System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting medical image data; means for inputting patient medical history information; means for uploading the medical image data and the patient medical history information to a database; means for searching the database for similar cases; means for generating a suspected disease name based on the similar cases; means for searching a comprehensive medical knowledge database using the suspected disease name and patient medical history information; means for obtaining a diagnosis and a remedy from the medical knowledge database; and means for providing the diagnosis and the remedy.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] Because evaluating medical images requires a high level of expertise and experience, there are cases where non-specialist doctors must evaluate images, especially in emergency medical settings. In such situations, there is a high risk of overlooking images or misdiagnosis, which could be detrimental to the patient. Therefore, there is a growing need for a system that allows doctors to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatment options. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system including the following means: a means for inputting medical image data, a means for inputting patient medical history information, a means for uploading the medical image data and the patient medical history information to a database, a means for searching the database for similar cases, a means for generating a suspected disease name based on the similar cases, a means for searching a comprehensive medical knowledge database using the suspected disease name and the patient medical history information, a means for obtaining a diagnosis and countermeasures from the medical knowledge database, and a means for providing the diagnosis and countermeasures. This system allows doctors to quickly and accurately evaluate medical images and provide appropriate countermeasures even in areas outside their specialty.

[0006] "Medical image data" refers to image data taken for medical diagnosis, including, for example, CT scans, MRIs, X-rays, and ultrasound images.

[0007] "Patient medical history information" includes detailed medical information such as the patient's past and present medical condition, examination results, treatment history, allergy information, and medical history.

[0008] A "database" is a collection of electronically stored information, a system for systematically organizing various data so that it can be managed and searched.

[0009] A "similar case" is a past case that has similar characteristics to the input medical image data and patient history information.

[0010] The "suspected disease name" is the name of a disease that may be predicted based on the input medical image data and the patient's medical history information.

[0011] "Generative AI" is an artificial intelligence technology that uses generative algorithms to analyze and generate data, and is used to analyze and generate medical images and text data.

[0012] A "medical knowledge database" is a database that stores medical knowledge extracted from medical papers and medical books.

[0013] "Diagnosis" is the process by which a medical professional identifies a medical condition based on a patient's symptoms and test results.

[0014] "Treatment" refers to the treatment or procedure recommended for a particular diagnosis.

[0015] The "means of providing" refers to an interface or system for communicating analysis and diagnosis results to users (doctors). [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 enables even non-specialist doctors to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the function of providing effective diagnoses using generative AI.

[0038] System configuration and operation

[0039] System configuration

[0040] 1. Terminal

[0041] A device for users (doctors) to input medical image data and patient history information.

[0042] Examples include computers, tablets, and smartphones.

[0043] 2. Server

[0044] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[0045] Generative AI is used to search and analyze the database.

[0046] 3. Database

[0047] Medical image database: A database that stores medical image data and corresponding medical history information.

[0048] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[0049] System Operation

[0050] Entering medical images and medical history information

[0051] The user (doctor) inputs medical image data acquired during medical examination and the patient's medical history information into the terminal, thereby obtaining digital data.

[0052] Uploading data

[0053] The terminal packages the medical image data and medical history information and uploads them to a server using secure communication means.

[0054] Data analysis and exploration

[0055] The server analyzes the received medical images and medical history information, extracts features from these data using generative AI, and then searches the medical image database for the most similar cases.

[0056] Generation of suspected disease names

[0057] The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the new patient's medical history information as a query to search a medical knowledge database.

[0058] Providing diagnostics and solutions

[0059] The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and compiles them into a report. The report is detailed and includes suspected disease names, findings, medical knowledge, and countermeasures. It is then sent to the terminal and displayed to the user (doctor).

[0060] Specific examples

[0061] Suspected acute stroke

[0062] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[0063] 2. The terminal uploads the entered data to the server.

[0064] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0065] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database.

[0066] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0067] Diagnosis of pneumonia

[0068] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[0069] 2. The device uploads the data to the server.

[0070] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[0071] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database.

