System

Abstract

A system is provided.SOLUTION: A system comprising means for receiving medical documents of different formats, means for analyzing data formats of the received medical documents and extracting metadata, means for storing the extracted metadata in a database, means for receiving a request for conversion into a unified format, means for acquiring document data based on the conversion request and transmitting the document data to a generated AI model, means for converting the medical documents of different formats into the unified format using the generated AI model, means for re-storing the converted document data in the database, and means for providing the document data of the unified format.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] The data formats of medical document templates, which are independently designed by different medical institutions and departments, are not standardized, making it difficult to efficiently utilize data, share data between different institutions, and combine data for medical research. If this problem is left unaddressed, data inconsistencies and duplications will likely occur in the medical field, potentially leading to a decline in the quality of medical care. Therefore, a technology is needed to convert medical documents in different formats into a unified format. [Means for solving the problem]

[0005] This invention provides a means for receiving medical documents in different formats, analyzing the data format, extracting metadata, and storing it in a database. It also provides a means for accepting a request for conversion to a unified format, sending document data to a generative AI model based on the conversion request, and using the generative AI model to convert medical documents in different formats into a unified format. It also includes a system for restoring the converted document data to a database and providing document data in a unified format. Using such a means makes it possible to unify the document formats of different medical institutions, thereby promoting efficient data utilization and medical research.

[0006] "Medical documents in different formats" refer to documents such as questionnaires, test results, and medical records that are designed independently by each medical institution or department, and are medical data that do not follow a standardized format.

[0007] A "generative AI model" refers to a large-scale generative language model, a technology that performs natural language processing based on input data and converts the format and content of documents.

[0008] "Metadata" refers to auxiliary information that accompanies a medical document, and includes, for example, the creation date and time, the creator, the name of the medical institution, and the type of document.

[0009] A "database" is an information aggregation system that allows stored data to be managed efficiently and securely.

[0010] A "unified format" is a format that standardizes and unifies the document formats used by different medical institutions and departments.

[0011] A "conversion request" refers to a request by a user to convert a medical document of a particular format into another format.

[0012] "Document data" refers to the content of medical documents themselves, and is digital data including patient information, case information, medical records, and test results.

[0013] "Terminal" refers to the device that a user uses to operate the system, such as a PC, tablet, or smartphone.

[0014] A "server" is a central computer that operates the entire system and is responsible for data processing and network management.

[0015] "User" refers to a medical professional or administrator who operates the system, and is a person who accesses the system to operate it or input data. [Brief explanation of the drawings]

[0016] [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. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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, a 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), and an APU (Accelerated Processing Unit).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. 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."

[0037] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[0038] System configuration

[0039] 1. Input of initial data (user):

[0040] The user operates the terminal to input document templates for each medical institution into the system. For example, a medical questionnaire from Clinic A and test results from Clinic B are uploaded to the system.

[0041] 2. Save to database (server):

[0042] The server receives medical documents uploaded by users, analyzes the data format, and extracts metadata, which are then stored in a database.

[0043] 3. Request for conversion to unified format (terminal):

[0044] The user operates the terminal to select the document to be converted and sends a request for conversion to the unified format to the server.

[0045] 4. Data transmission and conversion to the LLM model (server):

[0046] The server receives the conversion request, retrieves the target document data from the database, and then sends the document data and conversion rules to the generative AI model, which then analyzes the document and converts it into the specified unified format.

[0047] 5. Resave to unified format (server):

[0048] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[0049] 6. Provision of Unified Format Documents (User):

[0050] Users can download, view, and edit documents converted into a unified format on their devices, making it easier to combine and analyze data between different medical institutions.

[0051] Specific examples

[0052] For example, Clinic A uses the following questionnaire:

[0053] Patient name

[0054] date of birth

[0055] Symptoms

[0056] Meanwhile, Clinic B uses the following questionnaire:

[0057] Patient Name

[0058] birthday

[0059] Current medical condition

[0060] Processing flow

[0061] 1. Enter the initial data:

[0062] The user uploads the medical questionnaires from Clinic A and Clinic B to the system. For example, the medical questionnaire from Clinic A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache."

[0063] 2. Save to database:

[0064] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Clinic A's data might be saved as "Patient Name: Taro Yamada," "Date of Birth: January 1, 1980," and "Symptoms: Headache."

[0065] 3. Request for conversion to unified format:

[0066] The user sends a request from the terminal to the server to convert the medical questionnaire from Clinic A into the format of Clinic B.

[0067] 4. Data transfer and conversion to the LLM model:

[0068] The server retrieves the relevant questionnaire data from the database and sends it to the LLM model, which automatically converts "Patient Name" to "Patient Name," "Birth Date" to "Birthday," and "Symptoms" to "Current Condition."

[0069] 5. Resave to unified format:

[0070] The server receives the converted data and restores it to the database. For example, Clinic A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache."

[0071] 6. Provision of uniform format documents:

[0072] The user can check the converted medical questionnaire on the terminal and download or edit it as necessary. This ensures data consistency between Clinic A and Clinic B.

[0073] This invention will unify the document formats used by different medical institutions, enabling more efficient use of data and promoting medical research.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] A user uses a terminal to upload document templates from Hospital A and Hospital B to the system. When uploading, the user can select each document type, such as a medical questionnaire, test results, or medical records.

[0077] Step 2:

[0078] The server receives the uploaded documents. After receiving them, the server analyzes the content of each document and identifies the document type (e.g., medical questionnaire, test results, etc.).

[0079] Step 3:

[0080] The server extracts metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the analyzed data, and the extracted metadata is registered in a database.

[0081] Step 4:

[0082] The server stores the parsed document content and metadata in a database, along with any necessary tagging to enable future reuse.

[0083] Step 5:

[0084] The user selects a specific document on the terminal and requests conversion to a unified format. The user specifies the details of the unified format (e.g., which hospital's format to convert to).

[0085] Step 6:

[0086] The terminal sends the user's conversion request to the server. The request includes the document ID to be converted and the requested format information.

[0087] Step 7:

[0088] The server receives the conversion request and retrieves the corresponding document data from the database. The retrieved document data includes the document content and metadata.

[0089] Step 8:

[0090] The server sends the document data and the unified format conversion rules to the generative AI model, which then begins analyzing and converting the document data.

[0091] Step 9:

[0092] The generative AI model analyzes the document content and converts it into a specified unified format, specifically by changing field names (e.g., changing "Patient Name" to "Patient First Name") and adjusting the data format.

[0093] Step 10:

[0094] The server receives the converted document data from the generative AI model, and checks that the received document data conforms to the unified format.

[0095] Step 11:

[0096] The server re-stores the converted document data in the database. When re-saving, metadata indicating that the conversion has occurred (e.g., conversion date and time, source format, and destination format) is added.

[0097] Step 12:

[0098] The user accesses the database to obtain the converted document from the terminal. The user searches for the document in the unified format from the database, and downloads or views it as needed.

[0099] Step 13:

[0100] The terminal sends the user's download request to the server, and the server sends the document in a unified format to the terminal, where the user can view and edit the document.

[0101] In this way, the system converts documents from different medical institutions into a unified format, promoting efficient data utilization and medical research.

[0102] Example 1

[0103] Next, a description will be given of 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."

[0104] The lack of standardized medical document formats used by different medical institutions makes it difficult to exchange and integrate information. This leads to a lack of data consistency and reduces the efficiency of statistical analysis and medical research. Furthermore, manual format conversion is time-consuming and labor-intensive, and there is a risk of human error.

[0105] 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.

[0106] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for analyzing medical documents uploaded from a terminal and storing them in the database, means for generating prompt sentences for the generative AI model and converting document data to the unified format in response to the conversion request, and means for adding conversion metadata to the re-saved data. This enables standardization of document formats among different medical institutions and efficient use of data.

[0107] "Medical documents in different formats" refers to medical documents such as medical questionnaires and test results that are created in different formats at multiple medical institutions.

[0108] "Data format analysis" refers to the process of analyzing the content of received medical documents and extracting specific items or information.

[0109] "Metadata" is data that indicates additional information about the contents of medical documents, and is information that facilitates management and searching in a database.

[0110] A "database" is a collection of data that is organized and stored in an organized manner, and is a system that allows for easy searching and updating.

[0111] A "request for conversion to a unified format" is a request sent by a user to a server to convert a particular document into a standardized format.

[0112] A "generative AI model" is an AI technology that models human language generation capabilities and generates and converts documents based on large datasets.

[0113] A "prompt sentence" is an input sentence that instructs the generative AI model on how to process something, and includes specific conversion rules.

[0114] "Conversion metadata" is additional information about the converted document that is generated during the process of converting into a unified format, and is information for maintaining the correspondence with the original document.

[0115] A "terminal" is a device such as a computer, tablet, or smartphone that a user uses to access the system.

[0116] A "server" is a computer system that provides resources and data over a network and processes requests from client terminals.

[0117] "Document data" refers to specific information contained in a medical document, including items such as names, dates, and symptoms.

[0118] MODE FOR CARRYING OUT THE INVENTION

[0119] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[0120] Overall system configuration

[0121] Input of initial data (user)

[0122] Users use their devices to upload document templates for each medical institution to the system. Users operate devices such as PCs, tablets, and smartphones to enter information such as the medical questionnaire from Clinic A and the test results from Clinic B into the system. Specifically, users operate the system's input screen, click the "File Upload" button, select medical document files from their local disk, and then click the "Upload" button, which sends these files to the server.

[0123] Save to database (server)

[0124] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. For example, an analysis program runs on the server, analyzes the document contents, and extracts items such as the patient's name and date of birth. This information is then stored as metadata in a database in JSON format or similar.

[0125] Conversion request to unified format (user)

[0126] The user operates the terminal, selects the document to be converted, and sends a request for conversion to the unified format to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using the drop-down list or search function, and clicks the "Convert to unified format" button, which sends a conversion request to the server.

[0127] Data transmission and conversion to the LLM model (server)

[0128] The server receives the conversion request, retrieves the target document data from the database, and sends it to a generative AI model (e.g., GPT-4 (registered trademark)). The server generates a prompt sentence before sending it to the LLM model. The prompt sentence contains the original document data and conversion rules. The LLM model receives the document data and automatically converts it into the specified format.

[0129] Resave to unified format (server)

[0130] The server receives the converted document data returned by the generative AI model and restores it to the database. When restoring the data, conversion metadata is also added, making it possible to clearly identify the correspondence between the original document and the converted document.

[0131] Provision of unified format documents (user)

[0132] Users can download, view, and edit the converted documents on their devices, facilitating data sharing and analysis between different medical institutions.

[0133] Specific examples

[0134] For example, Clinic A uses the following questionnaire:

[0135] Patient name

[0136] date of birth

[0137] Symptoms

[0138] Meanwhile, Clinic B uses the following questionnaire:

[0139] Patient Name

[0140] birthday

[0141] Current medical condition

[0142] The user uploads the medical questionnaires for Clinic A and Clinic B to the system and sends a request to convert the medical questionnaire from Clinic A to the format of Clinic B. The server retrieves the relevant document from the database and generates the following prompt:

[0143] Convert the given medical document into the following format:

[0144] Original format:

[0145] Patient name: Taro Yamada

[0146] Date of Birth: January 1, 1980

[0147] Symptom: Headache

[0148] Unified format:

[0149] Patient Name: Taro Yamada

[0150] Date of birth: January 1, 1980

[0151] Current medical condition: Headache

[0152] The generative AI model converts the data based on the prompt and sends the results back to the server, which then stores the data in a database for users to view and download. This ensures data consistency between Clinic A and Clinic B.

[0153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0154] Step 1:

[0155] Input of initial data (user)

[0156] The user uses the terminal to upload the document template of each medical institution to the system. Specifically, the user opens the system's input screen, clicks the "File Upload" button, selects the medical document file (e.g., the medical questionnaire for Clinic A) from the local disk, and clicks the "Upload" button.

[0157] Input: A medical document file selected by the user.

[0158] Output: Medical document data sent to the server.

[0159] Step 2:

[0160] Save to database (server)

[0161] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. Specifically, an analysis program is launched within the server, which analyzes the document contents (e.g., "patient name," "date of birth," and "symptoms") and extracts specific items. The analyzed data and metadata are then stored in a database.

[0162] Input: Medical document data uploaded by the user.

[0163] Output: A database containing the parsed medical document data and metadata.

[0164] Step 3:

[0165] Conversion request to unified format (user)

[0166] The user selects the document to be converted and sends the conversion request to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using a drop-down list or the search function, and clicks the "Convert to unified format" button.

[0167] Input: The conversion request selected by the user.

[0168] Output: The conversion request data sent to the server.

[0169] Step 4:

[0170] Data transmission and conversion to the LLM model (server)

[0171] After receiving the conversion request, the server retrieves the target document data from the database and sends it to the generative AI model (e.g., GPT-4). Specifically, the server reads the relevant document data from the database and generates a prompt. The generated prompt and the document data are sent together to the generative AI model to convert the document into a unified format.

[0172] Input: Document data retrieved from the database and generated prompt statements.

[0173] Output: The conversion request and document data sent to the generative AI model, and the converted document data.

[0174] Step 5:

[0175] Resave to unified format (server)

[0176] The server receives the converted document data from the generative AI model and restores it to the database. Specifically, it adds conversion metadata to the converted document data and stores it in the database. This clarifies the correspondence between the original document and the converted document.

[0177] Input: The transformed document data received from the generative AI model.

[0178] Output: The resaved converted document data and conversion metadata.

[0179] Step 6:

[0180] Provision of unified format documents (user)

[0181] Users can download, view, and edit the converted documents on their devices. Specifically, users access the system's document viewing screen and select a document from the list of documents converted to a unified format. They view the selected document on their device and click buttons to download or edit it as needed.

[0182] Input: A unified format document selected by the user.

[0183] Output: Medical document data in a unified format provided to the terminal.

[0184] (Application example 1)

[0185] Next, a description will be given of Application 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."

[0186] Medical institutions often handle medical documents in different formats, and converting these documents into a unified format is time-consuming and inefficient. It is also important to manage this data securely and provide access only to appropriate users, but current methods make it difficult to ensure complete security. To solve this problem, a system with efficient conversion methods and advanced security measures is needed.

[0187] 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.

[0188] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for generating a prompt sentence when sending it to the generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for encrypting the converted document data, and means for providing the document data in the unified format, thereby enabling efficient conversion and secure management of medical documents in different formats.

[0189] "Medical documents in different formats" refers to patient information and medical records with different formats and contents that are created independently by different medical institutions or departments.

[0190] "Analyzing the data format" means analyzing the structure and content of the received medical document and identifying each item and data type.

[0191] "Extracting metadata" means extracting basic information and attribute information (e.g., patient name, treatment date, diagnosis, etc.) contained in medical documents.

[0192] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to analyze medical documents and convert them into a unified format.

[0193] A "prompt" is a question or command sentence entered into a generative AI model to instruct it on a specific transformation task.

[0194] A "unified format" is a standardized document format that allows for uniform management and analysis of multiple different types of medical documents.

[0195] A "conversion request" is a request from a user to the system to convert a particular medical document into a unified format.

[0196] "Encryption" means transforming data in medical documents using a specific algorithm so that the data cannot be accessed by third parties.

[0197] "Restoring" means storing the converted document data in a database so that it can be easily accessed later.

[0198] "Providing" means making the converted medical documents in a unified format available for viewing, editing, and downloading on the user's device.

[0199] This invention is a system that realizes an application that converts different formats of medical documents into a unified format and securely manages and provides them. Below, the program processing of this system is explained in natural language.

[0200] System Configuration

[0201] The system consists of the following main components:

[0202] 1. Data Entry Interface

[0203] Hardware: Smartphones, tablets

[0204] Software: Camera app, file upload function

[0205] Users can use smartphones or tablets to take photos of medical documents in different formats or upload them as files, allowing various types of medical documents to be imported into the system.

[0206] 2. Data format conversion

[0207] Software: Tesseract OCR, OpenAI® GPT-4

[0208] Incoming medical document data is first converted to text using Tesseract OCR, then a generative AI model such as OpenAI GPT-4 is used to convert the text data into a unified format. When using a generative AI model, a prompt is generated to instruct the model on a specific conversion task.

[0209] Prompt Sentence Examples

[0210] "Please convert the following document data into a unified format. Please list each item on a separate line. Patient name: Yamada Taro Date of birth: January 1, 1980 Symptoms: Headache"

[0211] 3. Data Encryption and Storage

[0212] Software: PyCryptodome, cloud storage (AWS (registered trademark), etc.)

[0213] Once converted into a unified format, the data is encrypted using PyCryptodome with a strong encryption method such as AES-256, and then securely stored in cloud storage, where it can be easily accessed later while minimizing security risks.

[0214] 4. Secure data viewing and authentication management

[0215] Hardware: Smartphones, tablets

[0216] Software: GOOGLE FI (registered trademark) rebase Auth

[0217] When a user views data, two-step authentication and biometric authentication are performed using authentication services such as Google (registered trademark) Firebase Auth, ensuring that only legitimate users can access the data.

[0218] 5. Audit Log Management

[0219] Software: MongoDB

[0220] All data access and operation history is recorded in MongoDB, making it possible to audit system usage and enhance security.

[0221] Adding specific examples

[0222] For example, a user takes a photo of a medical questionnaire from Clinic A with their smartphone and uploads it to the system. The questionnaire contains the following information: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Symptom: Headache." This data is received and extracted as text data using Tesseract OCR. It is then sent to the generative AI model along with a prompt, which converts it into a unified format: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Current Symptom: Headache." This data is encrypted with AES-256 and stored in cloud storage. When a user attempts to view the data, they are authenticated via Google Firebase Auth, ensuring that only authorized users can access the data.

[0223] In this way, efficient conversion and secure management of different types of medical documents is achieved.

[0224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0225] Step 1:

[0226] Data Entry:

[0227] Users use their smartphones or tablets to take or scan medical documents in different formats, and the input data is uploaded in image or PDF format.

[0228] Step 2:

[0229] Image and document recognition:

[0230] The server analyzes the images and PDFs it receives and converts them into text data using Tesseract OCR. The input is image data and the output is string data.

[0231] Step 3:

[0232] Metadata Extraction:

[0233] The server analyzes the text data and extracts metadata (patient name, date of birth, symptoms, etc.). The input is the string data obtained in step 2, and the output is the extracted metadata.

[0234] Step 4:

[0235] Save to database:

[0236] The server stores the extracted metadata in a database. The input is the extracted metadata, and the output is the information stored in the database.

[0237] Step 5:

[0238] Accepting conversion requests:

[0239] A user sends a request to the system from a terminal to convert a specific medical document into a unified format. The input is the conversion request information, and the output is a message confirming the conversion request.

[0240] Step 6:

[0241] Sending data to a generative AI model:

[0242] The server accepts the conversion request, retrieves the corresponding document data from the database, and sends it to the generative AI model. The input is the conversion request information and the document data retrieved from the database, and the output is the prompt text and the data to be sent.

[0243] Step 7:

[0244] Transformation by generative AI models:

[0245] The generative AI model converts medical documents in different formats into a unified format based on the prompt text and document data it receives. The input is the prompt text and document data, and the output is document data in the unified format.

[0246] Step 8:

[0247] Encryption of converted data:

[0248] The server encrypts the converted data with AES-256. The input is the document data converted to a unified format, and the output is the encrypted document data.

[0249] Step 9:

[0250] Resave to database:

[0251] The server restores the encrypted document data to the database. The input is the encrypted document data, and the output is the encrypted data stored in the database.

[0252] Step 10:

[0253] Data provided by:

[0254] The user authenticates and then views the medical documents converted into a unified format on the terminal. The input is authentication information, and the output is viewable document data.

