelligence algorithm or system that generates summaries or other text based on input information.

[1299] "Means for providing summarized content" refers to the methods and techniques for displaying the generated summary to a user or transmitting it to another system.

[1300] The "emotion engine" is a system that recognizes emotions from the user's tone of voice, facial expressions, etc., and analyzes that information.

[1301] "Means for adjusting the output of a generative AI model based on information from an emotion engine" refers to methods and technologies for changing the output content of a generative AI model in accordance with the emotional state of a user recognized by the emotion engine.

[1302] MODE FOR CARRYING OUT THE INVENTION

[1303] This invention is a system that extracts information from electronic medical records at medical institutions and summarizes that information. It also has the function of recognizing the user's emotions and adjusting the summary content accordingly. A specific embodiment of this system is described below.

[1304] server

[1305] The server accesses the medical institution's electronic medical record system and extracts the necessary information. Specifically, the server uses the API of the electronic medical record system (e.g., EPIC, Cerner) to obtain data such as patient medical records, test results, and prescription information. The obtained data is input into a generative AI model (e.g., OpenAI's GPT-4).

[1306] The server creates a prompt for the generative AI model and requests it to generate a summary. For example, the server sends the following prompt to the generative AI model:

[1307] "Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu"

[1308] The generative AI model generates a summary based on the input information and returns the summary to the server, which then sends the generated summary to the medical institution's terminal.

[1309] Terminal

[1310] The terminal is a computer or tablet used within the medical institution. The terminal receives the summary sent from the server and displays it on the screen. The doctor can check the summary through the terminal and enter corrections or additional information as necessary.

[1311] The device is also equipped with an emotion engine that uses a camera and microphone to recognize the user's tone of voice and facial expressions. The emotion engine analyzes the user's emotional state and sends that information to the server. For example, if the user looks anxious, the emotion engine sends that information to the server.

[1312] User

[1313] The user (doctor) uses a terminal to check the summary of the electronic medical record. If the user feels anxious or stressed, the emotion engine recognizes that emotion and notifies the server. The server adjusts the output of the generative AI model based on the information from the emotion engine, providing a more detailed and easy-to-understand summary.

[1314] For example, send the following prompt to the generative AI model:

[1315] "Please provide a clear and concise explanation as users are feeling anxious. Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu."

[1316] In this way, the system can improve the efficiency of document preparation work by doctors and provide flexible responses according to the user's feelings. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1317] Step 1:

[1318] The server accesses the medical institution's electronic medical record system and extracts the necessary information. Specifically, the server uses the electronic medical record system's API to obtain data such as patient medical records, test results, and prescription information. The input is data from the electronic medical record system, and the output is the extracted patient information.

[1319] Step 2:

[1320] The server inputs the extracted information into the generative AI model. Specifically, the server creates a prompt sentence based on the extracted data and sends it to the generative AI model. The input is the extracted patient information, and the output is the prompt sentence sent to the generative AI model. For example, the following prompt sentence is generated:

[1321] "Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu"

[1322] Step 3:

[1323] The generative AI model generates a summary based on the input prompt. The input is the prompt, and the output is the generated summary. The generated summary is returned to the server.

[1324] Step 4:

[1325] The server sends the generated summary to the medical institution's terminal. Specifically, the server sends the generated summary to the terminal in JSON format. The input is the generated summary, and the output is the summary data sent to the terminal.

[1326] Step 5:

[1327] The terminal receives the summary sent from the server and displays it on the screen. The input is the summary data sent from the server, and the output is the summary content displayed on the screen. The doctor can check the summary through the terminal and enter corrections or additional information as necessary.

[1328] Step 6:

[1329] The device uses a camera and microphone to recognize the doctor's tone of voice and facial expressions. Specifically, the device analyzes the data acquired from the camera and microphone in real time to determine the doctor's emotional state. The input is data from the camera and microphone, and the output is the analyzed emotional state.

[1330] Step 7:

[1331] The emotion engine sends the analyzed emotional state to the server. The input is the analyzed emotional state and the output is the emotion data sent to the server.

[1332] Step 8:

[1333] The server adjusts the output of the generative AI model based on information from the emotion engine. Specifically, the server creates and sends a new prompt to the generative AI model. The input is emotion data from the emotion engine, and the output is the adjusted prompt. For example, the server generates the following prompt:

[1334] "Please provide a clear and concise explanation as users are feeling anxious. Please summarize the medical record of Patient A. Patient ID: A123, Visit Date: October 1, 2023, Symptoms: Fever, Cough, Diagnosis: Influenza, Prescription: Tamiflu."

[1335] Step 9:

[1336] The generative AI model generates a new summary based on the adjusted prompt. The input is the adjusted prompt, and the output is the newly generated summary. The generated summary is returned to the server.

[1337] Step 10:

[1338] The server sends the newly generated summary to the terminal. The input is the newly generated summary, and the output is the summary data sent to the terminal. The terminal receives the new summary sent from the server and displays it on the screen. The doctor can check the new summary through the terminal and enter corrections or additional information as necessary.

[1339] In this way, the system can streamline doctors' paperwork and provide flexible responses that respond to users' emotions.

[1340] (Application example 3)

[1341] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1342] Traditional document preparation work in medical institutions places a heavy burden on doctors and causes excessive work. In factories, the collection and summarization of work data and the provision of feedback based on workers' emotions are not efficiently carried out, resulting in reduced work efficiency and increased worker stress. To solve these issues, a system that integrates information extraction and summarization with emotion recognition is needed.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1344] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for collecting work data, means for generating AI to summarize the collected data, means for recognizing the emotions of workers, and means for adjusting the output of the generating AI according to the emotions. This reduces the burden of document preparation work at medical institutions, improves work efficiency in factories, and reduces worker stress.

[1345] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1346] "Means of extracting information" refers to the technology and equipment used to extract the necessary data from electronic medical records and sensors.

[1347] "Generative AI" is a technology that uses artificial intelligence to summarize and generate input data.

[1348] A "summarization means" is a technique or device for concisely summarizing extracted information.

[1349] The "means for providing the summarized content" refers to a technique or device for providing the generated summary to the user.

[1350] "Work data" refers to various data related to work within a factory.

[1351] "Means for collecting work data" refers to technologies and devices that collect work data using sensors and cameras within the factory.

[1352] "Means for recognizing the emotions of workers" refers to technology or devices that analyze the tone of voice and facial expressions of workers to recognize their emotions.

[1353] "Means for adjusting the output of the generative AI according to emotions" refers to technology or devices that change the output content of the generative AI based on recognized emotions.