[0072] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0073] This system allows even non-specialist physicians to quickly and accurately evaluate medical images and take appropriate measures, thereby improving the quality and safety of patient care.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The user (doctor) obtains the patient's medical images (e.g., CT scans, X-ray images) and inputs the corresponding patient's medical history information into the terminal. The input data is saved as an image file, and the medical history information is saved in text format.

[0077] Step 2:

[0078] The device packages the acquired medical images and medical history information and uploads them to a server via a secure communication protocol, where the data is encrypted to protect privacy.

[0079] Step 3:

[0080] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion locations, and shapes).

[0081] Step 4:

[0082] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to further improve the similarity.

[0083] Step 5:

[0084] The server generates suspected disease names based on similar cases, which involves using a generative AI to estimate the most appropriate disease name based on the diagnostic results of similar cases.

[0085] Step 6:

[0086] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[0087] Step 7:

[0088] The server uses information retrieved from the medical knowledge database to generate a detailed report containing diagnostic results and treatment options, including suspected illnesses, detected features, and recommended treatments.

[0089] Step 8:

[0090] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[0091] Step 9:

[0092] The terminal displays the received report to the user (doctor), who can use the report to make a quick and accurate diagnosis and treatment plan.

[0093] This specific process enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses, resulting in appropriate treatment for patients and improving work efficiency and the quality of treatment in medical settings.

[0094] Example 1

[0095] 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."

[0096] Even physicians without specialized expertise often have difficulty quickly and accurately evaluating medical images to obtain an appropriate diagnosis and treatment. This increases the risk of misdiagnosis and delayed treatment. The time and effort required to access appropriate information and make the right treatment decisions is also a significant burden.

[0097] 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.

[0098] In this invention, the server includes a means for inputting medical images, a means for inputting patient medical history, a means for uploading the medical images and the patient medical history to a cloud server, a means for performing preprocessing on the cloud server, a means for searching a database for similar cases from the cloud server and extracting features, a means for using a generative AI model to generate a suspected disease name based on the similar cases, a means for searching a medical knowledge database using the generated suspected disease name and the patient medical history, a means for acquiring diagnostic and treatment information from the medical knowledge database, and a means for displaying the acquired diagnostic and treatment information. This enables even non-specialist physicians to quickly and accurately evaluate medical images and quickly obtain an appropriate diagnosis and countermeasure.

[0099] "Medical images" are image data taken for medical purposes using radiation, ultrasound, magnetic resonance, etc.

[0100] "Patient medical history" refers to information that records a patient's past and present medical condition and treatment history.

[0101] A "cloud server" is a server system that provides distributed computing resources over the Internet.

[0102] A "generative AI model" is an artificial intelligence model that analyzes medical data and automatically generates diagnosis results and disease names.

[0103] "Preprocessing" refers to the initial processing operations performed on the data to be analyzed, and includes processes such as data normalization, filtering, and resizing.

[0104] "Feature extraction" is the process of extracting useful statistical or structural features from data.

[0105] "Suspected disease name" refers to the name of a disease that may be a candidate as a result of the analysis.

[0106] A "medical knowledge database" is a database that centrally manages knowledge and information extracted from medical papers and books.

[0107] "Diagnostic and treatment information" refers to information on diagnostic results and countermeasures or treatment methods based on medical knowledge.

[0108] This invention is a system that enables even non-specialist physicians to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the ability to provide effective diagnoses using generative AI models.

[0109] System configuration

[0110] 1. Terminal

[0111] The terminal is a device where users (doctors) input medical image data and patient medical history information. Examples include PCs, tablets, and smartphones. Each terminal runs application software that securely uploads the input data to a cloud server.

[0112] 2. Server

[0113] The server is a central processing unit that receives and analyzes medical images and medical history information uploaded from the device. The analysis is performed using a generative AI model. The server performs image preprocessing and feature extraction using deep learning frameworks such as TensorFlow and PyTorch.

[0114] 3. Database

[0115] The database manages two types of data:

[0116] Medical image database: stores medical image data and corresponding medical history information.