[0255] The above processing steps enable efficient conversion and secure management of medical documents in different formats.

[0256] 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.

[0257] This invention is a system that uses a generative AI model and an emotion engine to convert different medical document templates into a unified format, and further optimizes the conversion process by recognizing the user's emotions. The program processing of this system is explained below in natural language.

[0258] System configuration

[0259] 1. Input of initial data (user):

[0260] The user operates the terminal to input document templates from each medical institution into the system. For example, they upload a medical questionnaire from Hospital A and test results from Hospital B. The emotion engine continuously recognizes the user's emotions as they are inputting.

[0261] 2. Save to database (server):

[0262] The server receives the medical documents uploaded by the user, analyzes the data format, and extracts metadata. The analyzed data and metadata are stored in a database. The user's emotional data is also stored in the database.

[0263] 3. Request for conversion to unified format (terminal):

[0264] The user operates the terminal to select the document to be converted and sends a request to convert it to a unified format to the server. The emotion engine monitors the user's emotional fluctuations and displays an assistant message as necessary.

[0265] 4. Data transmission and conversion to the LLM model (server):

[0266] The server receives the conversion request and retrieves the target document data from the database. The document data and conversion rules are then sent to the generative AI model, which analyzes the document and converts it into the specified unified format. The emotion engine optimizes the generative AI model's algorithm based on the user's emotional data.

[0267] 5. Resave to unified format (server):

[0268] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[0269] 6. Provision of Unified Format Documents (User):

[0270] Users can download, view, and edit documents converted into a unified format on their devices. The emotion engine evaluates user satisfaction and sends feedback messages as needed. This makes it easier to combine and analyze data across different medical institutions.

[0271] Specific examples

[0272] For example, Hospital A uses the following questionnaire:

[0273] Patient name

[0274] date of birth

[0275] Symptoms

[0276] Meanwhile, Hospital B uses the following questionnaire:

[0277] Patient Name

[0278] birthday

[0279] Current medical condition

[0280] Processing flow

[0281] 1. Enter the initial data:

[0282] The user uploads the medical questionnaires from Hospital A and Hospital B to the system. For example, the medical questionnaire from Hospital A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache." The emotion engine also continuously recognizes the user's emotional data (e.g., impatience, satisfaction, etc.).

[0283] 2. Save to database:

[0284] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Hospital A's data might be saved as "Patient Name: Yamada Taro," "Date of Birth: January 1, 1980," and "Symptoms: Headache." At the same time, the user's emotional data is also saved.

[0285] 3. Request for conversion to unified format:

[0286] The user sends a request from their terminal to the server to convert a medical questionnaire from Hospital A into the format of Hospital B. The emotion engine monitors the user's fluctuating emotions and displays an appropriate support message.

[0287] 4. Data transfer and conversion to the LLM model:

[0288] The server retrieves the relevant medical questionnaire data from the database and sends it to the LLM model. The LLM model automatically converts "patient name" to "patient name," "date of birth" to "date of birth," and "symptoms" to "current medical condition." The emotion engine adjusts the algorithm of the generative AI model appropriately based on the user's emotion data.

[0289] 5. Resave to unified format:

[0290] The server receives the converted data and restores it to the database. For example, Hospital A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache." The conversion date and time and conversion format information are also saved as metadata.

[0291] 6. Provision of uniform format documents:

[0292] The user checks the converted questionnaire on their device and downloads or edits it as necessary. The emotion engine evaluates the user's emotions and sends feedback messages to help ensure user satisfaction. This ensures data consistency between Hospital A and Hospital B.

[0293] This invention not only unifies the document formats used among different medical institutions, but also provides a better user experience that takes into account the user's feelings.

[0294] The processing flow will be explained below.

[0295] Step 1:

[0296] The user uses a terminal to upload document templates from Hospital A and Hospital B to the system. The uploaded documents include medical questionnaires, test results, medical records, etc., and are set as templates. As the user types, the emotion engine recognizes the user's emotions in real time.

[0297] Step 2:

[0298] The server receives the uploaded medical document. After receiving it, it identifies the document type (e.g., medical questionnaire, test results) and performs an initial analysis, which extracts important items from the document.

[0299] Step 3:

[0300] The server then extracts structured metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the extracted data. The extracted metadata is then registered in a database, and the document data itself is also stored.

[0301] Step 4:

[0302] The emotion engine analyzes the user's emotional data and evaluates the stress and satisfaction they feel. The emotional data is also stored in a database and used to optimize the conversion process.

[0303] Step 5:

[0304] The user operates the terminal to select a specific document and request its conversion to a unified format. The user specifies the details of the document to be converted (e.g., which template to convert it to). The emotion engine continuously monitors the user's emotions during operation and provides help messages and support as needed.

[0305] Step 6:

[0306] The terminal sends the user's conversion request to the server, which includes the document ID to be converted and the requested format information.

[0307] Step 7:

[0308] The server receives the conversion request and retrieves the specified document data from the database. The retrieved document data includes the document content and metadata.

[0309] Step 8:

[0310] The server sends the acquired document data and conversion rules to the generative AI model. The generative AI model analyzes the document data and converts it into the specified unified format. At this time, the generative AI model's algorithm is optimized appropriately based on the user's emotional data recognized by the emotion engine.

[0311] Step 9:

[0312] The generative AI model analyzes the document content and changes the specified field names (e.g., converting "Patient Name" to "Patient First Name") and adjusts the data format.

[0313] Step 10:

[0314] The server receives the converted document data from the generative AI model, and checks that the received data conforms to the unified format.

[0315] Step 11:

[0316] The server then re-stores the converted document data in the database, adding metadata such as the date and time of the conversion and the format information of the source and destination documents.

[0317] Step 12:

[0318] The user searches and accesses the converted document from their device, and the emotion engine evaluates the user's current emotions and displays feedback messages based on their satisfaction or stress level.

[0319] Step 13:

[0320] The user clicks the "Download" button on the terminal to download the converted document. The server receives the download request and sends the corresponding document data to the terminal.

[0321] Step 14:

[0322] The user views the converted document on the device and edits it as necessary. The emotion engine monitors this and provides assistance when the user wants to convert it again.

[0323] In this way, the system not only converts documents from different medical institutions into a unified format, but also optimizes the process by taking into account user sentiment, providing a better user experience.

[0324] Example 2

[0325] Next, a description will be given of 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."

[0326] With the existence of data in different formats, there is a need for easy and efficient conversion into a unified format. It is also important to consider the user's feelings during the data conversion process and improve the user experience. This will make it easier to use data between different institutions and provide a system that can reduce the stress users feel when converting data.

[0327] 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.

[0328] In this invention, the server includes means for receiving data in different formats, means for analyzing the format of the received data and extracting metadata, means for saving the extracted metadata in a storage device, means for accepting a conversion request, means for acquiring data based on the conversion request and sending it to a generative AI model, means for converting data in different formats into a unified format using the generative AI model, means for restoring the converted data to a storage device, means for providing data in the unified format, and an emotion engine for recognizing user emotions, wherein the emotion engine collects user emotion data and optimizes the conversion process. This enables efficient data conversion between different institutions and improves the user experience.

[0329] "Heterogeneous data" is information or documents written in different structures or formats.

[0330] "Means for receiving" refers to the function by which the system acquires input data, takes it in and processes it internally.

[0331] "Means for analyzing formats and extracting metadata" refers to a function for understanding the structure of input data and extracting necessary information (metadata).

[0332] A "storage device" is a hardware or storage system for storing data and metadata.

[0333] The "means for accepting a conversion request" is a function for receiving a data conversion instruction from a user and transmitting the instruction to the system.

[0334] "Means for acquiring data and sending it to the generative AI model" refers to a function that acquires the necessary data from a storage device and sends that data to the generative AI model for processing.

[0335] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate or transform data.

[0336] "Means for converting to a unified format" refers to the ability to convert data of different formats into a standardized format using a generative AI model.

[0337] The "means for re-saving" is a function for saving the converted data again in the storage device.

[0338] The "means for providing" is a function for displaying or downloading the converted unified format data so that the user can use it.

[0339] The "emotion engine" is a system that recognizes the user's emotions and collects and analyzes that data.

[0340] The "means for collecting emotional data and optimizing the conversion process" is a function for making adjustments based on the collected emotional data to improve the efficiency of the data conversion process and user satisfaction.

[0341] This invention is a system that uses a generative AI model and an emotion engine to convert data of different formats into a unified format. The goal is to improve the user experience by recognizing user emotions and optimizing the conversion process during the conversion process.

[0342] The system's components include a server, a terminal, an emotion engine, and a generative AI model. The server functions as a data processing unit equipped with a high-performance processor and ample storage capacity. The terminal is an input device operated by the user, such as a PC or smartphone. The emotion engine is a software component that collects and analyzes user emotion data, and the generative AI model is an AI algorithm for generating text and converting data.

[0343] The operation of the system will be specifically described below.

[0344] Users use their devices to upload different types of data to the system. For example, when a user inputs a medical document template into the system, the emotion engine recognizes the user's emotions in real time and collects emotion data. Users simply open a file selection window on their device, select a document file, and click the upload button to send the file to the system.

[0345] The server analyzes the format of the received data, extracts metadata, and stores it in a storage device. For example, in the case of medical documents, information such as the patient's name, date of birth, and symptoms are extracted as metadata. Along with this metadata, the user's emotional data is also stored in the storage device.

[0346] The user selects the data to be converted using the terminal and sends a request to the server to convert it into a unified format. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[0347] Based on the conversion request, the server retrieves the relevant data from the storage device and sends it to the generative AI model. The generative AI model then converts the data based on the specified unified format. For example, it automatically converts "patient name" to "patient name" and "date of birth" to "date of birth" in different medical documents.

[0348] The server receives the converted data returned from the generative AI model and stores it back in the storage device. This converted data also includes conversion metadata (e.g., conversion date and time, original format information), enabling efficient data management.

[0349] Users can view the data converted into a unified format on their devices and download or edit it as needed. The emotion engine evaluates user satisfaction and sends feedback messages. This process not only ensures data consistency across different institutions, but also improves the user experience.

[0350] As a concrete example, the following prompt sentence is shown.

[0351] Please convert Hospital A's medical questionnaire into Hospital B's format:

[0352] Hospital A's medical questionnaire:

[0353] Patient name: Taro Yamada

[0354] Date of Birth: January 1, 1980

[0355] Symptom: Headache

[0356] Convert to Hospital B format:

[0357] Patient Name: Taro Yamada

[0358] Date of birth: January 1, 1980

[0359] Current medical condition: Headache

[0360] This system efficiently converts data of various formats into a unified format, and also provides a better user experience that takes user emotions into consideration.

[0361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0362] Step 1:

[0363] A user uploads data to the system using a terminal. Specifically, the user opens a file selection window on the terminal, selects a medical document file, and clicks the upload button. The input is the medical document file, and the output is sending the file to the server. The user's emotions are monitored by the emotion engine.

[0364] Step 2:

[0365] The server receives the uploaded data and analyzes its format. Specifically, it analyzes the data structure and extracts metadata such as the patient's name, date of birth, and symptoms. The input is the medical document file sent in step 1, and the output is the extracted metadata. Along with this metadata, the user's emotion data collected by the emotion engine is also stored in the storage device.

[0366] Step 3:

[0367] The user uses the terminal to select the data they wish to convert and sends a request to convert it to a unified format to the server. Specifically, they select the target data from a data list on the terminal screen and click the conversion request button. The input is the selected data and the conversion request, and the output is the transmission of the conversion request to the server. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[0368] Step 4:

[0369] After receiving the conversion request, the server retrieves the corresponding data from the storage device and sends it to the generative AI model. Specifically, it reads the data including metadata from the storage device and sends it to the generative AI model along with the configured conversion rules. The input is the conversion request and the corresponding data, and the output is sending the data to the generative AI model.

[0370] Step 5:

[0371] The generative AI model analyzes the transmitted data and converts it into the specified unified format. Specifically, the generative AI model converts "patient name" to "patient name" and "date of birth" to "date of birth." The input is the data transmitted in step 4, and the output is the data converted into the unified format. The generative AI model's algorithm is also optimized based on the user's emotion data provided by the emotion engine.

[0372] Step 6:

[0373] The server receives the converted data from the generative AI model and stores it again in a storage device. Specifically, it stores the converted data again in a storage device and also adds conversion metadata (e.g., conversion date and time, original format information). The input is the converted data from the generative AI model, and the output is the reconverted data stored in a storage device.

[0374] Step 7:

[0375] The user can use their device to check the converted data and download or edit it as needed. Specifically, the device displays a list of converted data, selects the desired data, and clicks the download button. The input is the converted data stored in the storage device, and the output is the data downloaded to the user's device. Finally, the emotion engine evaluates the user's satisfaction and sends a feedback message.

[0376] (Application example 2)

[0377] Next, a description will be given of Application 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."

[0378] In the process of converting documents of different formats into a unified format, the challenge is to provide a more efficient and user-friendly document conversion system that takes into account the impact of the user's emotional state on conversion accuracy and efficiency.In addition, security-related documents also have different formats depending on the site, and unifying them is required for efficient data management and rapid information sharing.

[0379] 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.

[0380] In this invention, the server includes means for receiving documents in different formats, means for analyzing the data format of the received documents and extracting metadata, means for storing the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and transmitting it to a generative AI model, means for converting documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for receiving and analyzing user emotion data and optimizing the generative AI model's algorithm based on the emotion data, and means for monitoring user emotion and displaying appropriate support messages. This improves the efficiency of document conversion from different formats to a unified format, enabling responses that take user emotion into consideration. Furthermore, standardizing the formats of security-related documents that differ from site to site can achieve efficient data management and rapid information sharing.

[0381] Definitions of important words

[0382] "Documents in different formats" refer to document files with different formats and layouts created by different departments or work sites.

[0383] "Metadata" refers to additional information and attribute information about the data format and content of a document, and contributes to improving database management and search efficiency.

[0384] A "database" is a system for systematically storing and managing multiple data.

[0385] A "generative AI model" is an algorithm or system that uses artificial intelligence to automatically generate or transform data or documents.

[0386] A "unified format" is a format in which documents of different formats are converted into a single, consistent format, improving data consistency and utilization efficiency.

[0387] A "conversion request" is a request submitted by a user to the system to convert documents of different formats into a unified format.

[0388] "Emotional data" refers to data obtained as a result of evaluating and analyzing the user's emotional state.

[0389] An "algorithm" is a set of procedures and methods for performing specific calculations or processes, and is the basis for controlling the operation of generative AI models.

[0390] "Support messages" are advice and guidance provided by the system according to the user's emotional state, and are intended to improve the user's operational efficiency.

[0391] MODE FOR CARRYING OUT THE INVENTION

[0392] System Configuration

[0393] This invention is a system that efficiently converts documents of different formats into a unified format and provides support messages that take into account the user's feelings. This system consists of the following main components:

[0394] 1. User Device

[0395] 2. Cloud Server

[0396] 3. Database

[0397] 4. Generative AI Models

[0398] 5. Sentiment Analysis Engine

[0399] Hardware and Software

[0400] Hardware:

[0401] User device (smart glasses or smartphone)

[0402] Cloud servers (common cloud server providers, e.g., AWS, Google Cloud)

[0403] software:

[0404] Data analysis libraries (e.g., pandas)

[0405] Generative AI model libraries (e.g., OpenAI GPT, BERT)

[0406] Sentiment analysis engine (e.g., IBM Watson®, Microsoft® Azure® Emotion API)

[0407] Connectivity libraries (e.g. MQTT)

[0408] User device operation

[0409] Users use smart glasses or smartphones to input documents obtained from different sites or departments. The user's emotional state is continuously monitored by an emotion analysis engine, and the data is sent to a cloud server. For example, when entering reports such as "surveillance camera abnormalities" or "intrusion detection" at a security site, emotional data such as impatience or tension is also collected at the same time.

[0410] Cloud server processing

[0411] The cloud server receives the text and emotion data sent from the user device and performs the following processes:

[0412] 1. Data Analysis:

[0413] The cloud server first analyzes the data format of the received document and extracts the necessary metadata. For example, if a report of a "surveillance camera malfunction" is sent, metadata such as the camera number and the details of the malfunction will be extracted.

[0414] 2. Data Retention:

[0415] The extracted metadata is stored in a database, along with the user's emotional data.

[0416] 3. Accepting conversion requests:

[0417] When a user sends a request to the cloud server to convert a specific document into a unified format, the cloud server accepts the request, retrieves the target document data from the database, and sends it to the generative AI model.

[0418] 4. Run the generative AI model:

[0419] The generative AI model converts documents of different formats into a unified format based on the submitted document data, and optimizes the model's algorithm using user sentiment data.

[0420] 5. Resave the converted data:

[0421] The converted document data in a unified format is then stored back on the cloud server, and the conversion process is also recorded as metadata.

[0422] Providing unified format documents

[0423] The user can check the converted document data on their device and download or edit it as needed. The sentiment analysis engine evaluates the user's satisfaction and provides appropriate support messages. This reduces stress while working in security situations and enables users to work efficiently.

[0424] Specific examples

[0425] Data Entry Example

[0426] Report from Scene A: "Surveillance camera malfunction: Camera 3 has stopped working."

[0427] Prompt Sentence Examples

[0428] Send the following prompt to the generative AI model:

[0429] Please convert the following security reports into a unified format:

[0430] Report A: Surveillance Camera Abnormality: Camera 3 has stopped working

[0431] This system allows users to efficiently convert documents of different formats into a unified format and receive optimal support that takes emotions into consideration.

[0432] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0433] Program processing steps

[0434] Step 1:

[0435] The user inputs documents in different formats into a device (smart glasses or smartphone), which then sends the input data to the cloud server. The input data includes the document content and the user's emotional data. For example, a report such as "Surveillance camera abnormality: Camera 3 has stopped working" is sent along with the emotional data "anxious."

[0436] Step 2:

[0437] The cloud server analyzes the received document and extracts metadata. For example, from a document titled "Surveillance camera abnormality," it extracts the metadata "Camera 3" and "Out of operation." Emotion data is also analyzed, and this data is stored in a database. The input data is multiple document data and emotion data, and the output data is the analyzed metadata and save instructions.

[0438] Step 3:

[0439] A user sends a request to convert a report of a "surveillance camera anomaly" into a unified format from their terminal. For example, they send a request to convert the report into a unified format. At this time, the user's emotional data is also acquired in real time. The input data is the conversion request and the emotional data, and the output data is a confirmation of the conversion request.

[0440] Step 4:

[0441] The cloud server retrieves the target document data from the database and sends the document data and emotion data to the generative AI model. For example, the cloud server retrieves the document data for "surveillance camera abnormality," adds emotion data, and sends it to the generative AI model. The input data is the document data and emotion data, and the output data is a transmission confirmation.

[0442] Step 5:

[0443] The generative AI model analyzes the document data and converts it into a unified format. The algorithm is optimized based on the emotion data, and the conversion process is carried out. For example, "Surveillance camera anomaly" is converted into "Security incident report." The input data is the document data and emotion data, and the output data is the converted document in a unified format.

[0444] Step 6:

[0445] The cloud server receives the converted document data from the generative AI model and stores it in the database. The conversion process is also recorded as metadata. The input data is the converted document data, and the output data is a notification that saving has been completed.

[0446] Step 7:

[0447] The user checks the converted document data on their device, downloading or editing it as necessary. The emotion analysis engine evaluates the level of satisfaction and displays a support message as appropriate. For example, a unified format document stating "Surveillance camera abnormality" is displayed on the device. The input data is the converted document data and real-time emotion data, and the output data is the support message and final confirmation.