[1354] The system for implementing this invention has the functions of extracting information from electronic medical records, generating summaries using generative AI, and providing those summaries. It also includes the functions of collecting work data in a factory, generating summaries, and recognizing the emotions of workers and adjusting feedback accordingly.

[1355] Hardware and software used

[1356] Hardware:

[1357] Camera: Used to capture the facial expressions of the workers.

[1358] Microphone: Used to capture the worker's tone of voice.

[1359] Sensors: Used to collect operational data within the factory.

[1360] software:

[1361] OpenCV: Used to process camera images.

[1362] transformers: Used to run generative AI models.

[1363] emotion_recognition: Used as an emotion recognition engine.

[1364] Data processing and calculation

[1365] The server first collects data from electronic medical records and sensors in the factory. The collected data is input into a generative AI model to generate a summary. Next, a camera and microphone are used to capture the worker's facial expressions and tone of voice, which are then analyzed by an emotion recognition engine. Based on the recognized emotions, the generative AI's output is adjusted, and final feedback is provided to the worker.

[1366] Specific examples

[1367] For example, work data in a factory, such as temperature, humidity, and machine operation status, is collected. This data is input into a generative AI model, which summarizes the progress and problems of the work. If a worker is feeling anxious, the emotion recognition engine will recognize that emotion, and the generative AI will be adjusted to provide more considerate feedback.

[1368] Prompt Sentence Examples

[1369] "Summarize the work data from within the factory. If workers are feeling uneasy, provide polite feedback."

[1370] In this way, the burden of paperwork at medical institutions can be reduced, and work efficiency at factories can be improved and stress on workers can be reduced.

[1371] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1372] Step 1:

[1373] The server collects data from electronic medical records and sensors in the factory. The electronic medical records provide patient medical information, while the sensors provide operational data such as temperature, humidity, and machine operation status in the factory. This data is then input into the server.

[1374] Step 2:

[1375] The server inputs the collected data into a generative AI model to generate summaries. Medical information reports and discharge summaries are generated from electronic medical record data, while summaries of work progress and issues are generated from factory work data. The generated summaries are output to the server.

[1376] Step 3:

[1377] The server uses a camera and microphone to capture the facial expressions and tone of voice of the worker, and this data is input into the server.

[1378] Step 4:

[1379] The server inputs the captured facial expression and tone data into an emotion recognition engine to recognize the worker's emotions. The emotion recognition engine analyzes the input data and outputs the worker's emotions (e.g., anxiety, joy, anger, etc.).

[1380] Step 5:

[1381] The server adjusts the output of the AI ​​based on the recognized emotion. For example, if the worker is feeling anxious, the AI ​​will be adjusted to provide more polite feedback. This adjusted feedback is output to the server.

[1382] Step 6:

[1383] The server provides the adjusted feedback to the worker, which is displayed on the worker's device or transmitted via voice, allowing the worker to receive appropriate instructions and feedback.

[1384] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1385] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1386] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1387] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1388] [Third embodiment]

[1389] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1390] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1391] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[1392] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1393] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1394] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1395] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1396] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1397] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[1398] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1399] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1400] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1401] "Example 1"

[1402] The system of the present invention contracts with medical institutions and provides a generation AI service that extracts information from electronic medical records and summarizes the contents. Specifically, it includes a means for extracting necessary information from electronic medical records, a generation AI means for summarizing the extracted information, and a means for providing the summarized contents.

[1403] "Example 2"

[1404] Generative AI is used to create medical information reports and discharge summaries. Specifically, it automatically generates medical information reports and discharge summaries based on information extracted from electronic medical records.

[1405] "Example 3"

[1406] This system is provided under contract with medical institutions. Specifically, based on the contract, it extracts and summarizes information from electronic medical records and provides the summary content. This reduces the burden of document preparation on doctors and solves the problem of overwork.

[1407] The processing flow of each embodiment will be described below.

[1408] "Example 1"

[1409] Step 1: Sign a contract with the medical institution.

[1410] Step 2: Based on the contract, extract the necessary information from the electronic medical record.

[1411] Step 3: Input the extracted information into the generative AI to generate a summary.

[1412] Step 4: Provide the generated summary to the medical institution.

[1413] "Example 2"

[1414] Step 1: Extract the necessary information from the electronic medical record.

[1415] Step 2: The extracted information is input into the generation AI, and a medical information report and discharge summary are automatically generated.

[1416] Step 3: Provide the generated medical information report and discharge summary to the medical institution.

[1417] "Example 3"

[1418] Step 1: Sign a contract with the medical institution.

[1419] Step 2: Based on the contract, information is extracted from the electronic medical record, summarized, and the summary content is provided.

[1420] Step 3: This will reduce the burden of paperwork on doctors and solve the problem of overwork.

[1421] Example 1

[1422] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1423] Conventional medical institutions rely on electronic medical record systems to manage medical information, but it is difficult to quickly extract and summarize the necessary information from the vast amount of data. Furthermore, the manual task of summarizing information by medical professionals requires time and effort, hindering efficient medical care. Furthermore, because the quality of the summary depends on the skill of the medical professional, it is difficult to provide consistent, high-quality summaries.

[1424] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1425] In this invention, the server includes means for extracting information from electronic medical records, means for preprocessing the extracted information, means for inputting the preprocessed information into a generative AI model to generate a summary, and means for providing the generated summary content. This makes it possible to quickly and accurately extract necessary information from electronic medical records, automatically generate consistent, high-quality summaries using the generative AI model, and provide them to medical professionals.

[1426] An "electronic medical record" is a system that electronically records and manages patient medical information at medical institutions.

[1427] "Means for extracting information" refers to methods and techniques for obtaining necessary medical information from the electronic medical record system.

[1428] "Preprocessing means" refers to methods or techniques for analyzing the extracted information and converting it into a form suitable for generating summaries.

[1429] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to summarize input information.

[1430] A "means for generating a summary" is a method or technology for inputting preprocessed information into a generative AI model and generating a summary.

[1431] The "means for providing summary content" refers to a method or technology for providing the generated summary text to medical professionals.

[1432] "Medical institution" means a facility that provides medical services, such as a hospital, medical office, or clinic.

[1433] A "medical information report" is a document used to provide details of a patient's medical treatment to other medical institutions and medical professionals.

[1434] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient's care, and is created when the patient is discharged from the hospital.

[1435] MODE FOR CARRYING OUT THE INVENTION

[1436] This invention is a system that contracts with medical institutions and provides a generative AI service that extracts information from electronic medical records and summarizes the content. A specific embodiment of this system will be described below.

[1437] System configuration

[1438] The server has the following main functions:

[1439] 1. Information extraction from electronic medical records:

[1440] The server accesses the medical institution's electronic medical record system (e.g., EPIC, Cerner) and extracts necessary data such as patient medical information, test results, and prescription information.