[0117] Medical knowledge database: Stores knowledge extracted from medical papers and medical books.

[0118] System Operation

[0119] 1. The user inputs medical image data acquired during medical treatment and the patient's medical history information into the terminal, which generates digital data.

[0120] 2. The device encrypts this data and uploads it to the server using a secure communication method (e.g., HTTPS).

[0121] 3. The server analyzes the received medical images and medical history information, specifically preprocessing the images (e.g., normalizing and resizing) and extracting features using a generative AI model.

[0122] 4. The server uses the extracted features to search for the most similar cases from the medical image database.

[0123] 5. The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the patient's medical history information as a query to search a medical knowledge database.

[0124] 6. The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and generates a report containing them. This report includes suspected diagnosis, findings, medical knowledge, and countermeasures.

[0125] 7. The terminal displays the report to the user, allowing the user to quickly and accurately diagnose and plan treatment.

[0126] Specific examples

[0127] Suspected acute stroke

[0128] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[0129] Sample prompt: "Analyze this patient's CT scans to assess whether they indicate acute stroke."

[0130] 2. The terminal uploads the entered data to the server.

[0131] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "acute stroke."

[0132] 4. The server retrieves the appropriate response from the medical knowledge database.

[0133] 5. The device displays a report to the user containing the diagnosis and recommended solutions.

[0134] Diagnosis of pneumonia

[0135] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[0136] Sample prompt: "Analyze this patient's chest x-ray to assess the possibility of pneumonia."

[0137] 2. The device uploads the data to the server.

[0138] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "pneumonia."

[0139] 4. The server retrieves appropriate treatments and recommended tests from the medical knowledge database.

[0140] 5. The device displays this information to the user and supports appropriate treatment planning.

[0141] This allows even non-specialist doctors to quickly and accurately evaluate medical images and take appropriate measures. Specific embodiments of the invention can improve the quality and safety of patient care.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] The user inputs medical image data and patient history information.

[0145] Input: Medical image data (e.g., CT scans, X-rays), patient history information

[0146] How it works: The user enters the required information into the input form displayed on the screen of their computer or tablet and clicks the button to upload the image data.

[0147] Output: Digital medical image data and patient history information are stored on the terminal.

[0148] Step 2:

[0149] The terminal uploads medical image data and patient medical history information to a cloud server.

[0150] Input: Digital medical image data and patient history information entered in step 1

[0151] How it works: The device encrypts input data and sends it securely to the cloud server using the HTTPS protocol.

[0152] Output: The encrypted data is uploaded to the cloud server.

[0153] Step 3:

[0154] The server analyzes and preprocesses the uploaded data.

[0155] Input: Encrypted and uploaded medical image data and patient history information

[0156] How it works: The server decrypts the data, preprocesses the images (e.g., normalizes, resizes), and extracts features from the medical images using deep learning models (e.g., TensorFlow, PyTorch).

[0157] Output: Preprocessed image data and extracted features

[0158] Step 4:

[0159] The server uses the generated AI model to search for similar cases.

[0160] Input: Features extracted in step 3

[0161] Operation: The server searches for similar cases in a medical image database using a similarity search algorithm such as K-Nearest Neighbors.

[0162] Output: A list of the most similar cases and their corresponding features

[0163] Step 5:

[0164] The server generates a suspected disease name based on similar cases.

[0165] Input: List of similar cases obtained in step 4 and feature values

[0166] How it works: The server uses a generative AI model to generate suspected disease names from similar cases.

[0167] Output: Generated suspected disease name

[0168] Step 6:

[0169] The server generates a suspected disease name and uses the patient's medical history information to search a medical knowledge database.

[0170] Input: Generated suspected disease name, patient medical history information

[0171] Operation: The server uses NLP techniques to search a medical knowledge database and extract relevant diagnostic information and treatment options.

[0172] Output: Diagnostic information and remedial actions

[0173] Step 7:

[0174] The device displays diagnostic and remediation information.