[0448] This allows the entire system to operate efficiently, enabling highly accurate document conversion and support that takes user emotions into account.

[0449] 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.

[0450] 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> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[0451] 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.

[0452] [Second embodiment]

[0453] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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).

[0459] 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. 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0465] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[0466] System configuration

[0467] 1. Input of initial data (user):

[0468] The user operates the terminal to input document templates for each medical institution into the system. For example, a medical questionnaire from Clinic A and test results from Clinic B are uploaded to the system.

[0469] 2. Save to database (server):

[0470] The server receives medical documents uploaded by users, analyzes the data format, and extracts metadata, which are then stored in a database.

[0471] 3. Request for conversion to unified format (terminal):

[0472] The user operates the terminal to select the document to be converted and sends a request for conversion to the unified format to the server.

[0473] 4. Data transmission and conversion to the LLM model (server):

[0474] The server receives the conversion request, retrieves the target document data from the database, and then sends the document data and conversion rules to the generative AI model, which then analyzes the document and converts it into the specified unified format.

[0475] 5. Resave to unified format (server):

[0476] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[0477] 6. Provision of Unified Format Documents (User):

[0478] Users can download, view, and edit documents converted into a unified format on their devices, making it easier to combine and analyze data between different medical institutions.

[0479] Specific examples

[0480] For example, Clinic A uses the following questionnaire:

[0481] Patient name

[0482] date of birth

[0483] Symptoms

[0484] Meanwhile, Clinic B uses the following questionnaire:

[0485] Patient Name

[0486] birthday

[0487] Current medical condition

[0488] Processing flow

[0489] 1. Enter the initial data:

[0490] The user uploads the medical questionnaires from Clinic A and Clinic B to the system. For example, the medical questionnaire from Clinic A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache."

[0491] 2. Save to database:

[0492] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Clinic A's data might be saved as "Patient Name: Taro Yamada," "Date of Birth: January 1, 1980," and "Symptoms: Headache."

[0493] 3. Request for conversion to unified format:

[0494] The user sends a request from the terminal to the server to convert the medical questionnaire from Clinic A into the format of Clinic B.

[0495] 4. Data transfer and conversion to the LLM model:

[0496] The server retrieves the relevant questionnaire data from the database and sends it to the LLM model, which automatically converts "Patient Name" to "Patient Name," "Birth Date" to "Birthday," and "Symptoms" to "Current Condition."

[0497] 5. Resave to unified format:

[0498] The server receives the converted data and restores it to the database. For example, Clinic A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache."

[0499] 6. Provision of uniform format documents:

[0500] The user can check the converted medical questionnaire on the terminal and download or edit it as necessary. This ensures data consistency between Clinic A and Clinic B.

[0501] This invention will unify the document formats used by different medical institutions, enabling more efficient use of data and promoting medical research.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] A user uses a terminal to upload document templates from Hospital A and Hospital B to the system. When uploading, the user can select each document type, such as a medical questionnaire, test results, or medical records.

[0505] Step 2:

[0506] The server receives the uploaded documents. After receiving them, the server analyzes the content of each document and identifies the document type (e.g., medical questionnaire, test results, etc.).

[0507] Step 3:

[0508] The server extracts metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the analyzed data, and the extracted metadata is registered in a database.

[0509] Step 4:

[0510] The server stores the parsed document content and metadata in a database, along with any necessary tagging to enable future reuse.

[0511] Step 5:

[0512] The user selects a specific document on the terminal and requests conversion to a unified format. The user specifies the details of the unified format (e.g., which hospital's format to convert to).

[0513] Step 6:

[0514] The terminal sends the user's conversion request to the server. The request includes the document ID to be converted and the requested format information.

[0515] Step 7:

[0516] The server receives the conversion request and retrieves the corresponding document data from the database. The retrieved document data includes the document content and metadata.

[0517] Step 8:

[0518] The server sends the document data and the unified format conversion rules to the generative AI model, which then begins analyzing and converting the document data.

[0519] Step 9:

[0520] The generative AI model analyzes the document content and converts it into a specified unified format, specifically by changing field names (e.g., changing "Patient Name" to "Patient First Name") and adjusting the data format.

[0521] Step 10:

[0522] The server receives the converted document data from the generative AI model, and checks that the received document data conforms to the unified format.

[0523] Step 11:

[0524] The server re-stores the converted document data in the database. When re-saving, metadata indicating that the conversion has occurred (e.g., conversion date and time, source format, and destination format) is added.

[0525] Step 12:

[0526] The user accesses the database to obtain the converted document from the terminal. The user searches for the document in the unified format from the database, and downloads or views it as needed.

[0527] Step 13:

[0528] The terminal sends the user's download request to the server, and the server sends the document in a unified format to the terminal, where the user can view and edit the document.

[0529] In this way, the system converts documents from different medical institutions into a unified format, promoting efficient data utilization and medical research.

[0530] Example 1

[0531] Next, a description will be given of 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."

[0532] The lack of standardized medical document formats used by different medical institutions makes it difficult to exchange and integrate information. This leads to a lack of data consistency and reduces the efficiency of statistical analysis and medical research. Furthermore, manual format conversion is time-consuming and labor-intensive, and there is a risk of human error.

[0533] 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.

[0534] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for analyzing medical documents uploaded from a terminal and storing them in the database, means for generating prompt sentences for the generative AI model and converting document data to the unified format in response to the conversion request, and means for adding conversion metadata to the re-saved data. This enables standardization of document formats among different medical institutions and efficient use of data.

[0535] "Medical documents in different formats" refers to medical documents such as medical questionnaires and test results that are created in different formats at multiple medical institutions.

[0536] "Data format analysis" refers to the process of analyzing the content of received medical documents and extracting specific items or information.

[0537] "Metadata" is data that indicates additional information about the contents of medical documents, and is information that facilitates management and searching in a database.

[0538] A "database" is a collection of data that is organized and stored in an organized manner, and is a system that allows for easy searching and updating.

[0539] A "request for conversion to a unified format" is a request sent by a user to a server to convert a particular document into a standardized format.

[0540] A "generative AI model" is an AI technology that models human language generation capabilities and generates and converts documents based on large datasets.

[0541] A "prompt sentence" is an input sentence that instructs the generative AI model on how to process something, and includes specific conversion rules.

[0542] "Conversion metadata" is additional information about the converted document that is generated during the process of converting into a unified format, and is information for maintaining the correspondence with the original document.

[0543] A "terminal" is a device such as a computer, tablet, or smartphone that a user uses to access the system.

[0544] A "server" is a computer system that provides resources and data over a network and processes requests from client terminals.

[0545] "Document data" refers to specific information contained in a medical document, including items such as names, dates, and symptoms.

[0546] MODE FOR CARRYING OUT THE INVENTION

[0547] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[0548] Overall system configuration

[0549] Input of initial data (user)

[0550] Users use their devices to upload document templates for each medical institution to the system. Users operate devices such as PCs, tablets, and smartphones to enter information such as the medical questionnaire from Clinic A and the test results from Clinic B into the system. Specifically, users operate the system's input screen, click the "File Upload" button, select medical document files from their local disk, and then click the "Upload" button, which sends these files to the server.

[0551] Save to database (server)

[0552] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. For example, an analysis program runs on the server, analyzes the document contents, and extracts items such as the patient's name and date of birth. This information is then stored as metadata in a database in JSON format or similar.

[0553] Conversion request to unified format (user)

[0554] The user operates the terminal, selects the document to be converted, and sends a request for conversion to the unified format to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using the drop-down list or search function, and clicks the "Convert to unified format" button, which sends a conversion request to the server.

[0555] Data transmission and conversion to the LLM model (server)

[0556] The server receives the conversion request, retrieves the target document data from the database, and sends it to the generative AI model (e.g., GPT-4). The server generates a prompt sentence before sending it to the LLM model. The prompt sentence contains the original document data and the conversion rules. The LLM model receives the document data and automatically converts it into the specified format.

[0557] Resave to unified format (server)

[0558] The server receives the converted document data returned by the generative AI model and restores it to the database. When restoring the data, conversion metadata is also added, making it possible to clearly identify the correspondence between the original document and the converted document.

[0559] Provision of unified format documents (user)

[0560] Users can download, view, and edit the converted documents on their devices, facilitating data sharing and analysis between different medical institutions.

[0561] Specific examples

[0562] For example, Clinic A uses the following questionnaire:

[0563] Patient name

[0564] date of birth

[0565] Symptoms

[0566] Meanwhile, Clinic B uses the following questionnaire:

[0567] Patient Name

[0568] birthday

[0569] Current medical condition

[0570] The user uploads the medical questionnaires for Clinic A and Clinic B to the system and sends a request to convert the medical questionnaire from Clinic A to the format of Clinic B. The server retrieves the relevant document from the database and generates the following prompt:

[0571] Convert the given medical document into the following format:

[0572] Original format:

[0573] Patient name: Taro Yamada

[0574] Date of Birth: January 1, 1980

[0575] Symptom: Headache

[0576] Unified format:

[0577] Patient Name: Taro Yamada

[0578] Date of birth: January 1, 1980

[0579] Current medical condition: Headache

[0580] The generative AI model converts the data based on the prompt and sends the results back to the server, which then stores the data in a database for users to view and download. This ensures data consistency between Clinic A and Clinic B.

[0581] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0582] Step 1:

[0583] Input of initial data (user)

[0584] The user uses the terminal to upload the document template of each medical institution to the system. Specifically, the user opens the system's input screen, clicks the "File Upload" button, selects the medical document file (e.g., the medical questionnaire for Clinic A) from the local disk, and clicks the "Upload" button.

[0585] Input: A medical document file selected by the user.

[0586] Output: Medical document data sent to the server.

[0587] Step 2:

[0588] Save to database (server)

[0589] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. Specifically, an analysis program is launched within the server, which analyzes the document contents (e.g., "patient name," "date of birth," and "symptoms") and extracts specific items. The analyzed data and metadata are then stored in a database.

[0590] Input: Medical document data uploaded by the user.

[0591] Output: A database containing the parsed medical document data and metadata.

[0592] Step 3:

[0593] Conversion request to unified format (user)

[0594] The user selects the document to be converted and sends the conversion request to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using a drop-down list or the search function, and clicks the "Convert to unified format" button.

[0595] Input: The conversion request selected by the user.

[0596] Output: The conversion request data sent to the server.

[0597] Step 4:

[0598] Data transmission and conversion to the LLM model (server)

[0599] After receiving the conversion request, the server retrieves the target document data from the database and sends it to the generative AI model (e.g., GPT-4). Specifically, the server reads the relevant document data from the database and generates a prompt. The generated prompt and the document data are sent together to the generative AI model to convert the document into a unified format.

[0600] Input: Document data retrieved from the database and generated prompt statements.

[0601] Output: The conversion request and document data sent to the generative AI model, and the converted document data.

[0602] Step 5:

[0603] Resave to unified format (server)

[0604] The server receives the converted document data from the generative AI model and restores it to the database. Specifically, it adds conversion metadata to the converted document data and stores it in the database. This clarifies the correspondence between the original document and the converted document.

[0605] Input: The transformed document data received from the generative AI model.

[0606] Output: The resaved converted document data and conversion metadata.

[0607] Step 6:

[0608] Provision of unified format documents (user)

[0609] Users can download, view, and edit the converted documents on their devices. Specifically, users access the system's document viewing screen and select a document from the list of documents converted to a unified format. They view the selected document on their device and click buttons to download or edit it as needed.

[0610] Input: A unified format document selected by the user.

[0611] Output: Medical document data in a unified format provided to the terminal.

[0612] (Application example 1)

[0613] Next, a description will be given of Application 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."

[0614] Medical institutions often handle medical documents in different formats, and converting these documents into a unified format is time-consuming and inefficient. It is also important to manage this data securely and provide access only to appropriate users, but current methods make it difficult to ensure complete security. To solve this problem, a system with efficient conversion methods and advanced security measures is needed.

[0615] 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.

[0616] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for generating a prompt sentence when sending it to the generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for encrypting the converted document data, and means for providing the document data in the unified format, thereby enabling efficient conversion and secure management of medical documents in different formats.

[0617] "Medical documents in different formats" refers to patient information and medical records with different formats and contents that are created independently by different medical institutions or departments.

[0618] "Analyzing the data format" means analyzing the structure and content of the received medical document and identifying each item and data type.

[0619] "Extracting metadata" means extracting basic information and attribute information (e.g., patient name, treatment date, diagnosis, etc.) contained in medical documents.

[0620] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to analyze medical documents and convert them into a unified format.

[0621] A "prompt" is a question or command sentence entered into a generative AI model to instruct it on a specific transformation task.

[0622] A "unified format" is a standardized document format that allows for uniform management and analysis of multiple different types of medical documents.

[0623] A "conversion request" is a request from a user to the system to convert a particular medical document into a unified format.

[0624] "Encryption" means transforming data in medical documents using a specific algorithm so that the data cannot be accessed by third parties.

[0625] "Restoring" means storing the converted document data in a database so that it can be easily accessed later.

[0626] "Providing" means making the converted medical documents in a unified format available for viewing, editing, and downloading on the user's device.

[0627] This invention is a system that realizes an application that converts different formats of medical documents into a unified format and securely manages and provides them. Below, the program processing of this system is explained in natural language.

[0628] System Configuration

[0629] The system consists of the following main components:

[0630] 1. Data Entry Interface

[0631] Hardware: Smartphones, tablets

[0632] Software: Camera app, file upload function

[0633] Users can use smartphones or tablets to take photos of medical documents in different formats or upload them as files, allowing various types of medical documents to be imported into the system.

[0634] 2. Data format conversion

[0635] Software: Tesseract OCR, OpenAI GPT-4

[0636] Incoming medical document data is first converted to text using Tesseract OCR, then a generative AI model such as OpenAI GPT-4 is used to convert the text data into a unified format. When using a generative AI model, a prompt is generated to instruct the model on a specific conversion task.

[0637] Prompt Sentence Examples

[0638] "Please convert the following document data into a unified format. Please list each item on a separate line. Patient name: Yamada Taro Date of birth: January 1, 1980 Symptoms: Headache"

[0639] 3. Data Encryption and Storage

[0640] Software: PyCryptodome, cloud storage (AWS, etc.)

[0641] Once converted into a unified format, the data is encrypted using PyCryptodome with a strong encryption method such as AES-256, and then securely stored in cloud storage, where it can be easily accessed later while minimizing security risks.

[0642] 4. Secure data viewing and authentication management

[0643] Hardware: Smartphones, tablets

[0644] Software: Google Firebase Auth

[0645] When users access data, two-step authentication and biometric authentication are performed using authentication services such as Google Firebase Auth, ensuring that only legitimate users can access the data.

[0646] 5. Audit Log Management

[0647] Software: MongoDB

[0648] All data access and operation history is recorded in MongoDB, making it possible to audit system usage and enhance security.

[0649] Adding specific examples

[0650] For example, a user takes a photo of a medical questionnaire from Clinic A with their smartphone and uploads it to the system. The questionnaire contains the following information: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Symptom: Headache." This data is received and extracted as text data using Tesseract OCR. It is then sent to the generative AI model along with a prompt, which converts it into a unified format: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Current Symptom: Headache." This data is encrypted with AES-256 and stored in cloud storage. When a user attempts to view the data, they are authenticated via Google Firebase Auth, ensuring that only authorized users can access the data.

[0651] In this way, efficient conversion and secure management of different types of medical documents is achieved.

[0652] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0653] Step 1:

[0654] Data Entry:

[0655] Users use their smartphones or tablets to take or scan medical documents in different formats, and the input data is uploaded in image or PDF format.

[0656] Step 2:

[0657] Image and document recognition:

[0658] The server analyzes the images and PDFs it receives and converts them into text data using Tesseract OCR. The input is image data and the output is string data.

[0659] Step 3:

[0660] Metadata Extraction:

[0661] The server analyzes the text data and extracts metadata (patient name, date of birth, symptoms, etc.). The input is the string data obtained in step 2, and the output is the extracted metadata.

[0662] Step 4:

[0663] Save to database:

[0664] The server stores the extracted metadata in a database. The input is the extracted metadata, and the output is the information stored in the database.

[0665] Step 5:

[0666] Accepting conversion requests:

[0667] A user sends a request to the system from a terminal to convert a specific medical document into a unified format. The input is the conversion request information, and the output is a message confirming the conversion request.

[0668] Step 6:

[0669] Sending data to a generative AI model:

[0670] The server accepts the conversion request, retrieves the corresponding document data from the database, and sends it to the generative AI model. The input is the conversion request information and the document data retrieved from the database, and the output is the prompt text and the data to be sent.

[0671] Step 7:

[0672] Transformation by generative AI models:

[0673] The generative AI model converts medical documents in different formats into a unified format based on the prompt text and document data it receives. The input is the prompt text and document data, and the output is document data in the unified format.

[0674] Step 8:

[0675] Encryption of converted data:

[0676] The server encrypts the converted data with AES-256. The input is the document data converted to a unified format, and the output is the encrypted document data.

[0677] Step 9:

[0678] Resave to database:

[0679] The server restores the encrypted document data to the database. The input is the encrypted document data, and the output is the encrypted data stored in the database.

[0680] Step 10:

[0681] Data provided by:

[0682] The user authenticates and then views the medical documents converted into a unified format on the terminal. The input is authentication information, and the output is viewable document data.

[0683] The above processing steps enable efficient conversion and secure management of medical documents in different formats.

[0684] 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.

[0685] This invention is a system that uses a generative AI model and an emotion engine to convert different medical document templates into a unified format, and further optimizes the conversion process by recognizing the user's emotions. The program processing of this system is explained below in natural language.

[0686] System configuration

[0687] 1. Input of initial data (user):

[0688] The user operates the terminal to input document templates from each medical institution into the system. For example, they upload a medical questionnaire from Hospital A and test results from Hospital B. The emotion engine continuously recognizes the user's emotions as they are inputting.

[0689] 2. Save to database (server):

[0690] The server receives the medical documents uploaded by the user, analyzes the data format, and extracts metadata. The analyzed data and metadata are stored in a database. The user's emotional data is also stored in the database.

[0691] 3. Request for conversion to unified format (terminal):

[0692] The user operates the terminal to select the document to be converted and sends a request to convert it to a unified format to the server. The emotion engine monitors the user's emotional fluctuations and displays an assistant message as necessary.

[0693] 4. Data transmission and conversion to the LLM model (server):

[0694] The server receives the conversion request and retrieves the target document data from the database. The document data and conversion rules are then sent to the generative AI model, which analyzes the document and converts it into the specified unified format. The emotion engine optimizes the generative AI model's algorithm based on the user's emotional data.

[0695] 5. Resave to unified format (server):

[0696] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[0697] 6. Provision of Unified Format Documents (User):

[0698] Users can download, view, and edit documents converted into a unified format on their devices. The emotion engine evaluates user satisfaction and sends feedback messages as needed. This makes it easier to combine and analyze data across different medical institutions.

[0699] Specific examples

[0700] For example, Hospital A uses the following questionnaire:

[0701] Patient name

[0702] date of birth

[0703] Symptoms

[0704] Meanwhile, Hospital B uses the following questionnaire:

[0705] Patient Name

[0706] birthday

[0707] Current medical condition

[0708] Processing flow

[0709] 1. Enter the initial data:

[0710] The user uploads the medical questionnaires from Hospital A and Hospital B to the system. For example, the medical questionnaire from Hospital A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache." The emotion engine also continuously recognizes the user's emotional data (e.g., impatience, satisfaction, etc.).

[0711] 2. Save to database:

[0712] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Hospital A's data might be saved as "Patient Name: Yamada Taro," "Date of Birth: January 1, 1980," and "Symptoms: Headache." At the same time, the user's emotional data is also saved.