[1441] Specifically, it uses an API to retrieve data from the electronic medical record system.

[1442] 2. Information preprocessing:

[1443] The server preprocesses the acquired medical information.

[1444] Specifically, the server analyzes the acquired data and extracts the necessary information (diagnosis name, test results, prescribed medications, etc.).

[1445] 3. Information summary generation:

[1446] The server inputs the preprocessed information into a generative AI model (e.g., OpenAI's GPT-4) to generate a summary.

[1447] The generative AI model uses natural language processing techniques to summarize the extracted information in a concise, easy-to-understand format.

[1448] 4. Providing Abstract Content:

[1449] The server transmits the generated summary to a terminal at the medical institution.

[1450] The terminal displays the summary to the medical professional.

[1451] Specific examples

[1452] Information extraction from electronic medical records:

[1453] The server retrieves patient A's medical records from the EPIC system via the API.

[1454] The data collected includes diagnosis, test results, and prescription medication information.

[1455] Information preprocessing:

[1456] The server extracts information such as "high blood pressure," "blood pressure measurement result 120 / 80 mmHg," and "losartan 50 mg" from the medical records.

[1457] Generate summary of information:

[1458] The server then feeds the extracted information into a GPT-4 model to generate a summary like this:

[1459] Prompt: "Please summarize the following medical record. Include diagnosis, test results, and prescription information."

[1460] Input data: "Patient A, October 1, 2023, hypertension, blood pressure measurement result 120 / 80 mmHg, losartan 50 mg once daily"

[1461] The generative AI model generates a summary sentence.

[1462] Example: "Patient A is being treated for hypertension diagnosed on October 1, 2023, with their most recent blood pressure reading of 120 / 80 mmHg. They are currently taking Losartan 50 mg once daily."

[1463] Summary content provided by:

[1464] The server transmits the generated summary to a terminal at the medical institution.

[1465] The terminal displays the summary for medical personnel to review.

[1466] In this way, the server extracts information from the electronic medical record, generates a summary using the generative AI model, and provides it to medical professionals via their devices, allowing them to quickly and accurately grasp the patient's medical information and provide efficient medical care.

[1467] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1468] Step 1:

[1469] Information extraction from electronic medical records

[1470] The server accesses the medical institution's electronic medical record system. Specifically, the server uses the API key to authenticate to the electronic medical record system, and then sends an API request specifying the patient ID to retrieve the medical record. The input is the patient ID, and the output is the medical record data. The server saves the medical record received as an API response in its database.

[1471] Step 2:

[1472] Preprocessing of extracted information

[1473] The server runs a script to parse the stored medical records. Specifically, the server uses regular expressions and natural language processing techniques to extract necessary information such as diagnosis, test results, and prescription medications. The input is the medical record data, and the output is preprocessed information (diagnosis, test results, prescription medications, etc.).

[1474] Step 3:

[1475] Information summary generation

[1476] The server inputs the preprocessed information into the generative AI model. Specifically, the server converts the preprocessed information into JSON format and sends an API request to the generative AI model. The input is the preprocessed information, and the output is a generated summary. The generative AI model uses natural language processing technology to summarize the input information in a concise, easy-to-understand format.

[1477] Step 4:

[1478] Providing summary content

[1479] The server creates an API response to send the generated summary to the medical institution's terminal. Specifically, the server returns the generated summary to the terminal as an API response. The input is the generated summary, and the output is the API response to the terminal. The terminal executes code to display the received summary on a user interface, and displays the summary so that the medical professional can check it.

[1480] (Application example 1)

[1481] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1482] Conventional electronic medical records management in medical institutions contain a huge amount of information, making it difficult to quickly extract and summarize the necessary information. Furthermore, there was a lack of tools to understand the security status of patient data and take appropriate measures. This meant that medical institution security personnel could not perform their work efficiently, potentially increasing security risks.

[1483] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1484] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI summarizing the extracted information, means for providing the summarized content, means for generating a security report from the extracted information, and means for displaying the generated security report, which enables security personnel at medical institutions to quickly grasp the security status of patient data and take appropriate measures.

[1485] An "electronic medical record" is a system that electronically records and manages patient medical information at medical institutions.

[1486] "Means for extracting information" refers to techniques and methods for automatically extracting necessary information from electronic medical records.

[1487] "Generative AI" is a system that uses artificial intelligence technology to generate new information based on input data.

[1488] "Summarization methods" are techniques or methods for concisely summarizing extracted information.

[1489] "Means of delivery" refers to the technology or method used to display or deliver the summarized information to the user.

[1490] A "security report" is a document that evaluates and reports the security status of patient data based on extracted information.

[1491] "Displaying means" refers to the technology or method for presenting the generated security report in a form that can be viewed by a user.

[1492] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The function of each element will be explained below.

[1493] server

[1494] The server extracts information from the electronic medical records, summarizes that information using generative AI, and generates a security report. Specifically, it performs the following processes:

[1495] 1. Information extraction from electronic medical records:

[1496] The server connects to the medical institution's electronic medical record system and obtains the necessary information through the API. To do this, it uses the requests library to send an HTTP request and obtain the electronic medical record data.

[1497] 2. Summary of information:

[1498] The extracted information is then summarized using OpenAI's generative AI model (e.g., GPT-3), which extracts key information from the input medical data and generates a concise summary.

[1499] 3. Generate security reports:

[1500] The summarized information is formatted into a security report that assesses the security status of patient data and identifies necessary measures.

[1501] Terminal

[1502] The terminal is responsible for providing the generated security report to the user. Specifically, a device such as a smartphone or tablet is used.

[1503] 1. View the report:

[1504] The device receives the security report sent from the server and displays it in a format that can be viewed by the user, allowing the user to quickly understand the security situation and take necessary measures.

[1505] User

[1506] The user is a security officer at a medical institution, and is responsible for evaluating the security status of patient data based on the generated security report and taking appropriate measures.

[1507] Specific examples

[1508] For example, the following medical data is extracted from electronic medical records:

[1509] Patient ID: 12345

[1510] Medical Record: On October 1, 2023, the patient presented with a headache. An MRI scan confirmed a mild concussion. Prescriptions included pain medication and rest.

[1511] Based on this data, a generative AI model generates a summary like this:

[1512] Patient ID: 12345

[1513] Medical Record Summary: On October 1, 2023, the patient complained of a headache and was diagnosed with a mild concussion. Prescriptions included pain medication and rest.

[1514] Based on this summary, a security report is generated and displayed on the terminal, allowing the user to view the report and take necessary security measures.

[1515] In this way, the server, terminal, and user can work together to quickly and efficiently manage the security status of medical data.