[0175] Input: Diagnostic information and remedial action taken in step 6

[0176] Operation: The device generates a report in PDF or HTML format containing diagnostic results and countermeasures, and displays it through the user interface.

[0177] Output: Diagnostic report displayed to the user

[0178] (Application example 1)

[0179] 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."

[0180] Maintaining normal operation of industrial equipment requires early detection of abnormalities and appropriate maintenance. However, it is difficult for engineers without specialized knowledge to quickly and accurately detect abnormalities and take appropriate countermeasures. Conventional methods take time to diagnose abnormalities and provide countermeasures, which can lead to reduced production efficiency and increased maintenance costs. The present invention aims to solve these problems and provide a system that supports optimal operation and maintenance of industrial equipment.

[0181] 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.

[0182] In this invention, the server includes a means for inputting the operation data of the industrial equipment, a means for inputting the maintenance history of the industrial equipment, and a means for uploading the operation data and the maintenance history to the database, which enables even an engineer without specialized knowledge to quickly and accurately detect an abnormality and provide an appropriate countermeasure.

[0183] "Industrial equipment" means machinery and equipment used in the manufacturing process.

[0184] "Operation data" refers to data that indicates information about the operating status and operating state of industrial equipment.

[0185] "Maintenance history" refers to a record of past maintenance work and repairs performed on industrial equipment.

[0186] A "database" is a system for storing large amounts of data in an organized manner and facilitating search and access.

[0187] "Similar cases" are cases similar to the operating conditions and maintenance history of industrial equipment stored in the past database.

[0188] A "suspected abnormality" is a condition that is predicted to indicate a potential problem with industrial equipment based on operational data and maintenance history.

[0189] The "maintenance knowledge database" is a database that stores information collected from technical documents and papers related to the maintenance of industrial equipment.

[0190] "Diagnosis" is the process of assessing the condition of industrial equipment and identifying potential problems.

[0191] "Countermeasures" are specific measures recommended to solve problems in industrial equipment based on the diagnosis results.

[0192] "Generative AI" is a type of artificial intelligence technology and a machine learning model for data analysis and predictive modeling.

[0193] To implement the invention, it is necessary to build a system that utilizes the operational data and maintenance history of industrial equipment. This system is realized using the following hardware and software.

[0194] Hardware used

[0195] 1. Server: A central processing unit that analyzes and stores data.

[0196] 2. Terminal: A device such as a computer, tablet, or smartphone that allows technicians to input and view data.

[0197] Software used

[0198] 1. Data format: JSON format

[0199] 2. AI libraries: TensorFlow or PyTorch (used to build generative AI models)

[0200] 3. Communication method: HTTPS protocol

[0201] System configuration and operation

[0202] Data Entry and Upload

[0203] Technicians input the operational data and maintenance history of industrial equipment into a terminal, which then captures the data in digital format. The terminal then packages the data and uploads it to a server using secure communications.

[0204] Feature Extraction and Search

[0205] The server analyzes the received operational data and maintenance history and uses generative AI to extract features from these data. It then searches the database for the most similar cases, allowing it to compare past data with new data.

[0206] Anomaly generation and database search

[0207] The server generates a suspected anomaly based on the most similar cases, and uses this suspected anomaly and the maintenance history as a query to search a maintenance knowledge database, from which relevant diagnostic information and countermeasures are extracted.

[0208] Report Generation and Viewing

[0209] The server generates a report containing the diagnosis and countermeasures. This report, which includes suspected abnormalities, findings, maintenance knowledge, and countermeasures, is sent to the terminal. Technicians can use this report to make quick and accurate maintenance decisions.

[0210] Specific examples

[0211] When a technician inputs data to detect abnormalities in the robot, the data is sent to a server, where the generative AI detects the abnormality, compares it with the most similar past data, and provides appropriate maintenance methods.

[0212] Prompt Sentence Examples

[0213] "The robot's operating data and maintenance history have been entered as follows:

[0214] Operational data: {sensor_data}

[0215] Maintenance history: {maintenance_history}

[0216] Based on this, generate a diagnosis of the anomaly and provide appropriate remedial action."