[0713] 3. Request for conversion to unified format:

[0714] The user sends a request from their terminal to the server to convert a medical questionnaire from Hospital A into the format of Hospital B. The emotion engine monitors the user's fluctuating emotions and displays an appropriate support message.

[0715] 4. Data transfer and conversion to the LLM model:

[0716] The server retrieves the relevant medical questionnaire data from the database and sends it to the LLM model. The LLM model automatically converts "patient name" to "patient name," "date of birth" to "date of birth," and "symptoms" to "current medical condition." The emotion engine adjusts the algorithm of the generative AI model appropriately based on the user's emotion data.

[0717] 5. Resave to unified format:

[0718] The server receives the converted data and restores it to the database. For example, Hospital A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache." The conversion date and time and conversion format information are also saved as metadata.

[0719] 6. Provision of uniform format documents:

[0720] The user checks the converted questionnaire on their device and downloads or edits it as necessary. The emotion engine evaluates the user's emotions and sends feedback messages to help ensure user satisfaction. This ensures data consistency between Hospital A and Hospital B.

[0721] This invention not only unifies the document formats used among different medical institutions, but also provides a better user experience that takes into account the user's feelings.

[0722] The processing flow will be explained below.

[0723] Step 1:

[0724] The user uses a terminal to upload document templates from Hospital A and Hospital B to the system. The uploaded documents include medical questionnaires, test results, medical records, etc., and are set as templates. As the user types, the emotion engine recognizes the user's emotions in real time.

[0725] Step 2:

[0726] The server receives the uploaded medical document. After receiving it, it identifies the document type (e.g., medical questionnaire, test results) and performs an initial analysis, which extracts important items from the document.

[0727] Step 3:

[0728] The server then extracts structured metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the extracted data. The extracted metadata is then registered in a database, and the document data itself is also stored.

[0729] Step 4:

[0730] The emotion engine analyzes the user's emotional data and evaluates the stress and satisfaction they feel. The emotional data is also stored in a database and used to optimize the conversion process.

[0731] Step 5:

[0732] The user operates the terminal to select a specific document and request its conversion to a unified format. The user specifies the details of the document to be converted (e.g., which template to convert it to). The emotion engine continuously monitors the user's emotions during operation and provides help messages and support as needed.

[0733] Step 6:

[0734] The terminal sends the user's conversion request to the server, which includes the document ID to be converted and the requested format information.

[0735] Step 7:

[0736] The server receives the conversion request and retrieves the specified document data from the database. The retrieved document data includes the document content and metadata.

[0737] Step 8:

[0738] The server sends the acquired document data and conversion rules to the generative AI model. The generative AI model analyzes the document data and converts it into the specified unified format. At this time, the generative AI model's algorithm is optimized appropriately based on the user's emotional data recognized by the emotion engine.

[0739] Step 9:

[0740] The generative AI model analyzes the document content and changes the specified field names (e.g., converting "Patient Name" to "Patient First Name") and adjusts the data format.

[0741] Step 10:

[0742] The server receives the converted document data from the generative AI model, and checks that the received data conforms to the unified format.

[0743] Step 11:

[0744] The server then re-stores the converted document data in the database, adding metadata such as the date and time of the conversion and the format information of the source and destination documents.

[0745] Step 12:

[0746] The user searches and accesses the converted document from their device, and the emotion engine evaluates the user's current emotions and displays feedback messages based on their satisfaction or stress level.

[0747] Step 13:

[0748] The user clicks the "Download" button on the terminal to download the converted document. The server receives the download request and sends the corresponding document data to the terminal.

[0749] Step 14:

[0750] The user views the converted document on the device and edits it as necessary. The emotion engine monitors this and provides assistance when the user wants to convert it again.

[0751] In this way, the system not only converts documents from different medical institutions into a unified format, but also optimizes the process by taking into account user sentiment, providing a better user experience.

[0752] Example 2

[0753] Next, a description will be given of 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."

[0754] With the existence of data in different formats, there is a need for easy and efficient conversion into a unified format. It is also important to consider the user's feelings during the data conversion process and improve the user experience. This will make it easier to use data between different institutions and provide a system that can reduce the stress users feel when converting data.

[0755] 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.

[0756] In this invention, the server includes means for receiving data in different formats, means for analyzing the format of the received data and extracting metadata, means for saving the extracted metadata in a storage device, means for accepting a conversion request, means for acquiring data based on the conversion request and sending it to a generative AI model, means for converting data in different formats into a unified format using the generative AI model, means for restoring the converted data to a storage device, means for providing data in the unified format, and an emotion engine for recognizing user emotions, wherein the emotion engine collects user emotion data and optimizes the conversion process. This enables efficient data conversion between different institutions and improves the user experience.

[0757] "Heterogeneous data" is information or documents written in different structures or formats.

[0758] "Means for receiving" refers to the function by which the system acquires input data, takes it in and processes it internally.

[0759] "Means for analyzing formats and extracting metadata" refers to a function for understanding the structure of input data and extracting necessary information (metadata).

[0760] A "storage device" is a hardware or storage system for storing data and metadata.

[0761] The "means for accepting a conversion request" is a function for receiving a data conversion instruction from a user and transmitting the instruction to the system.

[0762] "Means for acquiring data and sending it to the generative AI model" refers to a function that acquires the necessary data from a storage device and sends that data to the generative AI model for processing.

[0763] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate or transform data.

[0764] "Means for converting to a unified format" refers to the ability to convert data of different formats into a standardized format using a generative AI model.

[0765] The "means for re-saving" is a function for saving the converted data again in the storage device.

[0766] The "means for providing" is a function for displaying or downloading the converted unified format data so that the user can use it.

[0767] The "emotion engine" is a system that recognizes the user's emotions and collects and analyzes that data.

[0768] The "means for collecting emotional data and optimizing the conversion process" is a function for making adjustments based on the collected emotional data to improve the efficiency of the data conversion process and user satisfaction.

[0769] This invention is a system that uses a generative AI model and an emotion engine to convert data of different formats into a unified format. The goal is to improve the user experience by recognizing user emotions and optimizing the conversion process during the conversion process.

[0770] The system's components include a server, a terminal, an emotion engine, and a generative AI model. The server functions as a data processing unit equipped with a high-performance processor and ample storage capacity. The terminal is an input device operated by the user, such as a PC or smartphone. The emotion engine is a software component that collects and analyzes user emotion data, and the generative AI model is an AI algorithm for generating text and converting data.

[0771] The operation of the system will be specifically described below.

[0772] Users use their devices to upload different types of data to the system. For example, when a user inputs a medical document template into the system, the emotion engine recognizes the user's emotions in real time and collects emotion data. Users simply open a file selection window on their device, select a document file, and click the upload button to send the file to the system.

[0773] The server analyzes the format of the received data, extracts metadata, and stores it in a storage device. For example, in the case of medical documents, information such as the patient's name, date of birth, and symptoms are extracted as metadata. Along with this metadata, the user's emotional data is also stored in the storage device.

[0774] The user selects the data to be converted using the terminal and sends a request to the server to convert it into a unified format. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[0775] Based on the conversion request, the server retrieves the relevant data from the storage device and sends it to the generative AI model. The generative AI model then converts the data based on the specified unified format. For example, it automatically converts "patient name" to "patient name" and "date of birth" to "date of birth" in different medical documents.

[0776] The server receives the converted data returned from the generative AI model and stores it back in the storage device. This converted data also includes conversion metadata (e.g., conversion date and time, original format information), enabling efficient data management.

[0777] Users can view the data converted into a unified format on their devices and download or edit it as needed. The emotion engine evaluates user satisfaction and sends feedback messages. This process not only ensures data consistency across different institutions, but also improves the user experience.

[0778] As a concrete example, the following prompt sentence is shown.

[0779] Please convert Hospital A's medical questionnaire into Hospital B's format:

[0780] Hospital A's medical questionnaire:

[0781] Patient name: Taro Yamada

[0782] Date of Birth: January 1, 1980

[0783] Symptom: Headache

[0784] Convert to Hospital B format:

[0785] Patient Name: Taro Yamada

[0786] Date of birth: January 1, 1980

[0787] Current medical condition: Headache

[0788] This system efficiently converts data of various formats into a unified format, and also provides a better user experience that takes user emotions into consideration.

[0789] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0790] Step 1:

[0791] A user uploads data to the system using a terminal. Specifically, the user opens a file selection window on the terminal, selects a medical document file, and clicks the upload button. The input is the medical document file, and the output is sending the file to the server. The user's emotions are monitored by the emotion engine.

[0792] Step 2:

[0793] The server receives the uploaded data and analyzes its format. Specifically, it analyzes the data structure and extracts metadata such as the patient's name, date of birth, and symptoms. The input is the medical document file sent in step 1, and the output is the extracted metadata. Along with this metadata, the user's emotion data collected by the emotion engine is also stored in the storage device.

[0794] Step 3:

[0795] The user uses the terminal to select the data they wish to convert and sends a request to convert it to a unified format to the server. Specifically, they select the target data from a data list on the terminal screen and click the conversion request button. The input is the selected data and the conversion request, and the output is the transmission of the conversion request to the server. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[0796] Step 4:

[0797] After receiving the conversion request, the server retrieves the corresponding data from the storage device and sends it to the generative AI model. Specifically, it reads the data including metadata from the storage device and sends it to the generative AI model along with the configured conversion rules. The input is the conversion request and the corresponding data, and the output is sending the data to the generative AI model.

[0798] Step 5:

[0799] The generative AI model analyzes the transmitted data and converts it into the specified unified format. Specifically, the generative AI model converts "patient name" to "patient name" and "date of birth" to "date of birth." The input is the data transmitted in step 4, and the output is the data converted into the unified format. The generative AI model's algorithm is also optimized based on the user's emotion data provided by the emotion engine.

[0800] Step 6:

[0801] The server receives the converted data from the generative AI model and stores it again in a storage device. Specifically, it stores the converted data again in a storage device and also adds conversion metadata (e.g., conversion date and time, original format information). The input is the converted data from the generative AI model, and the output is the reconverted data stored in a storage device.

[0802] Step 7:

[0803] The user can use their device to check the converted data and download or edit it as needed. Specifically, the device displays a list of converted data, selects the desired data, and clicks the download button. The input is the converted data stored in the storage device, and the output is the data downloaded to the user's device. Finally, the emotion engine evaluates the user's satisfaction and sends a feedback message.

[0804] (Application example 2)

[0805] Next, a description will be given of Application 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."

[0806] In the process of converting documents of different formats into a unified format, the challenge is to provide a more efficient and user-friendly document conversion system that takes into account the impact of the user's emotional state on conversion accuracy and efficiency.In addition, security-related documents also have different formats depending on the site, and unifying them is required for efficient data management and rapid information sharing.

[0807] 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.

[0808] In this invention, the server includes means for receiving documents in different formats, means for analyzing the data format of the received documents and extracting metadata, means for storing the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and transmitting it to a generative AI model, means for converting documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for receiving and analyzing user emotion data and optimizing the generative AI model's algorithm based on the emotion data, and means for monitoring user emotion and displaying appropriate support messages. This improves the efficiency of document conversion from different formats to a unified format, enabling responses that take user emotion into consideration. Furthermore, standardizing the formats of security-related documents that differ from site to site can achieve efficient data management and rapid information sharing.

[0809] Definitions of important words

[0810] "Documents in different formats" refer to document files with different formats and layouts created by different departments or work sites.

[0811] "Metadata" refers to additional information and attribute information about the data format and content of a document, and contributes to improving database management and search efficiency.

[0812] A "database" is a system for systematically storing and managing multiple data.

[0813] A "generative AI model" is an algorithm or system that uses artificial intelligence to automatically generate or transform data or documents.

[0814] A "unified format" is a format in which documents of different formats are converted into a single, consistent format, improving data consistency and utilization efficiency.

[0815] A "conversion request" is a request submitted by a user to the system to convert documents of different formats into a unified format.

[0816] "Emotional data" refers to data obtained as a result of evaluating and analyzing the user's emotional state.

[0817] An "algorithm" is a set of procedures and methods for performing specific calculations or processes, and is the basis for controlling the operation of generative AI models.

[0818] "Support messages" are advice and guidance provided by the system according to the user's emotional state, and are intended to improve the user's operational efficiency.

[0819] MODE FOR CARRYING OUT THE INVENTION

[0820] System Configuration

[0821] This invention is a system that efficiently converts documents of different formats into a unified format and provides support messages that take into account the user's feelings. This system consists of the following main components:

[0822] 1. User Device

[0823] 2. Cloud Server

[0824] 3. Database

[0825] 4. Generative AI Models

[0826] 5. Sentiment Analysis Engine

[0827] Hardware and Software

[0828] Hardware:

[0829] User device (smart glasses or smartphone)

[0830] Cloud servers (common cloud server providers, e.g., AWS, Google Cloud)

[0831] software:

[0832] Data analysis libraries (e.g., pandas)

[0833] Generative AI model libraries (e.g., OpenAI GPT, BERT)

[0834] Sentiment analysis engines (e.g., IBM Watson, Microsoft Azure Emotion API)

[0835] Connectivity libraries (e.g. MQTT)

[0836] User device operation

[0837] Users use smart glasses or smartphones to input documents obtained from different sites or departments. The user's emotional state is continuously monitored by an emotion analysis engine, and the data is sent to a cloud server. For example, when entering reports such as "surveillance camera abnormalities" or "intrusion detection" at a security site, emotional data such as impatience or tension is also collected at the same time.

[0838] Cloud server processing

[0839] The cloud server receives the text and emotion data sent from the user device and performs the following processes:

[0840] 1. Data Analysis:

[0841] The cloud server first analyzes the data format of the received document and extracts the necessary metadata. For example, if a report of a "surveillance camera malfunction" is sent, metadata such as the camera number and the details of the malfunction will be extracted.

[0842] 2. Data Retention:

[0843] The extracted metadata is stored in a database, along with the user's emotional data.

[0844] 3. Accepting conversion requests:

[0845] When a user sends a request to the cloud server to convert a specific document into a unified format, the cloud server accepts the request, retrieves the target document data from the database, and sends it to the generative AI model.

[0846] 4. Run the generative AI model:

[0847] The generative AI model converts documents of different formats into a unified format based on the submitted document data, and optimizes the model's algorithm using user sentiment data.

[0848] 5. Resave the converted data:

[0849] The converted document data in a unified format is then stored back on the cloud server, and the conversion process is also recorded as metadata.

[0850] Providing unified format documents

[0851] The user can check the converted document data on their device and download or edit it as needed. The sentiment analysis engine evaluates the user's satisfaction and provides appropriate support messages. This reduces stress while working in security situations and enables users to work efficiently.

[0852] Specific examples

[0853] Data Entry Example

[0854] Report from Scene A: "Surveillance camera malfunction: Camera 3 has stopped working."

[0855] Prompt Sentence Examples

[0856] Send the following prompt to the generative AI model:

[0857] Please convert the following security reports into a unified format:

[0858] Report A: Surveillance Camera Abnormality: Camera 3 has stopped working

[0859] This system allows users to efficiently convert documents of different formats into a unified format and receive optimal support that takes emotions into consideration.

[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0861] Program processing steps

[0862] Step 1:

[0863] The user inputs documents in different formats into a device (smart glasses or smartphone), which then sends the input data to the cloud server. The input data includes the document content and the user's emotional data. For example, a report such as "Surveillance camera abnormality: Camera 3 has stopped working" is sent along with the emotional data "anxious."

[0864] Step 2:

[0865] The cloud server analyzes the received document and extracts metadata. For example, from a document titled "Surveillance camera abnormality," it extracts the metadata "Camera 3" and "Out of operation." Emotion data is also analyzed, and this data is stored in a database. The input data is multiple document data and emotion data, and the output data is the analyzed metadata and save instructions.

[0866] Step 3:

[0867] A user sends a request to convert a report of a "surveillance camera anomaly" into a unified format from their terminal. For example, they send a request to convert the report into a unified format. At this time, the user's emotional data is also acquired in real time. The input data is the conversion request and the emotional data, and the output data is a confirmation of the conversion request.

[0868] Step 4:

[0869] The cloud server retrieves the target document data from the database and sends the document data and emotion data to the generative AI model. For example, the cloud server retrieves the document data for "surveillance camera abnormality," adds emotion data, and sends it to the generative AI model. The input data is the document data and emotion data, and the output data is a transmission confirmation.

[0870] Step 5:

[0871] The generative AI model analyzes the document data and converts it into a unified format. The algorithm is optimized based on the emotion data, and the conversion process is carried out. For example, "Surveillance camera anomaly" is converted into "Security incident report." The input data is the document data and emotion data, and the output data is the converted document in a unified format.

[0872] Step 6:

[0873] The cloud server receives the converted document data from the generative AI model and stores it in the database. The conversion process is also recorded as metadata. The input data is the converted document data, and the output data is a notification that saving has been completed.

[0874] Step 7:

[0875] The user checks the converted document data on their device, downloading or editing it as necessary. The emotion analysis engine evaluates the level of satisfaction and displays a support message as appropriate. For example, a unified format document stating "Surveillance camera abnormality" is displayed on the device. The input data is the converted document data and real-time emotion data, and the output data is the support message and final confirmation.

[0876] This allows the entire system to operate efficiently, enabling highly accurate document conversion and support that takes user emotions into account.

[0877] 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.

[0878] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[0879] 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.

[0880] [Third embodiment]

[0881] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0882] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0883] 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).

[0884] 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.

[0885] 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.

[0886] 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).

[0887] 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. 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0893] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[0894] System configuration

[0895] 1. Input of initial data (user):

[0896] The user operates the terminal to input document templates for each medical institution into the system. For example, a medical questionnaire from Clinic A and test results from Clinic B are uploaded to the system.

[0897] 2. Save to database (server):

[0898] The server receives medical documents uploaded by users, analyzes the data format, and extracts metadata, which are then stored in a database.

[0899] 3. Request for conversion to unified format (terminal):

[0900] The user operates the terminal to select the document to be converted and sends a request for conversion to the unified format to the server.

[0901] 4. Data transmission and conversion to the LLM model (server):

[0902] The server receives the conversion request, retrieves the target document data from the database, and then sends the document data and conversion rules to the generative AI model, which then analyzes the document and converts it into the specified unified format.

[0903] 5. Resave to unified format (server):

[0904] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[0905] 6. Provision of Unified Format Documents (User):

[0906] Users can download, view, and edit documents converted into a unified format on their devices, making it easier to combine and analyze data between different medical institutions.

[0907] Specific examples

[0908] For example, Clinic A uses the following questionnaire:

[0909] Patient name

[0910] date of birth

[0911] Symptoms

[0912] Meanwhile, Clinic B uses the following questionnaire:

[0913] Patient Name

[0914] birthday

[0915] Current medical condition

[0916] Processing flow

[0917] 1. Enter the initial data:

[0918] The user uploads the medical questionnaires from Clinic A and Clinic B to the system. For example, the medical questionnaire from Clinic A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache."

[0919] 2. Save to database:

[0920] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Clinic A's data might be saved as "Patient Name: Taro Yamada," "Date of Birth: January 1, 1980," and "Symptoms: Headache."

[0921] 3. Request for conversion to unified format:

[0922] The user sends a request from the terminal to the server to convert the medical questionnaire from Clinic A into the format of Clinic B.

[0923] 4. Data transfer and conversion to the LLM model:

[0924] The server retrieves the relevant questionnaire data from the database and sends it to the LLM model, which automatically converts "Patient Name" to "Patient Name," "Birth Date" to "Birthday," and "Symptoms" to "Current Condition."