[1516] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1517] Step 1:

[1518] The server connects to the medical institution's electronic medical record system and obtains the necessary information through the API. Specifically, it uses the requests library to send an HTTP request and obtain the electronic medical record data. The input is the API endpoint and authentication token, and the output is the raw data obtained from the electronic medical record.

[1519] Step 2:

[1520] The server formats the acquired raw data to input into the generative AI model. Specifically, it extracts the necessary information and generates prompt sentences. The input is raw data acquired from the electronic medical record, and the output is prompt sentences to input into the generative AI model.

[1521] Step 3:

[1522] The server uses a generative AI model (e.g., GPT-3) to generate a summary based on the prompt. Specifically, it calls the OpenAI API, sends the prompt, and retrieves the summary. The input is the prompt, and the output is the generated summary.

[1523] Step 4:

[1524] The server generates a security report based on the generated summary. Specifically, it applies the summary to a security assessment template to create a report. The input is the generated summary, and the output is the security report.

[1525] Step 5:

[1526] The server sends the generated security report to the terminal. Specifically, it sends the report as an HTTP response. The input is the security report, and the output is the report sent to the terminal.

[1527] Step 6:

[1528] The terminal displays the received security report to the user. Specifically, the report is displayed on the screen of a smartphone or tablet. The input is the security report sent from the server, and the output is the report displayed in a format that can be viewed by the user.

[1529] Step 7:

[1530] Based on the displayed security report, the user evaluates the security status of patient data and takes necessary measures. Specifically, the user checks the contents of the report and implements measures if there are any security risks. The input is the displayed security report, and the output is the security measures taken by the user.

[1531] Example 2

[1532] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1533] Traditionally, medical professionals have often manually created medical information forms and discharge summaries, which is time-consuming and labor-intensive. Manual input errors and information omissions can occur, creating a risk that patient medical information may not be accurately communicated. Furthermore, the process of extracting information from electronic medical records and generating documents is not automated, resulting in inefficiencies and increasing the burden on medical professionals.

[1534] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1535] In this invention, the server includes: means for extracting information from an electronic medical record; means for storing the extracted information in a database; means for generating a medical information report or discharge summary for the target patient using a prompt statement instructing the user to generate a medical information report or discharge summary based on the stored information about the target patient and a generative AI model; and means for presenting the generated medical information report or discharge summary to a user who is a medical professional and accepting revisions. This automates the process of creating medical information reports and discharge summaries, reducing the burden on medical professionals and enabling accurate and efficient information transmission. The generating means in the server saves the generated medical information report or discharge summary in PDF format or Word format, and the accepting means presents the medical information report or discharge summary saved in PDF format or Word format to the user who is a medical professional and accepting revisions. The extracting means in the server obtains diagnosis, treatment details, test results, and prescription drug data from the electronic medical record.

[1536] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1537] "Means for extracting information" refers to methods and techniques for obtaining necessary medical information from electronic medical records.

[1538] A "database" is a system for systematically storing and managing extracted information.

[1539] A "generative AI model" is a model that uses artificial intelligence to perform natural language processing and generate medical information reports and discharge summaries.

[1540] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[1541] A "medical information report" is a document used to provide a patient's medical information to other medical institutions and doctors.

[1542] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient's care, and is created when the patient is discharged from the hospital.

[1543] "PDF format" is an abbreviation for Portable Document Format, a file format for electronically storing and displaying documents.

[1544] "Word format" is a document file format created with Microsoft (registered trademark) Word.

[1545] A "terminal" is a device such as a computer or tablet used by a user.

[1546] "User" refers to a medical professional who uses this system to check and modify medical information reports and discharge summaries.

[1547] This invention is a system that extracts information from electronic medical records and automatically generates medical information reports and discharge summaries using a generative AI model. Specific embodiments of this system are described below.

[1548] The server accesses an electronic medical record system (e.g., a general electronic medical record system) and extracts the patient's medical information. Specifically, it uses an API to obtain data such as diagnosis, treatment details, test results, and prescribed medications. This data is then stored in a database (e.g., a general database system).

[1549] Next, the server retrieves the stored data and inputs it into a generative AI model (e.g., a general generative AI model). At this time, it generates a prompt sentence to give the model specific instructions. An example of a prompt sentence is the following format:

[1550] Please prepare a medical information form based on the patient's medical information below. <Patient medical information> Patient name: Taro Yamada Diagnosis: Hypertension Treatment: Administration of antihypertensive drugs Test results: Blood pressure 140 / 90 mmHg Prescription medication: Losartan 50mg

[1551] The generative AI model generates medical information reports and discharge summaries based on the input data. The generated documents are saved in PDF or Word format by the server, and then sent to a device (e.g., a standard computer or tablet).

[1552] The user can review the generated document through the terminal, make corrections or add additional information to the document as needed, and once corrections are complete, save the final document and print it if necessary.

[1553] This system automates the process of creating medical information forms and discharge summaries, reducing the burden on medical professionals and enabling accurate and efficient information transmission.

[1554] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1555] Step 1:

[1556] The server accesses the electronic medical record system and extracts the patient's medical information. Specifically, it uses an API to obtain data such as the diagnosis, treatment, test results, and prescribed medications. The input is the medical information from the electronic medical record system, and the output is the extracted medical information. The server obtains the required data by sending a request such as GET / api / patient / {patient_id} / records.

[1557] Step 2:

[1558] The server saves the extracted medical information in a database. The input is the extracted medical information, and the output is the information saved in the database. Specifically, it executes the following SQL query: INSERT INTO patient_records (patient_id, diagnosis, treatment, test_results, medications) VALUES (?, ?, ?, ?, ?).

[1559] Step 3:

[1560] The server retrieves the necessary data from the database and inputs it into the generative AI model. The input is the medical information retrieved from the database, and the output is the prompt statement to be input into the generative AI model. Specifically, it executes the SQL query SELECT diagnosis, treatment, test_results, medications FROM patient_records WHERE patient_id = ? and embeds the retrieved data into the prompt statement.

[1561] Step 4:

[1562] The server uses a generative AI model to generate medical information reports and discharge summaries. The input is a prompt and medical information, and the output is the generated document. The generative AI model is sent a prompt like this:

[1563] Please prepare a medical information form based on the patient's medical information below. <Patient medical information> Patient name: Taro Yamada Diagnosis: Hypertension Treatment: Administration of antihypertensive drugs Test results: Blood pressure 140 / 90 mmHg Prescription medication: Losartan 50mg

[1564] Step 5:

[1565] The server saves the generated document in PDF or Word format. The input is the generated document, and the output is a PDF or Word file. Specifically, a library (e.g., iText, Apache (registered trademark) POI) is used to generate the document and save it in the file system.