[0217] As described above, this system enables even engineers without specialized knowledge to quickly and accurately detect abnormalities and provide appropriate countermeasures, thereby improving factory production efficiency and reducing maintenance costs.

[0218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0219] Step 1:

[0220] The user inputs the operation data and maintenance history of industrial equipment into the terminal. This input includes operating status data obtained from sensors and past maintenance records. This allows the terminal to collect digital data. To process the input data, the operation data is converted into JSON format, and the maintenance history is also converted into the same format.

[0221] Step 2:

[0222] The device packages the operation data and maintenance history and uploads them to the server using a secure communication method (HTTPS protocol). The data packaging involves combining various data fields and adding metadata. The packaged data is sent to the server in JSON format.

[0223] Step 3:

[0224] The server analyzes the received operational data and maintenance history. This involves using a generative AI model to extract features from the data. Specifically, the model, trained using TensorFlow or PyTorch, identifies important features from the input data (for example, vibration patterns or temperature fluctuations). The output is stored as a feature vector.

[0225] Step 4:

[0226] The server uses the extracted feature vector to search for similar cases in the database. Here, it matches past operation data and maintenance history with similar features to find the most similar entry. The search algorithm used is, for example, cosine similarity, and calculates the similarity to output a list of similar cases.

[0227] Step 5:

[0228] The server generates suspected anomalies based on the most similar cases. A generative AI model is used to generate predictions about abnormal conditions based on new feature vectors and past cases. The output is a number of suspected anomalies and their probabilities.

[0229] Step 6:

[0230] The server uses the suspected anomaly and maintenance history as a query to search a maintenance knowledge database. This search extracts relevant diagnostic information and countermeasures. The knowledge database contains technical documentation and past maintenance cases, and provides a list of countermeasures.

[0231] Step 7:

[0232] The server generates a diagnostic and actionable report, which includes suspected anomalies, findings, and recommended actions. The report is generated in JSON format and sent to the device.

[0233] Step 8:

[0234] The terminal displays the received report to the technician, allowing the technician to quickly and accurately detect anomalies and implement appropriate countermeasures. UI components are generally used for display, making the report contents visually easy to understand.

[0235] 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.

[0236] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[0237] System configuration and operation

[0238] System configuration

[0239] 1. Terminal

[0240] A device for users (doctors) to input medical image data and patient history information.

[0241] Examples include computers, tablets, and smartphones.

[0242] It has a built-in emotion engine and is equipped with a camera and microphone to analyze the user's facial expressions, voice, and gestures.

[0243] 2. Server

[0244] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[0245] Generative AI is used to search and analyze the database.

[0246] 3. Database

[0247] Medical image database: A database that stores medical image data and corresponding medical history information.

[0248] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[0249] 4. Emotion Engine

[0250] Software that analyzes a user's facial expressions, voice, and gestures to recognize emotions.

[0251] It has the ability to adjust the system's response method based on the analysis results.

[0252] System Operation

[0253] Entering medical images and medical history information

[0254] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[0255] Uploading data

[0256] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[0257] Data analysis and exploration

[0258] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion location, shape, etc.). It then identifies similar past cases from the medical image database and compares them with the uploaded medical history information.

[0259] Generation of suspected disease names

[0260] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data from an emotion engine.

[0261] Providing diagnostics and solutions

[0262] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[0263] Providing reports

[0264] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0265] Specific examples

[0266] Suspected acute stroke

[0267] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[0268] 2. The terminal uploads the entered data to the server.

[0269] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0270] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[0271] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0272] Diagnosis of pneumonia

[0273] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[0274] 2. The device uploads the data to the server.

[0275] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[0276] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[0277] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0278] The system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Its emotion engine recognizes the user's emotional state and adjusts its response accordingly, reducing the burden on doctors and enabling more effective support.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] The user (doctor) acquires a patient's medical images (e.g., CT scans, X-ray images) and inputs the patient's corresponding medical history information into the terminal. The terminal saves the medical image data as an image file and the medical history information in text format.