[0925] 5. Resave to unified format:

[0926] The server receives the converted data and restores it to the database. For example, Clinic A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache."

[0927] 6. Provision of uniform format documents:

[0928] The user can check the converted medical questionnaire on the terminal and download or edit it as necessary. This ensures data consistency between Clinic A and Clinic B.

[0929] This invention will unify the document formats used by different medical institutions, enabling more efficient use of data and promoting medical research.

[0930] The processing flow will be explained below.

[0931] Step 1:

[0932] A user uses a terminal to upload document templates from Hospital A and Hospital B to the system. When uploading, the user can select each document type, such as a medical questionnaire, test results, or medical records.

[0933] Step 2:

[0934] The server receives the uploaded documents. After receiving them, the server analyzes the content of each document and identifies the document type (e.g., medical questionnaire, test results, etc.).

[0935] Step 3:

[0936] The server extracts metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the analyzed data, and the extracted metadata is registered in a database.

[0937] Step 4:

[0938] The server stores the parsed document content and metadata in a database, along with any necessary tagging to enable future reuse.

[0939] Step 5:

[0940] The user selects a specific document on the terminal and requests conversion to a unified format. The user specifies the details of the unified format (e.g., which hospital's format to convert to).

[0941] Step 6:

[0942] The terminal sends the user's conversion request to the server. The request includes the document ID to be converted and the requested format information.

[0943] Step 7:

[0944] The server receives the conversion request and retrieves the corresponding document data from the database. The retrieved document data includes the document content and metadata.

[0945] Step 8:

[0946] The server sends the document data and the unified format conversion rules to the generative AI model, which then begins analyzing and converting the document data.

[0947] Step 9:

[0948] The generative AI model analyzes the document content and converts it into a specified unified format, specifically by changing field names (e.g., changing "Patient Name" to "Patient First Name") and adjusting the data format.

[0949] Step 10:

[0950] The server receives the converted document data from the generative AI model, and checks that the received document data conforms to the unified format.

[0951] Step 11:

[0952] The server re-stores the converted document data in the database. When re-saving, metadata indicating that the conversion has occurred (e.g., conversion date and time, source format, and destination format) is added.

[0953] Step 12:

[0954] The user accesses the database to obtain the converted document from the terminal. The user searches for the document in the unified format from the database, and downloads or views it as needed.

[0955] Step 13:

[0956] The terminal sends the user's download request to the server, and the server sends the document in a unified format to the terminal, where the user can view and edit the document.

[0957] In this way, the system converts documents from different medical institutions into a unified format, promoting efficient data utilization and medical research.

[0958] Example 1

[0959] Next, a description will be given of 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."

[0960] The lack of standardized medical document formats used by different medical institutions makes it difficult to exchange and integrate information. This leads to a lack of data consistency and reduces the efficiency of statistical analysis and medical research. Furthermore, manual format conversion is time-consuming and labor-intensive, and there is a risk of human error.

[0961] 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.

[0962] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for analyzing medical documents uploaded from a terminal and storing them in the database, means for generating prompt sentences for the generative AI model and converting document data to the unified format in response to the conversion request, and means for adding conversion metadata to the re-saved data. This enables standardization of document formats among different medical institutions and efficient use of data.

[0963] "Medical documents in different formats" refers to medical documents such as medical questionnaires and test results that are created in different formats at multiple medical institutions.

[0964] "Data format analysis" refers to the process of analyzing the content of received medical documents and extracting specific items or information.

[0965] "Metadata" is data that indicates additional information about the contents of medical documents, and is information that facilitates management and searching in a database.

[0966] A "database" is a collection of data that is organized and stored in an organized manner, and is a system that allows for easy searching and updating.

[0967] A "request for conversion to a unified format" is a request sent by a user to a server to convert a particular document into a standardized format.

[0968] A "generative AI model" is an AI technology that models human language generation capabilities and generates and converts documents based on large datasets.

[0969] A "prompt sentence" is an input sentence that instructs the generative AI model on how to process something, and includes specific conversion rules.

[0970] "Conversion metadata" is additional information about the converted document that is generated during the process of converting into a unified format, and is information for maintaining the correspondence with the original document.

[0971] A "terminal" is a device such as a computer, tablet, or smartphone that a user uses to access the system.

[0972] A "server" is a computer system that provides resources and data over a network and processes requests from client terminals.

[0973] "Document data" refers to specific information contained in a medical document, including items such as names, dates, and symptoms.

[0974] MODE FOR CARRYING OUT THE INVENTION

[0975] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[0976] Overall system configuration

[0977] Input of initial data (user)

[0978] Users use their devices to upload document templates for each medical institution to the system. Users operate devices such as PCs, tablets, and smartphones to enter information such as the medical questionnaire from Clinic A and the test results from Clinic B into the system. Specifically, users operate the system's input screen, click the "File Upload" button, select medical document files from their local disk, and then click the "Upload" button, which sends these files to the server.

[0979] Save to database (server)

[0980] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. For example, an analysis program runs on the server, analyzes the document contents, and extracts items such as the patient's name and date of birth. This information is then stored as metadata in a database in JSON format or similar.

[0981] Conversion request to unified format (user)

[0982] The user operates the terminal, selects the document to be converted, and sends a request for conversion to the unified format to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using the drop-down list or search function, and clicks the "Convert to unified format" button, which sends a conversion request to the server.

[0983] Data transmission and conversion to the LLM model (server)

[0984] The server receives the conversion request, retrieves the target document data from the database, and sends it to the generative AI model (e.g., GPT-4). The server generates a prompt sentence before sending it to the LLM model. The prompt sentence contains the original document data and the conversion rules. The LLM model receives the document data and automatically converts it into the specified format.

[0985] Resave to unified format (server)

[0986] The server receives the converted document data returned by the generative AI model and restores it to the database. When restoring the data, conversion metadata is also added, making it possible to clearly identify the correspondence between the original document and the converted document.

[0987] Provision of unified format documents (user)

[0988] Users can download, view, and edit the converted documents on their devices, facilitating data sharing and analysis between different medical institutions.

[0989] Specific examples

[0990] For example, Clinic A uses the following questionnaire:

[0991] Patient name

[0992] date of birth

[0993] Symptoms

[0994] Meanwhile, Clinic B uses the following questionnaire:

[0995] Patient Name

[0996] birthday

[0997] Current medical condition

[0998] The user uploads the medical questionnaires for Clinic A and Clinic B to the system and sends a request to convert the medical questionnaire from Clinic A to the format of Clinic B. The server retrieves the relevant document from the database and generates the following prompt:

[0999] Convert the given medical document into the following format:

[1000] Original format:

[1001] Patient name: Taro Yamada

[1002] Date of Birth: January 1, 1980

[1003] Symptom: Headache

[1004] Unified format:

[1005] Patient Name: Taro Yamada

[1006] Date of birth: January 1, 1980

[1007] Current medical condition: Headache

[1008] The generative AI model converts the data based on the prompt and sends the results back to the server, which then stores the data in a database for users to view and download. This ensures data consistency between Clinic A and Clinic B.

[1009] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1010] Step 1:

[1011] Input of initial data (user)

[1012] The user uses the terminal to upload the document template of each medical institution to the system. Specifically, the user opens the system's input screen, clicks the "File Upload" button, selects the medical document file (e.g., the medical questionnaire for Clinic A) from the local disk, and clicks the "Upload" button.

[1013] Input: A medical document file selected by the user.

[1014] Output: Medical document data sent to the server.

[1015] Step 2:

[1016] Save to database (server)

[1017] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. Specifically, an analysis program is launched within the server, which analyzes the document contents (e.g., "patient name," "date of birth," and "symptoms") and extracts specific items. The analyzed data and metadata are then stored in a database.

[1018] Input: Medical document data uploaded by the user.

[1019] Output: A database containing the parsed medical document data and metadata.

[1020] Step 3:

[1021] Conversion request to unified format (user)

[1022] The user selects the document to be converted and sends the conversion request to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using a drop-down list or the search function, and clicks the "Convert to unified format" button.

[1023] Input: The conversion request selected by the user.

[1024] Output: The conversion request data sent to the server.

[1025] Step 4:

[1026] Data transmission and conversion to the LLM model (server)

[1027] After receiving the conversion request, the server retrieves the target document data from the database and sends it to the generative AI model (e.g., GPT-4). Specifically, the server reads the relevant document data from the database and generates a prompt. The generated prompt and the document data are sent together to the generative AI model to convert the document into a unified format.

[1028] Input: Document data retrieved from the database and generated prompt statements.

[1029] Output: The conversion request and document data sent to the generative AI model, and the converted document data.

[1030] Step 5:

[1031] Resave to unified format (server)

[1032] The server receives the converted document data from the generative AI model and restores it to the database. Specifically, it adds conversion metadata to the converted document data and stores it in the database. This clarifies the correspondence between the original document and the converted document.

[1033] Input: The transformed document data received from the generative AI model.

[1034] Output: The resaved converted document data and conversion metadata.

[1035] Step 6:

[1036] Provision of unified format documents (user)

[1037] Users can download, view, and edit the converted documents on their devices. Specifically, users access the system's document viewing screen and select a document from the list of documents converted to a unified format. They view the selected document on their device and click buttons to download or edit it as needed.

[1038] Input: A unified format document selected by the user.

[1039] Output: Medical document data in a unified format provided to the terminal.

[1040] (Application example 1)

[1041] Next, a description will be given of Application 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."

[1042] Medical institutions often handle medical documents in different formats, and converting these documents into a unified format is time-consuming and inefficient. It is also important to manage this data securely and provide access only to appropriate users, but current methods make it difficult to ensure complete security. To solve this problem, a system with efficient conversion methods and advanced security measures is needed.

[1043] 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.

[1044] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for generating a prompt sentence when sending it to the generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for encrypting the converted document data, and means for providing the document data in the unified format, thereby enabling efficient conversion and secure management of medical documents in different formats.

[1045] "Medical documents in different formats" refers to patient information and medical records with different formats and contents that are created independently by different medical institutions or departments.

[1046] "Analyzing the data format" means analyzing the structure and content of the received medical document and identifying each item and data type.

[1047] "Extracting metadata" means extracting basic information and attribute information (e.g., patient name, treatment date, diagnosis, etc.) contained in medical documents.

[1048] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to analyze medical documents and convert them into a unified format.

[1049] A "prompt" is a question or command sentence entered into a generative AI model to instruct it on a specific transformation task.

[1050] A "unified format" is a standardized document format that allows for uniform management and analysis of multiple different types of medical documents.

[1051] A "conversion request" is a request from a user to the system to convert a particular medical document into a unified format.

[1052] "Encryption" means transforming data in medical documents using a specific algorithm so that the data cannot be accessed by third parties.

[1053] "Restoring" means storing the converted document data in a database so that it can be easily accessed later.

[1054] "Providing" means making the converted medical documents in a unified format available for viewing, editing, and downloading on the user's device.

[1055] This invention is a system that realizes an application that converts different formats of medical documents into a unified format and securely manages and provides them. Below, the program processing of this system is explained in natural language.

[1056] System Configuration

[1057] The system consists of the following main components:

[1058] 1. Data Entry Interface

[1059] Hardware: Smartphones, tablets

[1060] Software: Camera app, file upload function

[1061] Users can use smartphones or tablets to take photos of medical documents in different formats or upload them as files, allowing various types of medical documents to be imported into the system.

[1062] 2. Data format conversion

[1063] Software: Tesseract OCR, OpenAI GPT-4

[1064] Incoming medical document data is first converted to text using Tesseract OCR, then a generative AI model such as OpenAI GPT-4 is used to convert the text data into a unified format. When using a generative AI model, a prompt is generated to instruct the model on a specific conversion task.

[1065] Prompt Sentence Examples

[1066] "Please convert the following document data into a unified format. Please list each item on a separate line. Patient name: Yamada Taro Date of birth: January 1, 1980 Symptoms: Headache"

[1067] 3. Data Encryption and Storage

[1068] Software: PyCryptodome, cloud storage (AWS, etc.)

[1069] Once converted into a unified format, the data is encrypted using PyCryptodome with a strong encryption method such as AES-256, and then securely stored in cloud storage, where it can be easily accessed later while minimizing security risks.

[1070] 4. Secure data viewing and authentication management

[1071] Hardware: Smartphones, tablets

[1072] Software: Google Firebase Auth

[1073] When users access data, two-step authentication and biometric authentication are performed using authentication services such as Google Firebase Auth, ensuring that only legitimate users can access the data.

[1074] 5. Audit Log Management

[1075] Software: MongoDB

[1076] All data access and operation history is recorded in MongoDB, making it possible to audit system usage and enhance security.

[1077] Adding specific examples

[1078] For example, a user takes a photo of a medical questionnaire from Clinic A with their smartphone and uploads it to the system. The questionnaire contains the following information: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Symptom: Headache." This data is received and extracted as text data using Tesseract OCR. It is then sent to the generative AI model along with a prompt, which converts it into a unified format: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Current Symptom: Headache." This data is encrypted with AES-256 and stored in cloud storage. When a user attempts to view the data, they are authenticated via Google Firebase Auth, ensuring that only authorized users can access the data.

[1079] In this way, efficient conversion and secure management of different types of medical documents is achieved.

[1080] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1081] Step 1:

[1082] Data Entry:

[1083] Users use their smartphones or tablets to take or scan medical documents in different formats, and the input data is uploaded in image or PDF format.

[1084] Step 2:

[1085] Image and document recognition:

[1086] The server analyzes the images and PDFs it receives and converts them into text data using Tesseract OCR. The input is image data and the output is string data.

[1087] Step 3:

[1088] Metadata Extraction:

[1089] The server analyzes the text data and extracts metadata (patient name, date of birth, symptoms, etc.). The input is the string data obtained in step 2, and the output is the extracted metadata.

[1090] Step 4:

[1091] Save to database:

[1092] The server stores the extracted metadata in a database. The input is the extracted metadata, and the output is the information stored in the database.

[1093] Step 5:

[1094] Accepting conversion requests:

[1095] A user sends a request to the system from a terminal to convert a specific medical document into a unified format. The input is the conversion request information, and the output is a message confirming the conversion request.

[1096] Step 6:

[1097] Sending data to a generative AI model:

[1098] The server accepts the conversion request, retrieves the corresponding document data from the database, and sends it to the generative AI model. The input is the conversion request information and the document data retrieved from the database, and the output is the prompt text and the data to be sent.

[1099] Step 7:

[1100] Transformation by generative AI models:

[1101] The generative AI model converts medical documents in different formats into a unified format based on the prompt text and document data it receives. The input is the prompt text and document data, and the output is document data in the unified format.

[1102] Step 8:

[1103] Encryption of converted data:

[1104] The server encrypts the converted data with AES-256. The input is the document data converted to a unified format, and the output is the encrypted document data.

[1105] Step 9:

[1106] Resave to database:

[1107] The server restores the encrypted document data to the database. The input is the encrypted document data, and the output is the encrypted data stored in the database.

[1108] Step 10:

[1109] Data provided by:

[1110] The user authenticates and then views the medical documents converted into a unified format on the terminal. The input is authentication information, and the output is viewable document data.

[1111] The above processing steps enable efficient conversion and secure management of medical documents in different formats.

[1112] 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.

[1113] This invention is a system that uses a generative AI model and an emotion engine to convert different medical document templates into a unified format, and further optimizes the conversion process by recognizing the user's emotions. The program processing of this system is explained below in natural language.

[1114] System configuration

[1115] 1. Input of initial data (user):

[1116] The user operates the terminal to input document templates from each medical institution into the system. For example, they upload a medical questionnaire from Hospital A and test results from Hospital B. The emotion engine continuously recognizes the user's emotions as they are inputting.

[1117] 2. Save to database (server):

[1118] The server receives the medical documents uploaded by the user, analyzes the data format, and extracts metadata. The analyzed data and metadata are stored in a database. The user's emotional data is also stored in the database.

[1119] 3. Request for conversion to unified format (terminal):

[1120] The user operates the terminal to select the document to be converted and sends a request to convert it to a unified format to the server. The emotion engine monitors the user's emotional fluctuations and displays an assistant message as necessary.

[1121] 4. Data transmission and conversion to the LLM model (server):

[1122] The server receives the conversion request and retrieves the target document data from the database. The document data and conversion rules are then sent to the generative AI model, which analyzes the document and converts it into the specified unified format. The emotion engine optimizes the generative AI model's algorithm based on the user's emotional data.

[1123] 5. Resave to unified format (server):

[1124] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[1125] 6. Provision of Unified Format Documents (User):

[1126] Users can download, view, and edit documents converted into a unified format on their devices. The emotion engine evaluates user satisfaction and sends feedback messages as needed. This makes it easier to combine and analyze data across different medical institutions.

[1127] Specific examples

[1128] For example, Hospital A uses the following questionnaire:

[1129] Patient name

[1130] date of birth

[1131] Symptoms

[1132] Meanwhile, Hospital B uses the following questionnaire:

[1133] Patient Name

[1134] birthday

[1135] Current medical condition

[1136] Processing flow

[1137] 1. Enter the initial data:

[1138] The user uploads the medical questionnaires from Hospital A and Hospital B to the system. For example, the medical questionnaire from Hospital A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache." The emotion engine also continuously recognizes the user's emotional data (e.g., impatience, satisfaction, etc.).

[1139] 2. Save to database:

[1140] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Hospital A's data might be saved as "Patient Name: Yamada Taro," "Date of Birth: January 1, 1980," and "Symptoms: Headache." At the same time, the user's emotional data is also saved.

[1141] 3. Request for conversion to unified format:

[1142] The user sends a request from their terminal to the server to convert a medical questionnaire from Hospital A into the format of Hospital B. The emotion engine monitors the user's fluctuating emotions and displays an appropriate support message.

[1143] 4. Data transfer and conversion to the LLM model:

[1144] The server retrieves the relevant medical questionnaire data from the database and sends it to the LLM model. The LLM model automatically converts "patient name" to "patient name," "date of birth" to "date of birth," and "symptoms" to "current medical condition." The emotion engine adjusts the algorithm of the generative AI model appropriately based on the user's emotion data.

[1145] 5. Resave to unified format:

[1146] The server receives the converted data and restores it to the database. For example, Hospital A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache." The conversion date and time and conversion format information are also saved as metadata.

[1147] 6. Provision of uniform format documents:

[1148] The user checks the converted questionnaire on their device and downloads or edits it as necessary. The emotion engine evaluates the user's emotions and sends feedback messages to help ensure user satisfaction. This ensures data consistency between Hospital A and Hospital B.

[1149] This invention not only unifies the document formats used among different medical institutions, but also provides a better user experience that takes into account the user's feelings.

[1150] The processing flow will be explained below.

[1151] Step 1:

[1152] The user uses a terminal to upload document templates from Hospital A and Hospital B to the system. The uploaded documents include medical questionnaires, test results, medical records, etc., and are set as templates. As the user types, the emotion engine recognizes the user's emotions in real time.

[1153] Step 2:

[1154] The server receives the uploaded medical document. After receiving it, it identifies the document type (e.g., medical questionnaire, test results) and performs an initial analysis, which extracts important items from the document.

[1155] Step 3:

[1156] The server then extracts structured metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the extracted data. The extracted metadata is then registered in a database, and the document data itself is also stored.

[1157] Step 4:

[1158] The emotion engine analyzes the user's emotional data and evaluates the stress and satisfaction they feel. The emotional data is also stored in a database and used to optimize the conversion process.

[1159] Step 5:

[1160] The user operates the terminal to select a specific document and request its conversion to a unified format. The user specifies the details of the document to be converted (e.g., which template to convert it to). The emotion engine continuously monitors the user's emotions during operation and provides help messages and support as needed.