[1566] Step 6:

[1567] The server sends the generated document to the terminal. The input is a PDF or Word file, and the output is the document sent to the terminal. Specifically, the document is sent as an HTTP response, and the header Content-Disposition: attachment; filename="report.pdf" is set.

[1568] Step 7:

[1569] The user opens the received document on the terminal and checks its contents. The input is the document sent to the terminal and the output is the checked document. The user uses a text editor (e.g., a standard text editor) to enter corrections and additional information into the document as needed. Once corrections are complete, the user saves the final document and prints it if necessary.

[1570] (Application example 2)

[1571] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1572] In conventional medical systems, the task of extracting information from electronic medical records and creating medical information reports and discharge summaries is done manually, which is time-consuming and labor-intensive. Similarly, in security systems, the analysis of log data and video data and the creation of reports are done manually, making it difficult to respond quickly. To solve these problems, a system that automates information extraction, summarization, and report generation is needed.

[1573] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1574] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for extracting log data and video data collected from a security system, means for generating AI to summarize the extracted log data and video data, means for generating a security report based on the summarized log data and video data, and means for providing the generated security report. This not only enables the automatic generation of medical information notification forms and discharge summaries, but also enables the rapid generation and provision of security reports.

[1575] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1576] "Means for extracting information" refers to the technology and devices used to extract necessary data from electronic medical records and security systems.

[1577] "Generative AI" is a system that uses artificial intelligence technology to summarize data and automatically generate reports and documents.

[1578] A "summarization means" is a technique or device for concisely summarizing extracted information.

[1579] "Means of delivery" refers to the technology or device used to communicate the generated summary or report to the user.

[1580] A "security system" is a monitoring and defense mechanism for ensuring the safety of facilities and information systems.

[1581] "Log data" is data that records system operations and access history.

[1582] "Video data" refers to video information captured by a surveillance camera or the like.

[1583] A "security report" is a report prepared based on data collected from a security system.

[1584] To put the present invention into practice, it is necessary to build a system in which the elements of the server, terminal, and user work together. A specific embodiment of this system is shown below.

[1585] Server Roles

[1586] The server extracts information from electronic medical records and summarizes it using generative AI. It also extracts log data and video data collected from security systems and summarizes them to generate security reports. The server uses the following hardware and software:

[1587] Hardware: Powerful processor, ample memory, and storage

[1588] Software: Python, OpenAI API

[1589] Device Role

[1590] The terminal provides an interface for providing the generated summaries and reports to the user. The terminal is a mobile device such as a smartphone or tablet, and is designed for easy user access.

[1591] User Roles

[1592] Users check the summaries and reports provided through the terminal and take action as necessary. For example, medical institution staff check the medical information form and discharge summary and explain the situation to the patient. Security personnel also check the security report and take necessary measures.

[1593] Data processing and calculation

[1594] The server extracts data from electronic medical records and security systems and summarizes it using a generative AI model, which uses prompts like the following to input data:

[1595] Prompt Sentence Examples

[1596] Please create a security report using the following information:

[1597] Summary of log data:

[1598] 2023-10-01 12:00:00 - Unauthorized access detected

[1599] Video data summary:

[1600] 2023-10-01 12:05:00 - Suspicious person entered building

[1601] Based on this prompt, the generative AI model generates a security report, which is then provided to the user via their device.

[1602] Specific examples

[1603] For example, in medical institutions, generation AI can automatically generate medical information forms and discharge summaries based on patient medical information extracted from electronic medical records, reducing the burden on medical staff and enabling them to provide information quickly and accurately.

[1604] Additionally, security systems can detect suspicious activity from log data and video data and generate security reports summarizing the details, allowing security personnel to quickly take countermeasures.

[1605] In this way, the present invention automates the extraction, summarization, and provision of information in the medical and security fields, thereby realizing efficient business operations.

[1606] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1607] Step 1:

[1608] The server extracts information from the electronic medical record.

[1609] Input: Electronic medical record data

[1610] Output: Extracted medical information

[1611] Specific operation: The server accesses the electronic medical record system and obtains the patient's medical information, such as medical records, test results, and prescription information.

[1612] Step 2:

[1613] The server inputs the extracted medical information into a generative AI model to generate a summary.

[1614] Input: Extracted medical information

[1615] Output: Summarized medical information

[1616] Specific operation: The server creates a prompt for the generative AI model and instructs it to summarize the medical information. The generative AI model generates a medical information report and discharge summary based on the input information.

[1617] Step 3:

[1618] The server transmits the generated summary to the terminal.

[1619] Input: Summarized medical information

[1620] Output: Summary information sent to the terminal

[1621] Specific operation: The server sends the generated medical information report and discharge summary to the terminal so that medical staff can check them.

[1622] Step 4:

[1623] The server extracts log data and video data from the security system.

[1624] Input: Security system log data and video data

[1625] Output: Extracted log data and video data

[1626] Specific operation: The server accesses the security system and obtains log data and video data from surveillance cameras.

[1627] Step 5:

[1628] The server inputs the extracted log data and video data into a generative AI model to generate a summary.

[1629] Input: Extracted log data and video data

[1630] Output: Summarized log data and video data

[1631] Specific operation: The server creates prompts for the generative AI model and instructs it to summarize the log data and video data. The generative AI model then generates a security report based on the input information.

[1632] Step 6:

[1633] The server transmits the generated security report to the terminal.

[1634] Input: Summarized log data and video data

[1635] Output: Security report sent to the device

[1636] Specific operation: The server sends the generated security report to the terminal so that the security officer can check it.

[1637] Step 7:

[1638] The user checks the summary and report provided through the terminal and takes any necessary action.

[1639] Input: Summary information and security reports sent to the terminal

[1640] Output: User's response action

[1641] Specific operations: The user checks the medical information form, discharge summary, and security report displayed on the terminal, and provides explanations to the patient or takes security measures as necessary.

[1642] Example 3

[1643] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1644] In medical institutions, the burden of creating medical records is heavy for doctors, resulting in excessive work. In addition, creating medical information forms and discharge summaries requires a lot of time and effort, reducing the efficiency of doctors' work. This has led to problems such as a decline in the quality of medical care and fatigue among doctors.

[1645] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1646] In this invention, the server includes means for extracting information from electronic medical records, means for storing the extracted information in a database, means for inputting the stored information into a generative AI model to generate a summary, and means for providing the generated summary to a user, thereby enabling doctors to quickly summarize medical records and efficiently create medical information reports and discharge summaries.

[1647] An "electronic medical record" is a system for electronically managing patient medical records.

[1648] "Means of extracting information" refers to the methods and techniques used to extract the necessary data from electronic medical records.