[0282] Step 2:

[0283] The device packages the acquired medical image data and medical history information and uploads them to a server via a secure communication protocol. The data is encrypted during the upload process. An emotion engine also analyzes the user's facial expressions and voice to generate emotion data.

[0284] Step 3:

[0285] The server receives the uploaded medical image data and medical history information and begins analysis using generative AI. First, it extracts features from the medical image (abnormal areas, lesion location, shape, etc.).

[0286] Step 4:

[0287] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to obtain a more accurate similarity score.

[0288] Step 5:

[0289] The server generates suspected disease names based on similar cases. This process includes disease names estimated from past cases using generative AI, and also takes into account the user's emotional data using an emotion engine.

[0290] Step 6:

[0291] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[0292] Step 7:

[0293] The server generates a detailed report containing the diagnosis and treatment plan based on the information retrieved from the medical knowledge database. The report includes the suspected disease, detected features, and recommended treatment. The presentation and content of the report are adjusted according to the user's emotional state.

[0294] Step 8:

[0295] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[0296] Step 9:

[0297] The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0298] This specific processing enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses. The emotion engine provides flexible support according to the user's emotional state, improving the user experience.

[0299] Example 2

[0300] 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."

[0301] In modern medicine, even physicians without specialized expertise are required to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. However, achieving this is not easy due to the breadth of medical knowledge and the complexity of diagnoses. Another issue is that the physician's emotional state can affect the efficiency and accuracy of diagnostic work. To solve these problems, a diagnostic support system is needed that can efficiently and accurately analyze medical image data and patient medical history information, and that also takes the user's emotional state into account.

[0302] 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.

[0303] In this invention, the server includes a means for inputting medical image data, a means for inputting patient medical history information, a means for uploading the medical image data and the patient medical history information to a database, a means for searching the database for similar cases, a means for generating a suspected disease name based on the similar cases, a means for searching a comprehensive medical knowledge database using the suspected disease name and the patient's medical history information, a means for obtaining a diagnosis and countermeasures from the medical knowledge database, a means for providing the diagnosis and countermeasures, a means for recognizing a user's emotional state, and a means for adjusting a response method based on the user's emotional state. This enables doctors to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. Furthermore, by recognizing a user's emotional state and adjusting a response method accordingly, the efficiency and accuracy of diagnostic work can be improved.

[0304] "Medical image data" is data that visually records the state of the inside of the human body, obtained using medical equipment such as radiation or ultrasound.

[0305] "Patient medical history information" is a record of a patient's past diagnoses, treatments, and surgeries, as well as detailed information about their current symptoms and medical history.

[0306] A "database" is a collection of information that is systematically organized to efficiently store, retrieve, and manipulate specific information.

[0307] A "similar case" is a case from previously recorded medical information that is similar to the symptoms and medical image data of a current patient.

[0308] The "suspected disease name" is a disease name that is highly likely to be estimated based on medical image data and the patient's medical history information.

[0309] A "medical knowledge database" is a collection of diagnostic and treatment knowledge extracted from medical treatises, medical books, and other reliable medical sources.

[0310] "Diagnosis and countermeasures" refers to the diagnosis results generated based on medical image data and medical history information, as well as the recommended treatment and testing methods.

[0311] The "user's emotional state" is an emotional state based on the user's facial expressions, voice, gestures, etc., recognized through input devices such as a camera or microphone.

[0312] "Adjusting the response method" refers to a method for providing more appropriate support by changing the method and content of information presentation depending on the user's emotional state.

[0313] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[0314] System configuration

[0315] 1. Terminal

[0316] A device that allows users (doctors) to input medical image data and patient history information. Examples include PCs, tablets, and smartphones. The device is equipped with a camera and microphone, and an emotion engine analyzes the user's facial expressions, voice, and gestures. Specific examples include using tools such as Microsoft Azure Face API and Google Cloud Speech-to-Text.