[1161] Step 6:

[1162] The terminal sends the user's conversion request to the server, which includes the document ID to be converted and the requested format information.

[1163] Step 7:

[1164] The server receives the conversion request and retrieves the specified document data from the database. The retrieved document data includes the document content and metadata.

[1165] Step 8:

[1166] The server sends the acquired document data and conversion rules to the generative AI model. The generative AI model analyzes the document data and converts it into the specified unified format. At this time, the generative AI model's algorithm is optimized appropriately based on the user's emotional data recognized by the emotion engine.

[1167] Step 9:

[1168] The generative AI model analyzes the document content and changes the specified field names (e.g., converting "Patient Name" to "Patient First Name") and adjusts the data format.

[1169] Step 10:

[1170] The server receives the converted document data from the generative AI model, and checks that the received data conforms to the unified format.

[1171] Step 11:

[1172] The server then re-stores the converted document data in the database, adding metadata such as the date and time of the conversion and the format information of the source and destination documents.

[1173] Step 12:

[1174] The user searches and accesses the converted document from their device, and the emotion engine evaluates the user's current emotions and displays feedback messages based on their satisfaction or stress level.

[1175] Step 13:

[1176] The user clicks the "Download" button on the terminal to download the converted document. The server receives the download request and sends the corresponding document data to the terminal.

[1177] Step 14:

[1178] The user views the converted document on the device and edits it as necessary. The emotion engine monitors this and provides assistance when the user wants to convert it again.

[1179] In this way, the system not only converts documents from different medical institutions into a unified format, but also optimizes the process by taking into account user sentiment, providing a better user experience.

[1180] Example 2

[1181] Next, a description will be given of 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."

[1182] With the existence of data in different formats, there is a need for easy and efficient conversion into a unified format. It is also important to consider the user's feelings during the data conversion process and improve the user experience. This will make it easier to use data between different institutions and provide a system that can reduce the stress users feel when converting data.

[1183] 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.

[1184] In this invention, the server includes means for receiving data in different formats, means for analyzing the format of the received data and extracting metadata, means for saving the extracted metadata in a storage device, means for accepting a conversion request, means for acquiring data based on the conversion request and sending it to a generative AI model, means for converting data in different formats into a unified format using the generative AI model, means for restoring the converted data to a storage device, means for providing data in the unified format, and an emotion engine for recognizing user emotions, wherein the emotion engine collects user emotion data and optimizes the conversion process. This enables efficient data conversion between different institutions and improves the user experience.

[1185] "Heterogeneous data" is information or documents written in different structures or formats.

[1186] "Means for receiving" refers to the function by which the system acquires input data, takes it in and processes it internally.

[1187] "Means for analyzing formats and extracting metadata" refers to a function for understanding the structure of input data and extracting necessary information (metadata).

[1188] A "storage device" is a hardware or storage system for storing data and metadata.

[1189] The "means for accepting a conversion request" is a function for receiving a data conversion instruction from a user and transmitting the instruction to the system.

[1190] "Means for acquiring data and sending it to the generative AI model" refers to a function that acquires the necessary data from a storage device and sends that data to the generative AI model for processing.

[1191] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate or transform data.

[1192] "Means for converting to a unified format" refers to the ability to convert data of different formats into a standardized format using a generative AI model.

[1193] The "means for re-saving" is a function for saving the converted data again in the storage device.

[1194] The "means for providing" is a function for displaying or downloading the converted unified format data so that the user can use it.

[1195] The "emotion engine" is a system that recognizes the user's emotions and collects and analyzes that data.

[1196] The "means for collecting emotional data and optimizing the conversion process" is a function for making adjustments based on the collected emotional data to improve the efficiency of the data conversion process and user satisfaction.

[1197] This invention is a system that uses a generative AI model and an emotion engine to convert data of different formats into a unified format. The goal is to improve the user experience by recognizing user emotions and optimizing the conversion process during the conversion process.

[1198] The system's components include a server, a terminal, an emotion engine, and a generative AI model. The server functions as a data processing unit equipped with a high-performance processor and ample storage capacity. The terminal is an input device operated by the user, such as a PC or smartphone. The emotion engine is a software component that collects and analyzes user emotion data, and the generative AI model is an AI algorithm for generating text and converting data.

[1199] The operation of the system will be specifically described below.

[1200] Users use their devices to upload different types of data to the system. For example, when a user inputs a medical document template into the system, the emotion engine recognizes the user's emotions in real time and collects emotion data. Users simply open a file selection window on their device, select a document file, and click the upload button to send the file to the system.

[1201] The server analyzes the format of the received data, extracts metadata, and stores it in a storage device. For example, in the case of medical documents, information such as the patient's name, date of birth, and symptoms are extracted as metadata. Along with this metadata, the user's emotional data is also stored in the storage device.

[1202] The user selects the data to be converted using the terminal and sends a request to the server to convert it into a unified format. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[1203] Based on the conversion request, the server retrieves the relevant data from the storage device and sends it to the generative AI model. The generative AI model then converts the data based on the specified unified format. For example, it automatically converts "patient name" to "patient name" and "date of birth" to "date of birth" in different medical documents.

[1204] The server receives the converted data returned from the generative AI model and stores it back in the storage device. This converted data also includes conversion metadata (e.g., conversion date and time, original format information), enabling efficient data management.

[1205] Users can view the data converted into a unified format on their devices and download or edit it as needed. The emotion engine evaluates user satisfaction and sends feedback messages. This process not only ensures data consistency across different institutions, but also improves the user experience.

[1206] As a concrete example, the following prompt sentence is shown.

[1207] Please convert Hospital A's medical questionnaire into Hospital B's format:

[1208] Hospital A's medical questionnaire:

[1209] Patient name: Taro Yamada

[1210] Date of Birth: January 1, 1980

[1211] Symptom: Headache

[1212] Convert to Hospital B format:

[1213] Patient Name: Taro Yamada

[1214] Date of birth: January 1, 1980

[1215] Current medical condition: Headache

[1216] This system efficiently converts data of various formats into a unified format, and also provides a better user experience that takes user emotions into consideration.

[1217] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1218] Step 1:

[1219] A user uploads data to the system using a terminal. Specifically, the user opens a file selection window on the terminal, selects a medical document file, and clicks the upload button. The input is the medical document file, and the output is sending the file to the server. The user's emotions are monitored by the emotion engine.

[1220] Step 2:

[1221] The server receives the uploaded data and analyzes its format. Specifically, it analyzes the data structure and extracts metadata such as the patient's name, date of birth, and symptoms. The input is the medical document file sent in step 1, and the output is the extracted metadata. Along with this metadata, the user's emotion data collected by the emotion engine is also stored in the storage device.

[1222] Step 3:

[1223] The user uses the terminal to select the data they wish to convert and sends a request to convert it to a unified format to the server. Specifically, they select the target data from a data list on the terminal screen and click the conversion request button. The input is the selected data and the conversion request, and the output is the transmission of the conversion request to the server. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[1224] Step 4:

[1225] After receiving the conversion request, the server retrieves the corresponding data from the storage device and sends it to the generative AI model. Specifically, it reads the data including metadata from the storage device and sends it to the generative AI model along with the configured conversion rules. The input is the conversion request and the corresponding data, and the output is sending the data to the generative AI model.

[1226] Step 5:

[1227] The generative AI model analyzes the transmitted data and converts it into the specified unified format. Specifically, the generative AI model converts "patient name" to "patient name" and "date of birth" to "date of birth." The input is the data transmitted in step 4, and the output is the data converted into the unified format. The generative AI model's algorithm is also optimized based on the user's emotion data provided by the emotion engine.

[1228] Step 6:

[1229] The server receives the converted data from the generative AI model and stores it again in a storage device. Specifically, it stores the converted data again in a storage device and also adds conversion metadata (e.g., conversion date and time, original format information). The input is the converted data from the generative AI model, and the output is the reconverted data stored in a storage device.

[1230] Step 7:

[1231] The user can use their device to check the converted data and download or edit it as needed. Specifically, the device displays a list of converted data, selects the desired data, and clicks the download button. The input is the converted data stored in the storage device, and the output is the data downloaded to the user's device. Finally, the emotion engine evaluates the user's satisfaction and sends a feedback message.

[1232] (Application example 2)

[1233] Next, a description will be given of Application 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."

[1234] In the process of converting documents of different formats into a unified format, the challenge is to provide a more efficient and user-friendly document conversion system that takes into account the impact of the user's emotional state on conversion accuracy and efficiency.In addition, security-related documents also have different formats depending on the site, and unifying them is required for efficient data management and rapid information sharing.

[1235] 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.

[1236] In this invention, the server includes means for receiving documents in different formats, means for analyzing the data format of the received documents and extracting metadata, means for storing the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and transmitting it to a generative AI model, means for converting documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for receiving and analyzing user emotion data and optimizing the generative AI model's algorithm based on the emotion data, and means for monitoring user emotion and displaying appropriate support messages. This improves the efficiency of document conversion from different formats to a unified format, enabling responses that take user emotion into consideration. Furthermore, standardizing the formats of security-related documents that differ from site to site can achieve efficient data management and rapid information sharing.

[1237] Definitions of important words

[1238] "Documents in different formats" refer to document files with different formats and layouts created by different departments or work sites.

[1239] "Metadata" refers to additional information and attribute information about the data format and content of a document, and contributes to improving database management and search efficiency.

[1240] A "database" is a system for systematically storing and managing multiple data.

[1241] A "generative AI model" is an algorithm or system that uses artificial intelligence to automatically generate or transform data or documents.

[1242] A "unified format" is a format in which documents of different formats are converted into a single, consistent format, improving data consistency and utilization efficiency.

[1243] A "conversion request" is a request submitted by a user to the system to convert documents of different formats into a unified format.

[1244] "Emotional data" refers to data obtained as a result of evaluating and analyzing the user's emotional state.

[1245] An "algorithm" is a set of procedures and methods for performing specific calculations or processes, and is the basis for controlling the operation of generative AI models.

[1246] "Support messages" are advice and guidance provided by the system according to the user's emotional state, and are intended to improve the user's operational efficiency.

[1247] MODE FOR CARRYING OUT THE INVENTION

[1248] System Configuration

[1249] This invention is a system that efficiently converts documents of different formats into a unified format and provides support messages that take into account the user's feelings. This system consists of the following main components:

[1250] 1. User Device

[1251] 2. Cloud Server

[1252] 3. Database

[1253] 4. Generative AI Models

[1254] 5. Sentiment Analysis Engine

[1255] Hardware and Software

[1256] Hardware:

[1257] User device (smart glasses or smartphone)

[1258] Cloud servers (common cloud server providers, e.g., AWS, Google Cloud)

[1259] software:

[1260] Data analysis libraries (e.g., pandas)

[1261] Generative AI model libraries (e.g., OpenAI GPT, BERT)

[1262] Sentiment analysis engines (e.g., IBM Watson, Microsoft Azure Emotion API)

[1263] Connectivity libraries (e.g. MQTT)

[1264] User device operation

[1265] Users use smart glasses or smartphones to input documents obtained from different sites or departments. The user's emotional state is continuously monitored by an emotion analysis engine, and the data is sent to a cloud server. For example, when entering reports such as "surveillance camera abnormalities" or "intrusion detection" at a security site, emotional data such as impatience or tension is also collected at the same time.

[1266] Cloud server processing

[1267] The cloud server receives the text and emotion data sent from the user device and performs the following processes:

[1268] 1. Data Analysis:

[1269] The cloud server first analyzes the data format of the received document and extracts the necessary metadata. For example, if a report of a "surveillance camera malfunction" is sent, metadata such as the camera number and the details of the malfunction will be extracted.

[1270] 2. Data Retention:

[1271] The extracted metadata is stored in a database, along with the user's emotional data.

[1272] 3. Accepting conversion requests:

[1273] When a user sends a request to the cloud server to convert a specific document into a unified format, the cloud server accepts the request, retrieves the target document data from the database, and sends it to the generative AI model.

[1274] 4. Run the generative AI model:

[1275] The generative AI model converts documents of different formats into a unified format based on the submitted document data, and optimizes the model's algorithm using user sentiment data.

[1276] 5. Resave the converted data:

[1277] The converted document data in a unified format is then stored back on the cloud server, and the conversion process is also recorded as metadata.

[1278] Providing unified format documents

[1279] The user can check the converted document data on their device and download or edit it as needed. The sentiment analysis engine evaluates the user's satisfaction and provides appropriate support messages. This reduces stress while working in security situations and enables users to work efficiently.

[1280] Specific examples

[1281] Data Entry Example

[1282] Report from Scene A: "Surveillance camera malfunction: Camera 3 has stopped working."

[1283] Prompt Sentence Examples

[1284] Send the following prompt to the generative AI model:

[1285] Please convert the following security reports into a unified format:

[1286] Report A: Surveillance Camera Abnormality: Camera 3 has stopped working

[1287] This system allows users to efficiently convert documents of different formats into a unified format and receive optimal support that takes emotions into consideration.

[1288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1289] Program processing steps

[1290] Step 1:

[1291] The user inputs documents in different formats into a device (smart glasses or smartphone), which then sends the input data to the cloud server. The input data includes the document content and the user's emotional data. For example, a report such as "Surveillance camera abnormality: Camera 3 has stopped working" is sent along with the emotional data "anxious."

[1292] Step 2:

[1293] The cloud server analyzes the received document and extracts metadata. For example, from a document titled "Surveillance camera abnormality," it extracts the metadata "Camera 3" and "Out of operation." Emotion data is also analyzed, and this data is stored in a database. The input data is multiple document data and emotion data, and the output data is the analyzed metadata and save instructions.

[1294] Step 3:

[1295] A user sends a request to convert a report of a "surveillance camera anomaly" into a unified format from their terminal. For example, they send a request to convert the report into a unified format. At this time, the user's emotional data is also acquired in real time. The input data is the conversion request and the emotional data, and the output data is a confirmation of the conversion request.

[1296] Step 4:

[1297] The cloud server retrieves the target document data from the database and sends the document data and emotion data to the generative AI model. For example, the cloud server retrieves the document data for "surveillance camera abnormality," adds emotion data, and sends it to the generative AI model. The input data is the document data and emotion data, and the output data is a transmission confirmation.

[1298] Step 5:

[1299] The generative AI model analyzes the document data and converts it into a unified format. The algorithm is optimized based on the emotion data, and the conversion process is carried out. For example, "Surveillance camera anomaly" is converted into "Security incident report." The input data is the document data and emotion data, and the output data is the converted document in a unified format.

[1300] Step 6:

[1301] The cloud server receives the converted document data from the generative AI model and stores it in the database. The conversion process is also recorded as metadata. The input data is the converted document data, and the output data is a notification that saving has been completed.

[1302] Step 7:

[1303] The user checks the converted document data on their device, downloading or editing it as necessary. The emotion analysis engine evaluates the level of satisfaction and displays a support message as appropriate. For example, a unified format document stating "Surveillance camera abnormality" is displayed on the device. The input data is the converted document data and real-time emotion data, and the output data is the support message and final confirmation.

[1304] This allows the entire system to operate efficiently, enabling highly accurate document conversion and support that takes user emotions into account.

[1305] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 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.

[1306] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[1307] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1308] [Fourth embodiment]

[1309] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1310] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1311] 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).

[1312] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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 control target 443 are also connected to the bus 52.

[1313] 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.

[1314] 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).

[1315] 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. 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.

[1316] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1317] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, 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.

[1318] 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.

[1319] 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.

[1320] In the robot 414, 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.

[1321] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1322] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[1323] System configuration

[1324] 1. Input of initial data (user):

[1325] The user operates the terminal to input document templates for each medical institution into the system. For example, a medical questionnaire from Clinic A and test results from Clinic B are uploaded to the system.

[1326] 2. Save to database (server):

[1327] The server receives medical documents uploaded by users, analyzes the data format, and extracts metadata, which are then stored in a database.

[1328] 3. Request for conversion to unified format (terminal):

[1329] The user operates the terminal to select the document to be converted and sends a request for conversion to the unified format to the server.

[1330] 4. Data transmission and conversion to the LLM model (server):

[1331] The server receives the conversion request, retrieves the target document data from the database, and then sends the document data and conversion rules to the generative AI model, which then analyzes the document and converts it into the specified unified format.

[1332] 5. Resave to unified format (server):

[1333] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[1334] 6. Provision of Unified Format Documents (User):

[1335] Users can download, view, and edit documents converted into a unified format on their devices, making it easier to combine and analyze data between different medical institutions.

[1336] Specific examples

[1337] For example, Clinic A uses the following questionnaire:

[1338] Patient name

[1339] date of birth

[1340] Symptoms

[1341] Meanwhile, Clinic B uses the following questionnaire:

[1342] Patient Name

[1343] birthday

[1344] Current medical condition

[1345] Processing flow

[1346] 1. Enter the initial data:

[1347] The user uploads the medical questionnaires from Clinic A and Clinic B to the system. For example, the medical questionnaire from Clinic A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache."

[1348] 2. Save to database:

[1349] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Clinic A's data might be saved as "Patient Name: Taro Yamada," "Date of Birth: January 1, 1980," and "Symptoms: Headache."

[1350] 3. Request for conversion to unified format:

[1351] The user sends a request from the terminal to the server to convert the medical questionnaire from Clinic A into the format of Clinic B.

[1352] 4. Data transfer and conversion to the LLM model:

[1353] The server retrieves the relevant questionnaire data from the database and sends it to the LLM model, which automatically converts "Patient Name" to "Patient Name," "Birth Date" to "Birthday," and "Symptoms" to "Current Condition."

[1354] 5. Resave to unified format:

[1355] The server receives the converted data and restores it to the database. For example, Clinic A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache."

[1356] 6. Provision of uniform format documents:

[1357] The user can check the converted medical questionnaire on the terminal and download or edit it as necessary. This ensures data consistency between Clinic A and Clinic B.

[1358] This invention will unify the document formats used by different medical institutions, enabling more efficient use of data and promoting medical research.

[1359] The processing flow will be explained below.

[1360] Step 1:

[1361] A user uses a terminal to upload document templates from Hospital A and Hospital B to the system. When uploading, the user can select each document type, such as a medical questionnaire, test results, or medical records.

[1362] Step 2:

[1363] The server receives the uploaded documents. After receiving them, the server analyzes the content of each document and identifies the document type (e.g., medical questionnaire, test results, etc.).

[1364] Step 3:

[1365] The server extracts metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the analyzed data, and the extracted metadata is registered in a database.

[1366] Step 4:

[1367] The server stores the parsed document content and metadata in a database, along with any necessary tagging to enable future reuse.

[1368] Step 5:

[1369] The user selects a specific document on the terminal and requests conversion to a unified format. The user specifies the details of the unified format (e.g., which hospital's format to convert to).

[1370] Step 6:

[1371] The terminal sends the user's conversion request to the server. The request includes the document ID to be converted and the requested format information.

[1372] Step 7:

[1373] The server receives the conversion request and retrieves the corresponding document data from the database. The retrieved document data includes the document content and metadata.

[1374] Step 8:

[1375] The server sends the document data and the unified format conversion rules to the generative AI model, which then begins analyzing and converting the document data.

[1376] Step 9:

[1377] The generative AI model analyzes the document content and converts it into a specified unified format, specifically by changing field names (e.g., changing "Patient Name" to "Patient First Name") and adjusting the data format.

[1378] Step 10:

[1379] The server receives the converted document data from the generative AI model, and checks that the received document data conforms to the unified format.

[1380] Step 11:

[1381] The server re-stores the converted document data in the database. When re-saving, metadata indicating that the conversion has occurred (e.g., conversion date and time, source format, and destination format) is added.