[1649] A "database" is a collection of data that stores information systematically and can be retrieved as needed.

[1650] A "generative AI model" is an algorithm or system that uses artificial intelligence to process data and perform summarization or generation.

[1651] A "means for generating a summary" is a method or technology that uses a generative AI model to concisely summarize extracted information.

[1652] "Means for providing to users" refers to methods and techniques for providing the generated summary to doctors and other medical professionals in an easy-to-view format.

[1653] A "medical information report" is a document used to communicate the details of a patient's medical treatment to other medical institutions and doctors.

[1654] A "discharge summary" is a document that summarizes the medical treatment and progress of a patient when they are discharged from the hospital.

[1655] A "medical institution" is a facility that provides medical services, such as a hospital or clinic.

[1656] This invention is a system provided under a contract with a medical institution, which extracts information from electronic medical records, generates summaries, and provides them to users. A specific embodiment of this system will be described below.

[1657] The server first extracts information from the electronic medical record system. To do this, the server uses specific software (e.g., Apache Kafka) to retrieve the necessary data from the electronic medical record. The retrieved data is then stored in a database (e.g., MySQL).

[1658] Next, the server inputs the stored data into a generative AI model to generate a summary. OpenAI's GPT-4 is used for the generative AI model. Specifically, the server retrieves medical records from the database and sends a prompt to the generative AI model. For example, the server sends a prompt such as, "Please summarize the patient's medical record. Please include the following information: patient's name, age, diagnosis, prescribed medications, and next appointment date."

[1659] The generated summary is provided to the user, who can view the summary through a dedicated interface (e.g., a web application). The server updates the page using HTML and JavaScript to display the generated summary in the web application interface. The user then views the summary through a web browser.

[1660] As a concrete example, consider the following scenario.

[1661] scenario:

[1662] A user (doctor) wants to summarize a patient's medical record. The user accesses the electronic medical record system and inputs the medical record. The server retrieves the medical record and generates a summary.

[1663] Example prompt sentence:

[1664] "Please summarize the patient's medical record. Include the following information: patient's name, age, diagnosis, prescribed medications, and next appointment."

[1665] This system allows doctors to quickly obtain summaries of medical records and reduces the burden of paperwork. This solves the problem of doctors' overwork and contributes to improving the quality of medical care. The flow of the identification process in Example 3 will be explained using Figure 15.

[1666] Step 1:

[1667] A user enters medical records into an electronic medical record system.

[1668] Input: Patient medical information (name, age, diagnosis, prescribed medications, next appointment, etc.)

[1669] Output: Medical records stored in the electronic medical record system

[1670] Specific operation: The user enters the required information into the input form of the electronic medical record system and clicks the "Save" button.

[1671] Step 2:

[1672] The server retrieves medical records from the electronic medical record system.

[1673] Input: Medical records stored in the electronic medical record system

[1674] Output: Medical records retrieved to the server

[1675] Specific operation: The server sends a request to the electronic medical record system via the API to obtain new medical records.

[1676] Step 3:

[1677] The server stores the acquired medical records in a database.

[1678] Input: Medical records retrieved on the server

[1679] Output: Medical records stored in a database

[1680] Specific operation: The server inserts the retrieved medical records into the database using an SQL query.

[1681] Step 4:

[1682] The server inputs the stored data into a generative AI model to generate a summary.

[1683] Input: Medical records stored in a database

[1684] Output: The summary generated by the generative AI model

[1685] How it works: The server retrieves medical records from the database and sends a prompt to the generative AI model, such as "Please summarize the patient's medical record. Please include the following information: patient name, age, diagnosis, prescribed medications, and next appointment date."

[1686] Step 5:

[1687] The server provides the generated summary to the user.

[1688] Input: A summary generated by a generative AI model

[1689] Output: Summary provided to the user

[1690] Specific operation: The server updates the page using HTML and JavaScript to display the generated summary in the web application interface. The user can then view the summary through their web browser.

[1691] (Application example 3)

[1692] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1693] Conventional document preparation work in medical institutions places a heavy burden on doctors and causes excessive work. In factories, data management for manufacturing processes is also complicated, making efficient management difficult. To solve these issues, a system is needed that automates the extraction and summarization of information and provides it efficiently.

[1694] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1695] In this invention, the server includes means for extracting information from electronic medical records, means for generating AI to summarize the extracted information, means for providing the summarized content, means for collecting manufacturing process data, means for generating AI to summarize the collected manufacturing process data, and means for providing the summarized manufacturing process data. This reduces the burden of document preparation work at medical institutions and enables efficient management of manufacturing process data at factories.

[1696] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1697] "Means for extracting information" refers to the technology and equipment used to extract necessary information from electronic medical records and manufacturing process data.

[1698] "Generative AI" is a technology that uses artificial intelligence to summarize and generate information.

[1699] "Means of summarization" refers to techniques or devices for concisely summarizing extracted information.

[1700] A "means for providing summarized content" is a technique or device for providing summarized information to a user.

[1701] "Manufacturing process data" refers to data related to the manufacturing process in a factory.

[1702] "Means of collection" refers to technologies and devices for collecting manufacturing process data in real time.

[1703] The "means for providing summarized manufacturing process data" refers to a technique or device for providing summarized manufacturing process data to a manager.

[1704] In order to implement this invention, the server, terminal, and user must fulfill their respective roles. A specific embodiment will be described below.

[1705] Server Roles

[1706] The server extracts information from electronic medical records and summarizes it using a generative AI model. It also collects manufacturing process data from factories and summarizes it using a generative AI model. This summarized information is then provided to users.

[1707] The server uses the following hardware and software:

[1708] Hardware: powerful processor, sufficient memory, storage devices

[1709] Software: Python, Transformers library, Requests library

[1710] Device Role

[1711] The terminal receives the summary information provided by the server and displays it to the user. The terminal can be a smartphone, tablet, or PC.

[1712] User Roles

[1713] Users check the summary information provided through the terminal and take necessary actions. The main users are doctors at medical institutions and factory managers.

[1714] Data processing and calculation

[1715] The server extracts necessary information from electronic medical records and manufacturing process data and summarizes it using a generative AI model. Specifically, the following prompt sentence is input to the generative AI model:

[1716] Prompt Sentence Examples

[1717] "Please summarize the following manufacturing process data:

[1718] Machine 1 is in operation, has an output of 100, and has 2 errors.

[1719] Machine 2 is in a stopped state, with an output of 50 and 5 errors.

[1720] Machine 3's status is UP, output is 200, and there is 1 error.

[1721] A generative AI model summarizes this data and outputs a summary such as:

[1722] "Currently, two of the three machines are operational with a total output of 350. There have been a total of eight errors."