[1382] Step 12:

[1383] The user accesses the database to obtain the converted document from the terminal. The user searches for the document in the unified format from the database, and downloads or views it as needed.

[1384] Step 13:

[1385] The terminal sends the user's download request to the server, and the server sends the document in a unified format to the terminal, where the user can view and edit the document.

[1386] In this way, the system converts documents from different medical institutions into a unified format, promoting efficient data utilization and medical research.

[1387] Example 1

[1388] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1389] The lack of standardized medical document formats used by different medical institutions makes it difficult to exchange and integrate information. This leads to a lack of data consistency and reduces the efficiency of statistical analysis and medical research. Furthermore, manual format conversion is time-consuming and labor-intensive, and there is a risk of human error.

[1390] 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.

[1391] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for analyzing medical documents uploaded from a terminal and storing them in the database, means for generating prompt sentences for the generative AI model and converting document data to the unified format in response to the conversion request, and means for adding conversion metadata to the re-saved data. This enables standardization of document formats among different medical institutions and efficient use of data.

[1392] "Medical documents in different formats" refers to medical documents such as medical questionnaires and test results that are created in different formats at multiple medical institutions.

[1393] "Data format analysis" refers to the process of analyzing the content of received medical documents and extracting specific items or information.

[1394] "Metadata" is data that indicates additional information about the contents of medical documents, and is information that facilitates management and searching in a database.

[1395] A "database" is a collection of data that is organized and stored in an organized manner, and is a system that allows for easy searching and updating.

[1396] A "request for conversion to a unified format" is a request sent by a user to a server to convert a particular document into a standardized format.

[1397] A "generative AI model" is an AI technology that models human language generation capabilities and generates and converts documents based on large datasets.

[1398] A "prompt sentence" is an input sentence that instructs the generative AI model on how to process something, and includes specific conversion rules.

[1399] "Conversion metadata" is additional information about the converted document that is generated during the process of converting into a unified format, and is information for maintaining the correspondence with the original document.

[1400] A "terminal" is a device such as a computer, tablet, or smartphone that a user uses to access the system.

[1401] A "server" is a computer system that provides resources and data over a network and processes requests from client terminals.

[1402] "Document data" refers to specific information contained in a medical document, including items such as names, dates, and symptoms.

[1403] MODE FOR CARRYING OUT THE INVENTION

[1404] This invention is a system that uses a generative AI model to convert different medical document templates into a unified format. The program processing of this system is explained below in natural language.

[1405] Overall system configuration

[1406] Input of initial data (user)

[1407] Users use their devices to upload document templates for each medical institution to the system. Users operate devices such as PCs, tablets, and smartphones to enter information such as the medical questionnaire from Clinic A and the test results from Clinic B into the system. Specifically, users operate the system's input screen, click the "File Upload" button, select medical document files from their local disk, and then click the "Upload" button, which sends these files to the server.

[1408] Save to database (server)

[1409] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. For example, an analysis program runs on the server, analyzes the document contents, and extracts items such as the patient's name and date of birth. This information is then stored as metadata in a database in JSON format or similar.

[1410] Conversion request to unified format (user)

[1411] The user operates the terminal, selects the document to be converted, and sends a request for conversion to the unified format to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using the drop-down list or search function, and clicks the "Convert to unified format" button, which sends a conversion request to the server.

[1412] Data transmission and conversion to the LLM model (server)

[1413] The server receives the conversion request, retrieves the target document data from the database, and sends it to the generative AI model (e.g., GPT-4). The server generates a prompt sentence before sending it to the LLM model. The prompt sentence contains the original document data and the conversion rules. The LLM model receives the document data and automatically converts it into the specified format.

[1414] Resave to unified format (server)

[1415] The server receives the converted document data returned by the generative AI model and restores it to the database. When restoring the data, conversion metadata is also added, making it possible to clearly identify the correspondence between the original document and the converted document.

[1416] Provision of unified format documents (user)

[1417] Users can download, view, and edit the converted documents on their devices, facilitating data sharing and analysis between different medical institutions.

[1418] Specific examples

[1419] For example, Clinic A uses the following questionnaire:

[1420] Patient name

[1421] date of birth

[1422] Symptoms

[1423] Meanwhile, Clinic B uses the following questionnaire:

[1424] Patient Name

[1425] birthday

[1426] Current medical condition

[1427] The user uploads the medical questionnaires for Clinic A and Clinic B to the system and sends a request to convert the medical questionnaire from Clinic A to the format of Clinic B. The server retrieves the relevant document from the database and generates the following prompt:

[1428] Convert the given medical document into the following format:

[1429] Original format:

[1430] Patient name: Taro Yamada

[1431] Date of Birth: January 1, 1980

[1432] Symptom: Headache

[1433] Unified format:

[1434] Patient Name: Taro Yamada

[1435] Date of birth: January 1, 1980

[1436] Current medical condition: Headache

[1437] The generative AI model converts the data based on the prompt and sends the results back to the server, which then stores the data in a database for users to view and download. This ensures data consistency between Clinic A and Clinic B.

[1438] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1439] Step 1:

[1440] Input of initial data (user)

[1441] The user uses the terminal to upload the document template of each medical institution to the system. Specifically, the user opens the system's input screen, clicks the "File Upload" button, selects the medical document file (e.g., the medical questionnaire for Clinic A) from the local disk, and clicks the "Upload" button.

[1442] Input: A medical document file selected by the user.

[1443] Output: Medical document data sent to the server.

[1444] Step 2:

[1445] Save to database (server)

[1446] The server receives the uploaded medical documents, analyzes their data format, and extracts metadata. Specifically, an analysis program is launched within the server, which analyzes the document contents (e.g., "patient name," "date of birth," and "symptoms") and extracts specific items. The analyzed data and metadata are then stored in a database.

[1447] Input: Medical document data uploaded by the user.

[1448] Output: A database containing the parsed medical document data and metadata.

[1449] Step 3:

[1450] Conversion request to unified format (user)

[1451] The user selects the document to be converted and sends the conversion request to the server. Specifically, the user accesses the system's conversion request screen, selects the document to be converted using a drop-down list or the search function, and clicks the "Convert to unified format" button.

[1452] Input: The conversion request selected by the user.

[1453] Output: The conversion request data sent to the server.

[1454] Step 4:

[1455] Data transmission and conversion to the LLM model (server)

[1456] After receiving the conversion request, the server retrieves the target document data from the database and sends it to the generative AI model (e.g., GPT-4). Specifically, the server reads the relevant document data from the database and generates a prompt. The generated prompt and the document data are sent together to the generative AI model to convert the document into a unified format.

[1457] Input: Document data retrieved from the database and generated prompt statements.

[1458] Output: The conversion request and document data sent to the generative AI model, and the converted document data.

[1459] Step 5:

[1460] Resave to unified format (server)

[1461] The server receives the converted document data from the generative AI model and restores it to the database. Specifically, it adds conversion metadata to the converted document data and stores it in the database. This clarifies the correspondence between the original document and the converted document.

[1462] Input: The transformed document data received from the generative AI model.

[1463] Output: The resaved converted document data and conversion metadata.

[1464] Step 6:

[1465] Provision of unified format documents (user)

[1466] Users can download, view, and edit the converted documents on their devices. Specifically, users access the system's document viewing screen and select a document from the list of documents converted to a unified format. They view the selected document on their device and click buttons to download or edit it as needed.

[1467] Input: A unified format document selected by the user.

[1468] Output: Medical document data in a unified format provided to the terminal.

[1469] (Application example 1)

[1470] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1471] Medical institutions often handle medical documents in different formats, and converting these documents into a unified format is time-consuming and inefficient. It is also important to manage this data securely and provide access only to appropriate users, but current methods make it difficult to ensure complete security. To solve this problem, a system with efficient conversion methods and advanced security measures is needed.

[1472] 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.

[1473] In this invention, the server includes means for receiving medical documents in different formats, means for analyzing the data format of the received medical documents and extracting metadata, means for saving the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and sending it to a generative AI model, means for generating a prompt sentence when sending it to the generative AI model, means for converting medical documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for encrypting the converted document data, and means for providing the document data in the unified format, thereby enabling efficient conversion and secure management of medical documents in different formats.

[1474] "Medical documents in different formats" refers to patient information and medical records with different formats and contents that are created independently by different medical institutions or departments.

[1475] "Analyzing the data format" means analyzing the structure and content of the received medical document and identifying each item and data type.

[1476] "Extracting metadata" means extracting basic information and attribute information (e.g., patient name, treatment date, diagnosis, etc.) contained in medical documents.

[1477] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to analyze medical documents and convert them into a unified format.

[1478] A "prompt" is a question or command sentence entered into a generative AI model to instruct it on a specific transformation task.

[1479] A "unified format" is a standardized document format that allows for uniform management and analysis of multiple different types of medical documents.

[1480] A "conversion request" is a request from a user to the system to convert a particular medical document into a unified format.

[1481] "Encryption" means transforming data in medical documents using a specific algorithm so that the data cannot be accessed by third parties.

[1482] "Restoring" means storing the converted document data in a database so that it can be easily accessed later.

[1483] "Providing" means making the converted medical documents in a unified format available for viewing, editing, and downloading on the user's device.

[1484] This invention is a system that realizes an application that converts different formats of medical documents into a unified format and securely manages and provides them. Below, the program processing of this system is explained in natural language.

[1485] System Configuration

[1486] The system consists of the following main components:

[1487] 1. Data Entry Interface

[1488] Hardware: Smartphones, tablets

[1489] Software: Camera app, file upload function

[1490] Users can use smartphones or tablets to take photos of medical documents in different formats or upload them as files, allowing various types of medical documents to be imported into the system.

[1491] 2. Data format conversion

[1492] Software: Tesseract OCR, OpenAI GPT-4

[1493] Incoming medical document data is first converted to text using Tesseract OCR, then a generative AI model such as OpenAI GPT-4 is used to convert the text data into a unified format. When using a generative AI model, a prompt is generated to instruct the model on a specific conversion task.

[1494] Prompt Sentence Examples

[1495] "Please convert the following document data into a unified format. Please list each item on a separate line. Patient name: Yamada Taro Date of birth: January 1, 1980 Symptoms: Headache"

[1496] 3. Data Encryption and Storage

[1497] Software: PyCryptodome, cloud storage (AWS, etc.)

[1498] Once converted into a unified format, the data is encrypted using PyCryptodome with a strong encryption method such as AES-256, and then securely stored in cloud storage, where it can be easily accessed later while minimizing security risks.

[1499] 4. Secure data viewing and authentication management

[1500] Hardware: Smartphones, tablets

[1501] Software: Google Firebase Auth

[1502] When users access data, two-step authentication and biometric authentication are performed using authentication services such as Google Firebase Auth, ensuring that only legitimate users can access the data.

[1503] 5. Audit Log Management

[1504] Software: MongoDB

[1505] All data access and operation history is recorded in MongoDB, making it possible to audit system usage and enhance security.

[1506] Adding specific examples

[1507] For example, a user takes a photo of a medical questionnaire from Clinic A with their smartphone and uploads it to the system. The questionnaire contains the following information: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Symptom: Headache." This data is received and extracted as text data using Tesseract OCR. It is then sent to the generative AI model along with a prompt, which converts it into a unified format: "Patient Name: Yamada Taro," "Birthdate: January 1, 1980," and "Current Symptom: Headache." This data is encrypted with AES-256 and stored in cloud storage. When a user attempts to view the data, they are authenticated via Google Firebase Auth, ensuring that only authorized users can access the data.

[1508] In this way, efficient conversion and secure management of different types of medical documents is achieved.

[1509] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1510] Step 1:

[1511] Data Entry:

[1512] Users use their smartphones or tablets to take or scan medical documents in different formats, and the input data is uploaded in image or PDF format.

[1513] Step 2:

[1514] Image and document recognition:

[1515] The server analyzes the images and PDFs it receives and converts them into text data using Tesseract OCR. The input is image data and the output is string data.

[1516] Step 3:

[1517] Metadata Extraction:

[1518] The server analyzes the text data and extracts metadata (patient name, date of birth, symptoms, etc.). The input is the string data obtained in step 2, and the output is the extracted metadata.

[1519] Step 4:

[1520] Save to database:

[1521] The server stores the extracted metadata in a database. The input is the extracted metadata, and the output is the information stored in the database.

[1522] Step 5:

[1523] Accepting conversion requests:

[1524] A user sends a request to the system from a terminal to convert a specific medical document into a unified format. The input is the conversion request information, and the output is a message confirming the conversion request.

[1525] Step 6:

[1526] Sending data to a generative AI model:

[1527] The server accepts the conversion request, retrieves the corresponding document data from the database, and sends it to the generative AI model. The input is the conversion request information and the document data retrieved from the database, and the output is the prompt text and the data to be sent.

[1528] Step 7:

[1529] Transformation by generative AI models:

[1530] The generative AI model converts medical documents in different formats into a unified format based on the prompt text and document data it receives. The input is the prompt text and document data, and the output is document data in the unified format.

[1531] Step 8:

[1532] Encryption of converted data:

[1533] The server encrypts the converted data with AES-256. The input is the document data converted to a unified format, and the output is the encrypted document data.

[1534] Step 9:

[1535] Resave to database:

[1536] The server restores the encrypted document data to the database. The input is the encrypted document data, and the output is the encrypted data stored in the database.

[1537] Step 10:

[1538] Data provided by:

[1539] The user authenticates and then views the medical documents converted into a unified format on the terminal. The input is authentication information, and the output is viewable document data.

[1540] The above processing steps enable efficient conversion and secure management of medical documents in different formats.

[1541] 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.

[1542] This invention is a system that uses a generative AI model and an emotion engine to convert different medical document templates into a unified format, and further optimizes the conversion process by recognizing the user's emotions. The program processing of this system is explained below in natural language.

[1543] System configuration

[1544] 1. Input of initial data (user):

[1545] The user operates the terminal to input document templates from each medical institution into the system. For example, they upload a medical questionnaire from Hospital A and test results from Hospital B. The emotion engine continuously recognizes the user's emotions as they are inputting.

[1546] 2. Save to database (server):

[1547] The server receives the medical documents uploaded by the user, analyzes the data format, and extracts metadata. The analyzed data and metadata are stored in a database. The user's emotional data is also stored in the database.

[1548] 3. Request for conversion to unified format (terminal):

[1549] The user operates the terminal to select the document to be converted and sends a request to convert it to a unified format to the server. The emotion engine monitors the user's emotional fluctuations and displays an assistant message as necessary.

[1550] 4. Data transmission and conversion to the LLM model (server):

[1551] The server receives the conversion request and retrieves the target document data from the database. The document data and conversion rules are then sent to the generative AI model, which analyzes the document and converts it into the specified unified format. The emotion engine optimizes the generative AI model's algorithm based on the user's emotional data.

[1552] 5. Resave to unified format (server):

[1553] The server receives the converted document data from the generative AI model and stores it in the database. The converted document data also includes conversion metadata, enabling efficient data management.

[1554] 6. Provision of Unified Format Documents (User):

[1555] Users can download, view, and edit documents converted into a unified format on their devices. The emotion engine evaluates user satisfaction and sends feedback messages as needed. This makes it easier to combine and analyze data across different medical institutions.

[1556] Specific examples

[1557] For example, Hospital A uses the following questionnaire:

[1558] Patient name

[1559] date of birth

[1560] Symptoms

[1561] Meanwhile, Hospital B uses the following questionnaire:

[1562] Patient Name

[1563] birthday

[1564] Current medical condition

[1565] Processing flow

[1566] 1. Enter the initial data:

[1567] The user uploads the medical questionnaires from Hospital A and Hospital B to the system. For example, the medical questionnaire from Hospital A contains the following information: "Patient name: Yamada Taro," "Date of birth: January 1, 1980," and "Symptoms: Headache." The emotion engine also continuously recognizes the user's emotional data (e.g., impatience, satisfaction, etc.).

[1568] 2. Save to database:

[1569] The server receives this data, analyzes the questionnaire format and metadata, and stores it in a database. For example, Hospital A's data might be saved as "Patient Name: Yamada Taro," "Date of Birth: January 1, 1980," and "Symptoms: Headache." At the same time, the user's emotional data is also saved.

[1570] 3. Request for conversion to unified format:

[1571] The user sends a request from their terminal to the server to convert a medical questionnaire from Hospital A into the format of Hospital B. The emotion engine monitors the user's fluctuating emotions and displays an appropriate support message.

[1572] 4. Data transfer and conversion to the LLM model:

[1573] The server retrieves the relevant medical questionnaire data from the database and sends it to the LLM model. The LLM model automatically converts "patient name" to "patient name," "date of birth" to "date of birth," and "symptoms" to "current medical condition." The emotion engine adjusts the algorithm of the generative AI model appropriately based on the user's emotion data.

[1574] 5. Resave to unified format:

[1575] The server receives the converted data and restores it to the database. For example, Hospital A's data is restored as "Patient name: Yamada Taro," "Birthday: January 1, 1980," and "Current condition: Headache." The conversion date and time and conversion format information are also saved as metadata.

[1576] 6. Provision of uniform format documents:

[1577] The user checks the converted questionnaire on their device and downloads or edits it as necessary. The emotion engine evaluates the user's emotions and sends feedback messages to help ensure user satisfaction. This ensures data consistency between Hospital A and Hospital B.

[1578] This invention not only unifies the document formats used among different medical institutions, but also provides a better user experience that takes into account the user's feelings.

[1579] The processing flow will be explained below.

[1580] Step 1:

[1581] The user uses a terminal to upload document templates from Hospital A and Hospital B to the system. The uploaded documents include medical questionnaires, test results, medical records, etc., and are set as templates. As the user types, the emotion engine recognizes the user's emotions in real time.

[1582] Step 2:

[1583] The server receives the uploaded medical document. After receiving it, it identifies the document type (e.g., medical questionnaire, test results) and performs an initial analysis, which extracts important items from the document.

[1584] Step 3:

[1585] The server then extracts structured metadata (e.g., creation date and time, hospital name, patient ID, etc.) from the extracted data. The extracted metadata is then registered in a database, and the document data itself is also stored.

[1586] Step 4:

[1587] The emotion engine analyzes the user's emotional data and evaluates the stress and satisfaction they feel. The emotional data is also stored in a database and used to optimize the conversion process.

[1588] Step 5:

[1589] The user operates the terminal to select a specific document and request its conversion to a unified format. The user specifies the details of the document to be converted (e.g., which template to convert it to). The emotion engine continuously monitors the user's emotions during operation and provides help messages and support as needed.

[1590] Step 6:

[1591] The terminal sends the user's conversion request to the server, which includes the document ID to be converted and the requested format information.

[1592] Step 7:

[1593] The server receives the conversion request and retrieves the specified document data from the database. The retrieved document data includes the document content and metadata.

[1594] Step 8:

[1595] The server sends the acquired document data and conversion rules to the generative AI model. The generative AI model analyzes the document data and converts it into the specified unified format. At this time, the generative AI model's algorithm is optimized appropriately based on the user's emotional data recognized by the emotion engine.

[1596] Step 9:

[1597] The generative AI model analyzes the document content and changes the specified field names (e.g., converting "Patient Name" to "Patient First Name") and adjusts the data format.

[1598] Step 10:

[1599] The server receives the converted document data from the generative AI model, and checks that the received data conforms to the unified format.

[1600] Step 11:

[1601] The server then re-stores the converted document data in the database, adding metadata such as the date and time of the conversion and the format information of the source and destination documents.

[1602] Step 12:

[1603] The user searches and accesses the converted document from their device, and the emotion engine evaluates the user's current emotions and displays feedback messages based on their satisfaction or stress level.

[1604] Step 13:

[1605] The user clicks the "Download" button on the terminal to download the converted document. The server receives the download request and sends the corresponding document data to the terminal.

[1606] Step 14:

[1607] The user views the converted document on the device and edits it as necessary. The emotion engine monitors this and provides assistance when the user wants to convert it again.

[1608] In this way, the system not only converts documents from different medical institutions into a unified format, but also optimizes the process by taking into account user sentiment, providing a better user experience.

[1609] Example 2

[1610] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1611] With the existence of data in different formats, there is a need for easy and efficient conversion into a unified format. It is also important to consider the user's feelings during the data conversion process and improve the user experience. This will make it easier to use data between different institutions and provide a system that can reduce the stress users feel when converting data.

[1612] 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.

[1613] In this invention, the server includes means for receiving data in different formats, means for analyzing the format of the received data and extracting metadata, means for saving the extracted metadata in a storage device, means for accepting a conversion request, means for acquiring data based on the conversion request and sending it to a generative AI model, means for converting data in different formats into a unified format using the generative AI model, means for restoring the converted data to a storage device, means for providing data in the unified format, and an emotion engine for recognizing user emotions, wherein the emotion engine collects user emotion data and optimizes the conversion process. This enables efficient data conversion between different institutions and improves the user experience.

[1614] "Heterogeneous data" is information or documents written in different structures or formats.

[1615] "Means for receiving" refers to the function by which the system acquires input data, takes it in and processes it internally.

[1616] "Means for analyzing formats and extracting metadata" refers to a function for understanding the structure of input data and extracting necessary information (metadata).

[1617] A "storage device" is a hardware or storage system for storing data and metadata.

[1618] The "means for accepting a conversion request" is a function for receiving a data conversion instruction from a user and transmitting the instruction to the system.

[1619] "Means for acquiring data and sending it to the generative AI model" refers to a function that acquires the necessary data from a storage device and sends that data to the generative AI model for processing.

[1620] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate or transform data.

[1621] "Means for converting to a unified format" refers to the ability to convert data of different formats into a standardized format using a generative AI model.

[1622] The "means for re-saving" is a function for saving the converted data again in the storage device.

[1623] The "means for providing" is a function for displaying or downloading the converted unified format data so that the user can use it.

[1624] The "emotion engine" is a system that recognizes the user's emotions and collects and analyzes that data.

[1625] The "means for collecting emotional data and optimizing the conversion process" is a function for making adjustments based on the collected emotional data to improve the efficiency of the data conversion process and user satisfaction.

[1626] This invention is a system that uses a generative AI model and an emotion engine to convert data of different formats into a unified format. The goal is to improve the user experience by recognizing user emotions and optimizing the conversion process during the conversion process.

[1627] The system's components include a server, a terminal, an emotion engine, and a generative AI model. The server functions as a data processing unit equipped with a high-performance processor and ample storage capacity. The terminal is an input device operated by the user, such as a PC or smartphone. The emotion engine is a software component that collects and analyzes user emotion data, and the generative AI model is an AI algorithm for generating text and converting data.

[1628] The operation of the system will be specifically described below.

[1629] Users use their devices to upload different types of data to the system. For example, when a user inputs a medical document template into the system, the emotion engine recognizes the user's emotions in real time and collects emotion data. Users simply open a file selection window on their device, select a document file, and click the upload button to send the file to the system.

[1630] The server analyzes the format of the received data, extracts metadata, and stores it in a storage device. For example, in the case of medical documents, information such as the patient's name, date of birth, and symptoms are extracted as metadata. Along with this metadata, the user's emotional data is also stored in the storage device.

[1631] The user selects the data to be converted using the terminal and sends a request to the server to convert it into a unified format. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[1632] Based on the conversion request, the server retrieves the relevant data from the storage device and sends it to the generative AI model. The generative AI model then converts the data based on the specified unified format. For example, it automatically converts "patient name" to "patient name" and "date of birth" to "date of birth" in different medical documents.

[1633] The server receives the converted data returned from the generative AI model and stores it back in the storage device. This converted data also includes conversion metadata (e.g., conversion date and time, original format information), enabling efficient data management.

[1634] Users can view the data converted into a unified format on their devices and download or edit it as needed. The emotion engine evaluates user satisfaction and sends feedback messages. This process not only ensures data consistency across different institutions, but also improves the user experience.

[1635] As a concrete example, the following prompt sentence is shown.

[1636] Please convert Hospital A's medical questionnaire into Hospital B's format:

[1637] Hospital A's medical questionnaire:

[1638] Patient name: Taro Yamada

[1639] Date of Birth: January 1, 1980

[1640] Symptom: Headache

[1641] Convert to Hospital B format:

[1642] Patient Name: Taro Yamada

[1643] Date of birth: January 1, 1980

[1644] Current medical condition: Headache

[1645] This system efficiently converts data of various formats into a unified format, and also provides a better user experience that takes user emotions into consideration.

[1646] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1647] Step 1:

[1648] A user uploads data to the system using a terminal. Specifically, the user opens a file selection window on the terminal, selects a medical document file, and clicks the upload button. The input is the medical document file, and the output is sending the file to the server. The user's emotions are monitored by the emotion engine.

[1649] Step 2:

[1650] The server receives the uploaded data and analyzes its format. Specifically, it analyzes the data structure and extracts metadata such as the patient's name, date of birth, and symptoms. The input is the medical document file sent in step 1, and the output is the extracted metadata. Along with this metadata, the user's emotion data collected by the emotion engine is also stored in the storage device.

[1651] Step 3:

[1652] The user uses the terminal to select the data they wish to convert and sends a request to convert it to a unified format to the server. Specifically, they select the target data from a data list on the terminal screen and click the conversion request button. The input is the selected data and the conversion request, and the output is the transmission of the conversion request to the server. The emotion engine monitors the user's emotions during this process and displays support messages as needed.

[1653] Step 4:

[1654] After receiving the conversion request, the server retrieves the corresponding data from the storage device and sends it to the generative AI model. Specifically, it reads the data including metadata from the storage device and sends it to the generative AI model along with the configured conversion rules. The input is the conversion request and the corresponding data, and the output is sending the data to the generative AI model.

[1655] Step 5:

[1656] The generative AI model analyzes the transmitted data and converts it into the specified unified format. Specifically, the generative AI model converts "patient name" to "patient name" and "date of birth" to "date of birth." The input is the data transmitted in step 4, and the output is the data converted into the unified format. The generative AI model's algorithm is also optimized based on the user's emotion data provided by the emotion engine.

[1657] Step 6:

[1658] The server receives the converted data from the generative AI model and stores it again in a storage device. Specifically, it stores the converted data again in a storage device and also adds conversion metadata (e.g., conversion date and time, original format information). The input is the converted data from the generative AI model, and the output is the reconverted data stored in a storage device.

[1659] Step 7:

[1660] The user can use their device to check the converted data and download or edit it as needed. Specifically, the device displays a list of converted data, selects the desired data, and clicks the download button. The input is the converted data stored in the storage device, and the output is the data downloaded to the user's device. Finally, the emotion engine evaluates the user's satisfaction and sends a feedback message.

[1661] (Application example 2)

[1662] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1663] In the process of converting documents of different formats into a unified format, the challenge is to provide a more efficient and user-friendly document conversion system that takes into account the impact of the user's emotional state on conversion accuracy and efficiency.In addition, security-related documents also have different formats depending on the site, and unifying them is required for efficient data management and rapid information sharing.

[1664] 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.

[1665] In this invention, the server includes means for receiving documents in different formats, means for analyzing the data format of the received documents and extracting metadata, means for storing the extracted metadata in a database, means for accepting a conversion request to a unified format, means for acquiring document data based on the conversion request and transmitting it to a generative AI model, means for converting documents in different formats to a unified format using the generative AI model, means for restoring the converted document data to the database, means for providing document data in the unified format, means for receiving and analyzing user emotion data and optimizing the generative AI model's algorithm based on the emotion data, and means for monitoring user emotion and displaying appropriate support messages. This improves the efficiency of document conversion from different formats to a unified format, enabling responses that take user emotion into consideration. Furthermore, standardizing the formats of security-related documents that differ from site to site can achieve efficient data management and rapid information sharing.

[1666] Definitions of important words

[1667] "Documents in different formats" refer to document files with different formats and layouts created by different departments or work sites.

[1668] "Metadata" refers to additional information and attribute information about the data format and content of a document, and contributes to improving database management and search efficiency.

[1669] A "database" is a system for systematically storing and managing multiple data.

[1670] A "generative AI model" is an algorithm or system that uses artificial intelligence to automatically generate or transform data or documents.

[1671] A "unified format" is a format in which documents of different formats are converted into a single, consistent format, improving data consistency and utilization efficiency.

[1672] A "conversion request" is a request submitted by a user to the system to convert documents of different formats into a unified format.

[1673] "Emotional data" refers to data obtained as a result of evaluating and analyzing the user's emotional state.

[1674] An "algorithm" is a set of procedures and methods for performing specific calculations or processes, and is the basis for controlling the operation of generative AI models.

[1675] "Support messages" are advice and guidance provided by the system according to the user's emotional state, and are intended to improve the user's operational efficiency.

[1676] MODE FOR CARRYING OUT THE INVENTION

[1677] System Configuration

[1678] This invention is a system that efficiently converts documents of different formats into a unified format and provides support messages that take into account the user's feelings. This system consists of the following main components:

[1679] 1. User Device

[1680] 2. Cloud Server

[1681] 3. Database

[1682] 4. Generative AI Models

[1683] 5. Sentiment Analysis Engine

[1684] Hardware and Software

[1685] Hardware:

[1686] User device (smart glasses or smartphone)

[1687] Cloud servers (common cloud server providers, e.g., AWS, Google Cloud)

[1688] software:

[1689] Data analysis libraries (e.g., pandas)

[1690] Generative AI model libraries (e.g., OpenAI GPT, BERT)

[1691] Sentiment analysis engines (e.g., IBM Watson, Microsoft Azure Emotion API)

[1692] Connectivity libraries (e.g. MQTT)

[1693] User device operation

[1694] Users use smart glasses or smartphones to input documents obtained from different sites or departments. The user's emotional state is continuously monitored by an emotion analysis engine, and the data is sent to a cloud server. For example, when entering reports such as "surveillance camera abnormalities" or "intrusion detection" at a security site, emotional data such as impatience or tension is also collected at the same time.

[1695] Cloud server processing

[1696] The cloud server receives the text and emotion data sent from the user device and performs the following processes:

[1697] 1. Data Analysis:

[1698] The cloud server first analyzes the data format of the received document and extracts the necessary metadata. For example, if a report of a "surveillance camera malfunction" is sent, metadata such as the camera number and the details of the malfunction will be extracted.

[1699] 2. Data Retention:

[1700] The extracted metadata is stored in a database, along with the user's emotional data.

[1701] 3. Accepting conversion requests:

[1702] When a user sends a request to the cloud server to convert a specific document into a unified format, the cloud server accepts the request, retrieves the target document data from the database, and sends it to the generative AI model.

[1703] 4. Run the generative AI model:

[1704] The generative AI model converts documents of different formats into a unified format based on the submitted document data, and optimizes the model's algorithm using user sentiment data.

[1705] 5. Resave the converted data:

[1706] The converted document data in a unified format is then stored back on the cloud server, and the conversion process is also recorded as metadata.

[1707] Providing unified format documents

[1708] The user can check the converted document data on their device and download or edit it as needed. The sentiment analysis engine evaluates the user's satisfaction and provides appropriate support messages. This reduces stress while working in security situations and enables users to work efficiently.

[1709] Specific examples

[1710] Data Entry Example

[1711] Report from Scene A: "Surveillance camera malfunction: Camera 3 has stopped working."

[1712] Prompt Sentence Examples

[1713] Send the following prompt to the generative AI model:

[1714] Please convert the following security reports into a unified format:

[1715] Report A: Surveillance Camera Abnormality: Camera 3 has stopped working

[1716] This system allows users to efficiently convert documents of different formats into a unified format and receive optimal support that takes emotions into consideration.

[1717] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1718] Program processing steps

[1719] Step 1:

[1720] The user inputs documents in different formats into a device (smart glasses or smartphone), which then sends the input data to the cloud server. The input data includes the document content and the user's emotional data. For example, a report such as "Surveillance camera abnormality: Camera 3 has stopped working" is sent along with the emotional data "anxious."

[1721] Step 2:

[1722] The cloud server analyzes the received document and extracts metadata. For example, from a document titled "Surveillance camera abnormality," it extracts the metadata "Camera 3" and "Out of operation." Emotion data is also analyzed, and this data is stored in a database. The input data is multiple document data and emotion data, and the output data is the analyzed metadata and save instructions.

[1723] Step 3:

[1724] A user sends a request to convert a report of a "surveillance camera anomaly" into a unified format from their terminal. For example, they send a request to convert the report into a unified format. At this time, the user's emotional data is also acquired in real time. The input data is the conversion request and the emotional data, and the output data is a confirmation of the conversion request.

[1725] Step 4:

[1726] The cloud server retrieves the target document data from the database and sends the document data and emotion data to the generative AI model. For example, the cloud server retrieves the document data for "surveillance camera abnormality," adds emotion data, and sends it to the generative AI model. The input data is the document data and emotion data, and the output data is a transmission confirmation.

[1727] Step 5:

[1728] The generative AI model analyzes the document data and converts it into a unified format. The algorithm is optimized based on the emotion data, and the conversion process is carried out. For example, "Surveillance camera anomaly" is converted into "Security incident report." The input data is the document data and emotion data, and the output data is the converted document in a unified format.

[1729] Step 6:

[1730] The cloud server receives the converted document data from the generative AI model and stores it in the database. The conversion process is also recorded as metadata. The input data is the converted document data, and the output data is a notification that saving has been completed.

[1731] Step 7:

[1732] The user checks the converted document data on their device, downloading or editing it as necessary. The emotion analysis engine evaluates the level of satisfaction and displays a support message as appropriate. For example, a unified format document stating "Surveillance camera abnormality" is displayed on the device. The input data is the converted document data and real-time emotion data, and the output data is the support message and final confirmation.

[1733] This allows the entire system to operate efficiently, enabling highly accurate document conversion and support that takes user emotions into account.

[1734] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice 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 voice data.

[1735] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[1736] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1737] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1738] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1739] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1740] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1741] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1742] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1743] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1744] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1745] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1746] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1747] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1748] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1749] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1750] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1751] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1752] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1753] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1754] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1755] The following is further disclosed regarding the above embodiment.

[1756] (Claim 1)

[1757] means for receiving medical documents in different formats;

[1758] means for analyzing the data format of the received medical document and extracting metadata;

[1759] a means for storing the extracted metadata in a database;

[1760] means for accepting a request for conversion to a unified format;

[1761] A means for obtaining document data based on a conversion request and transmitting the document data to a generative AI model;

[1762] A means of converting different medical documents into a unified format using generative AI models;

[1763] A means for re-storing the converted document data in the database;

[1764] A means of providing document data in a unified format

[1765] A system including:

[1766] (Claim 2)

[1767] The system according to claim 1, which converts document formats of different medical institutions into a unified format.

[1768] (Claim 3)

[1769] 10. The system of claim 1, wherein the system provides the terminal with medical documents converted into a unified format.

[1770] "Example 1"

[1771] (Claim 1)

[1772] means for receiving medical documents in different formats;

[1773] means for analyzing the data format of the received medical document and extracting metadata;

[1774] a means for storing the extracted metadata in a database;

[1775] means for accepting a request for conversion to a unified format;

[1776] A means for obtaining document data based on a conversion request and transmitting the document data to a generative AI model;

[1777] A means of converting different medical documents into a unified format using generative AI models;

[1778] A means for re-storing the converted document data in the database;

[1779] a means for providing document data in a unified format;

[1780] A means for analyzing medical documents uploaded from the terminal on the server and storing them in a database;

[1781] A means for generating prompt sentences for a generative AI model and converting document data into a unified format in response to a conversion request;

[1782] means for adding transformation metadata to the resaved data;

[1783] A system including:

[1784] (Claim 2)

[1785] The system according to claim 1, which converts document formats of different medical institutions into a unified format.

[1786] (Claim 3)

[1787] 10. The system of claim 1, wherein the system provides the terminal with medical documents converted into a unified format.

[1788] "Application Example 1"

[1789] (Claim 1)

[1790] means for receiving medical documents in different formats;

[1791] means for analyzing the data format of the received medical document and extracting metadata;

[1792] a means for storing the extracted metadata in a database;

[1793] means for accepting a request for conversion to a unified format;

[1794] A means for obtaining document data based on a conversion request and transmitting the document data to a generative AI model;

[1795] A means of converting different medical documents into a unified format using generative AI models;

[1796] a means for generating a prompt sentence when sent to the generative AI model;

[1797] A means for re-storing the converted document data in the database;

[1798] a means for encrypting the converted document data;

[1799] A means of providing document data in a unified format

[1800] A system including:

[1801] (Claim 2)

[1802] The system according to claim 1, which converts document formats of different medical institutions into a unified format.

[1803] (Claim 3)

[1804] 10. The system of claim 1, wherein the system provides the terminal with medical documents converted into a unified format.

[1805] "Example 2: Combining Emotion Engines"

[1806] (Claim 1)

[1807] means for receiving data in different formats;

[1808] means for analyzing the format of the received data and extracting metadata;

[1809] means for storing the extracted metadata in a storage device;

[1810] means for accepting a conversion request;

[1811] A means for obtaining data based on the transformation request and sending it to the generative AI model;

[1812] A means of converting different forms of data into a unified format using a generative AI model; and

[1813] means for restoring the converted data to a storage device;

[1814] a means for providing data in a uniform format;

[1815] an emotion engine that recognizes the user's emotions;

[1816] The system includes a means for an emotion engine to collect user emotion data and optimize the conversion process.

[1817] (Claim 2)

[1818] The system of claim 1, which converts data formats of different institutions into a unified format.

[1819] (Claim 3)

[1820] 2. The system of claim 1, wherein the data converted into a unified format is provided to the terminal.

[1821] "Application example 2 when combining emotion engines"

[1822] (Claim 1)

[1823] means for receiving documents in different formats;

[1824] means for analyzing the data format of the received document and extracting metadata;

[1825] a means for storing the extracted metadata in a database;

[1826] means for accepting a request for conversion to a unified format;

[1827] A means for obtaining document data based on a conversion request and transmitting the document data to a generative AI model;

[1828] A means of converting documents of different formats into a unified format using a generative AI model; and

[1829] A means for re-storing the converted document data in the database;

[1830] a means for providing document data in a unified format;

[1831] A means for receiving and analyzing user emotion data and optimizing the algorithm of the generative AI model based on the emotion data;

[1832] means for monitoring the user's emotions and displaying appropriate support messages;

[1833] A system including:

[1834] (Claim 2)

[1835] The system according to claim 1, wherein document formats of different data creation departments are converted into a unified format.

[1836] (Claim 3)

[1837] 10. The system of claim 1, wherein the system provides the terminal with a document converted into a unified format. [Explanation of symbols]

[1838] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving medical documents in different formats; means for analyzing the data format of the received medical document and extracting metadata; a means for storing the extracted metadata in a database; means for accepting a request for conversion to a unified format; A means for obtaining document data based on a conversion request and transmitting the document data to a generative AI model; A means of converting different medical documents into a unified format using generative AI models; A means for re-storing the converted document data in the database; A means of providing document data in a unified format A system including:

2. The system according to claim 1, wherein document formats of different medical institutions are converted into a unified format.

3. 2. The system according to claim 1, wherein the medical document converted into the unified format is provided to the terminal.

Images