[1723] The server sends this summary information to the terminal, which then displays it to the user, allowing the user to quickly understand the situation and take appropriate action.

[1724] In this way, the burden of paperwork at medical institutions is reduced and efficient management of manufacturing process data at factories is achieved.

[1725] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1726] Step 1:

[1727] The server extracts information from the electronic medical record.

[1728] Input: Electronic medical record data

[1729] Output: Extracted medical information

[1730] Specific operation: The server accesses the electronic medical record system and obtains the patient's medical information, such as medical records and test results.

[1731] Step 2:

[1732] The server inputs the extracted medical information into a generative AI model to generate a summary.

[1733] Input: Extracted medical information

[1734] Output: Summarized medical information

[1735] Specific operation: The server converts the extracted medical information into text format and inputs it as a prompt to the generative AI model. The generative AI model summarizes the input information and generates concise medical information.

[1736] Step 3:

[1737] The server transmits the summarized medical information to the terminal.

[1738] Input: Summarized medical information

[1739] Output: Summary information sent to the terminal

[1740] Specific operation: The server transmits data over the network to send the generated summary information to the terminal, which receives the information and displays it to the user.

[1741] Step 4:

[1742] The server collects manufacturing process data within the factory.

[1743] Input: Manufacturing process data

[1744] Output: Collected manufacturing process data

[1745] Specific operation: The server collects data in real time from each machine in the factory, such as the machine's operating status, output, and error information.

[1746] Step 5:

[1747] The server inputs the collected manufacturing process data into a generative AI model to generate a summary.

[1748] Input: Collected manufacturing process data

[1749] Output: Summarized manufacturing process data

[1750] Specific operation: The server converts the collected manufacturing process data into text format and inputs it as a prompt to the generative AI model. The generative AI model summarizes the input information and generates concise manufacturing process data.

[1751] Step 6:

[1752] The server transmits the summarized manufacturing process data to the terminal.

[1753] Input: Summarized manufacturing process data

[1754] Output: Summary information sent to the terminal

[1755] Specific operation: The server transmits data over the network to send the generated summary information to the terminal, which receives the information and displays it to the user.

[1756] Step 7:

[1757] The user checks the summary information provided through the terminal and takes necessary actions.

[1758] Input: Summary information displayed on terminal

[1759] Output: User action

[1760] Specific operations: The user checks the summary information displayed on the terminal and decides on a patient's treatment plan based on the medical information, or takes action to optimize factory operations based on manufacturing process data.

[1761] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1762] "Example 1"

[1763] One embodiment of the present invention provides a system incorporating an emotion engine. This system includes a generation AI means for extracting information from electronic medical records and summarizing the extracted information, and a means for providing the summarized content. It also includes an emotion engine that recognizes the user's emotions. Specifically, the system recognizes emotions from the user's tone of voice and facial expressions, and adjusts the output of the generation AI according to those emotions. For example, if the user feels stressed, the generation AI takes that information into account and adjusts to provide a more concise summary.

[1764] "Example 2"

[1765] In another embodiment, a system is provided in which an emotion engine is used to create medical information reports and discharge summaries. This system extracts information from electronic medical records and inputs the extracted information into a generation AI to automatically generate medical information reports and discharge summaries. The system also includes an emotion engine that recognizes the user's emotions. Specifically, the system recognizes emotions from the user's tone of voice and facial expressions and adjusts the output of the generation AI according to those emotions. For example, if the system senses that the user is feeling happy, the generation AI takes that information into account and adjusts to provide a more detailed medical information report and discharge summary.

[1766] "Example 3"

[1767] In yet another embodiment, a system is provided in which an emotion engine is provided under a contract with a medical institution. This system extracts information from electronic medical records, inputs the extracted information into a generation AI to generate a summary, and provides the summary to the medical institution. It also includes an emotion engine that recognizes the user's emotions. Specifically, it recognizes emotions from the user's tone of voice and facial expressions and adjusts the output of the generation AI according to those emotions. For example, if the system senses that the user is feeling anxious, the generation AI takes that information into account and adjusts to provide a more detailed summary.

[1768] The processing flow of each embodiment will be described below.

[1769] "Example 1"

[1770] Step 1: The system extracts information from the electronic medical record.

[1771] Step 2: The extracted information is input into the generative AI, which generates a summary.

[1772] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[1773] Step 4: The output of the generative AI is adjusted depending on the recognized emotion.

[1774] "Example 2"

[1775] Step 1: The system extracts information from the electronic medical record.

[1776] Step 2: The extracted information is input into the generation AI, and a medical information report and discharge summary are automatically generated.

[1777] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[1778] Step 4: The output of the generative AI is adjusted depending on the recognized emotion.

[1779] "Example 3"

[1780] Step 1: The system extracts information from the electronic medical record.

[1781] Step 2: The extracted information is input into the generative AI, which generates a summary.

[1782] Step 3: The generated summary is provided to the medical institution.

[1783] Step 4: At the same time, the emotion engine recognizes the user's emotions from their tone of voice and facial expressions.

[1784] Step 5: The output of the generative AI is adjusted depending on the recognized emotion.

[1785] Example 1

[1786] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1787] Conventional electronic medical record systems have difficulty efficiently summarizing vast amounts of medical information and providing it to medical professionals. Furthermore, because they provide information without considering the user's feelings, they are unable to provide appropriate information to users who are stressed. This has led to issues such as reduced efficiency in medical settings and reduced user satisfaction.

[1788] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1789] In this invention, the server includes a means for extracting information from electronic medical records, a generating AI means for summarizing the extracted information, a means for providing the summarized content, a means for recognizing the user's emotion, and a means for adjusting the output of the generating AI based on the recognized emotion. This makes it possible to efficiently extract information from electronic medical records and provide appropriate summary information according to the user's emotion.

[1790] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1791] "Means of extracting information" refers to the functions and technologies used to extract the necessary information from electronic medical records.

[1792] "Generative AI" is a system that uses artificial intelligence technology to summarize input information.

[1793] "Means of summarization" refers to functions and technologies for concisely summarizing information extracted using generative AI.

[1794] "Means of providing" refers to the functions and technologies for displaying or conveying summarized information to the user.

[1795] "Means for recognizing emotions" refers to functions and technologies for determining emotions from the user's tone of voice, facial expressions, etc.

[1796] "Means for adjusting output" refers to functions and technologies that appropriately modify the summary results of the generative AI based on the recognized emotions.

[1797] MODE FOR CARRYING OUT THE INVENTION

[1798] This invention is a system that contracts with medical institutions and provides a generative AI service that extracts information from electronic medical records and summarizes that content. Specifically, it includes means for extracting necessary information from electronic medical records, generative AI means for summarizing the extracted information, means for providing the summarized content, means for recognizing user emotions, and means for adjusting the output of the generative AI based on the recognized emotions.

[1799] Hardware and software used

[1800] The server uses hardware and software to extract information from electronic medical record systems (e.g., EPIC, Cerner). The extracted information is sent to a generative AI model (e.g., OpenAI's GPT-4). The generative AI model uses natural language processing techniques to summarize the information. The summarized information is then sent to the device to be provided to the user.

[1801] Furthermore, an emotion engine (e.g., Affectiva, Microsoft Azure Emotion API) is used to recognize emotions from the user's tone of voice and facial expressions. The emotion information recognized by the emotion engine is fed back to the generative AI model via the server. The generative AI model adjusts the content of the summary based on this feedback.

[1802] Specific examples

[1803] The user logs in to a medical institution's terminal and enters the patient ID "12345." The server extracts the medical records of patient "12345" from the electronic medical record system. The extracted information is sent to the generative AI model and summarized. The summarized information is displayed on the terminal for the user to review. If the emotion engine recognizes that the user is feeling stressed from their tone of voice or facial expression, the server sends that information to the generative AI model. The generative AI model adjusts the summary to make it more concise and sends it back to the terminal via the server. The user then reviews the final summary.

[1804] Prompt Sentence Examples

[1805] "Please summarize the medical record for patient ID: 12345. If the user is stressed, please keep the summary brief."

[1806] In this way, the system can extract information from a medical institution's electronic medical records, summarize it using a generative AI model, and adjust the output according to the user's emotions.

[1807] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1808] Step 1:

[1809] A user logs in to a terminal.

[1810] The user logs in by entering their user ID and password into the medical institution's terminal. The entered user ID and password are sent from the terminal to the server for authentication. If authentication is successful, the user is able to access the system.

[1811] Step 2:

[1812] The user enters the patient ID.

[1813] The user inputs the ID of the patient they wish to summarize into the terminal. The input patient ID is sent from the terminal to the server. The server then searches the electronic medical record system for the corresponding patient's medical records based on this patient ID.

[1814] Step 3:

[1815] The server extracts information from the electronic medical record system.

[1816] The server accesses the electronic medical record system using the patient ID and extracts the medical records of the corresponding patient. The extracted medical records are temporarily stored on the server. The input is the patient ID and the output is the medical records.

[1817] Step 4:

[1818] The server sends the extracted information to the generative AI model.

[1819] The server sends the extracted medical records to the generative AI model, which receives the medical records and begins processing the data for summarization. The input is the medical records, and the output is the summary results.

[1820] Step 5:

[1821] A generative AI model summarizes the information.

[1822] The generative AI model summarizes the received medical records using natural language processing techniques. The summarized information is sent back to the server. The input is the medical records, and the output is the summarized information.

[1823] Step 6:

[1824] The server sends the summarized information to the terminal.

[1825] The server sends the summary information received from the generative AI model to the terminal, which displays the summary information to the user. The input is the summarized information, and the output is the display on the terminal.

[1826] Step 7:

[1827] The user reviews the summarized information.

[1828] The user checks the summary information displayed on the terminal. The user decides the next action based on the summary information. The input is the summarized information, and the output is the user's confirmation.

[1829] Step 8:

[1830] The emotion engine recognizes the user's emotions.

[1831] The emotion engine analyzes the user's tone of voice and facial expression to recognize the user's emotion. The recognized emotion information is sent to the server. The input is the user's tone of voice and facial expression, and the output is emotion information.

[1832] Step 9:

[1833] The server sends the emotion engine feedback to the generative AI model.

[1834] The server sends the emotion information received from the emotion engine to the generative AI model, which then adjusts the summary content based on this feedback. The input is emotion information, and the output is adjustment instructions.

[1835] Step 10:

[1836] A generative AI model refines the summary.

[1837] The generative AI model adjusts the content of the summary based on feedback from the emotion engine. For example, if the user is feeling stressed, the summary will be made more concise. The adjusted summary is then sent back to the server. The input is emotion information, and the output is the adjusted summary.

[1838] Step 11:

[1839] The server sends the adjusted summary to the terminal.

[1840] The server sends the adjusted summary received from the generative AI model to the device, which then displays the adjusted summary to the user. The input is the adjusted summary, and the output is the display on the device.

[1841] Step 12:

[1842] The user confirms the final summary.

[1843] The user confirms the final summary displayed on the terminal. The user decides the next action based on the final summary. The input is the adjusted summary, and the output is the user's confirmation.

[1844] (Application example 1)

[1845] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1846] Conventional electronic medical record systems require medical professionals to manually organize and summarize vast amounts of information, which is time-consuming and labor-intensive. Furthermore, they often provide information without considering the user's feelings, which can be stressful. This can lead to reduced efficiency in medical settings and delayed responses to patients.

[1847] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for extracting information from the electronic medical record, means for generating AI to summarize the extracted information, means for providing the summarized content, means for recognizing the user's emotion, and means for adjusting the output of the generating AI according to the recognized emotion. This makes it possible to efficiently summarize the information in the electronic medical record and provide appropriate information according to the user's emotion.

[1848] An "electronic medical record" is a system that electronically records and manages a patient's medical information.

[1849] "Means for extracting information" refers to a device or program that has the function of automatically extracting necessary information from electronic medical records.

[1850] "Generative AI" is a system that uses artificial intelligence technology to summarize and generate input information.

[1851] A "summarizing means" is a device or program that has the function of concisely summarizing extracted information.

[1852] The "means for providing" is a device or program that has the function of displaying or transmitting the summarized information to the user.

[1853] The "means for recognizing emotions" is a device or program that has the function of detecting emotions from the user's tone of voice, facial expression, etc.

[1854] A "means for adjusting output" is a device or program that has the function of changing the output content of the generating AI based on the recognized emotion.

[1855] A system for carrying out this invention has the following configuration: The syst...

Claims

1. A means for extracting information from an electronic medical record; a means for storing the extracted information in a database; A means for generating a medical report or discharge summary for a target patient using a prompt sentence instructing the generation of a medical report or discharge summary based on the stored information for the target patient and a generative AI model; A means for presenting the generated medical information report or discharge summary to a user who is a medical professional and accepting corrections; A system including:

2. The generating means stores the generated medical information report or discharge summary in a PDF format or a Word format, 2. The system according to claim 1, wherein the accepting means presents the medical information report or the discharge summary saved in a PDF format or a Word format to a user who is a medical professional and accepts corrections.

3. The system according to claim 1 , wherein the extracting means obtains data on diagnosis, treatment, test results, and prescription drugs from an electronic medical record.

Images