[0317] 2. Server

[0318] A central processing unit that receives and analyzes medical images and medical history information uploaded from devices. It searches and analyzes the database using generative AI models (e.g., OpenAI's GPT series). Specifically, it uses medical image analysis software (e.g., Google DeepMind's AlphaFold).

[0319] 3. Database

[0320] Medical image database: A database that stores medical image data and corresponding medical history information.

[0321] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[0322] 4. Emotion Engine

[0323] Software that recognizes emotions by analyzing the user's facial expressions, voice, and gestures, and has the ability to adjust the system's response method based on the analysis results.

[0324] System Operation

[0325] This system analyzes medical image data and patient medical history information using the following procedure to provide an appropriate diagnosis and treatment.

[0326] 1. Entering medical images and medical history information

[0327] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[0328] 2. Uploading data

[0329] The device packages the medical image data and medical history information and uploads them to the server using a secure communication method (e.g., HTTPS), including the emotion data obtained from the emotion engine.

[0330] 3. Data analysis and retrieval

[0331] The server receives the uploaded medical images and medical history information and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, medical image analysis software is used to extract features from the images (e.g., abnormal areas, lesion location, shape, etc.). Similar past cases are then identified from a medical image database and compared with the input medical history information.

[0332] 4. Generation of suspected disease names

[0333] The server generates suspected disease names based on similar cases, including disease names predicted using a generative AI model, and also takes into account the user's emotional data from an emotion engine.

[0334] 5. Providing diagnosis and solutions

[0335] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[0336] 6. Providing reports

[0337] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0338] Specific examples

[0339] Suspected acute stroke

[0340] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[0341] 2. The terminal uploads the entered data to the server.

[0342] 3. The server uses the generative AI model to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0343] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[0344] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0345] Prompt Sentence Examples

[0346] "Enter the CT scan and medical history information of a patient suspected of having an acute stroke. The system will recommend emergency treatment."

[0347] Diagnosis of pneumonia

[0348] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[0349] 2. The device uploads the data to the server.

[0350] 3. The server uses the generative AI model to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[0351] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[0352] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0353] Prompt Sentence Examples

[0354] "Enter a chest x-ray and medical history of a patient with a fever and cough. We'll provide the information in an easy-to-understand format, taking into account the user's fatigue level."

[0355] This system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Furthermore, the emotion engine recognizes the user's emotional state and adjusts the response accordingly, reducing the burden on doctors and providing more effective support.

[0356] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0357] Step 1:

[0358] The user inputs medical image data and the patient's medical history information into the terminal. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions, voice, and gestures in real time. Specifically, the terminal receives CT images and X-ray images as medical image data and text data as medical history information. The emotion engine also uses AI-based facial recognition software and voice analysis tools. The input data are medical image files and text medical history information. The output data are medical image data, medical history information, and the user's emotional state data.

[0359] Step 2:

[0360] The terminal packages medical image data, medical history information, and emotion data and uploads them to the server using a secure communication method (e.g., HTTPS, SSL / TLS). The terminal converts this data into JSON format and sends it via a secure HTTP POST request. The input data is the packaged medical image data, medical history information, and emotion data. The output data is the securely uploaded packaged data.

[0361] Step 3:

[0362] The server receives the uploaded data and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, the server uses medical image analysis software to extract features from the image (e.g., abnormal areas, location and shape of lesions). A full-text search engine (e.g., Elasticsearch) is used to search for similar cases recorded in the past from a medical image database. The input data are medical image data and medical history information. The output data are feature data and a candidate list of similar cases.

[0363] Step 4:

[0364] The server generates a suspected disease name based on similar cases. The generative AI model estimates multiple diagnostic candidates and selects the most reliable one. The server also takes into account the user's emotional state obtained by the emotion engine. For example, if the user is in a hurry, the server will prioritize the most important information. The input data are feature data, similar case data, and emotion data. The output data is the suspected disease name.

[0365] Step 5:

[0366] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report. The report includes the suspected disease name, detected features, and recommended treatment. The format and presentation of the report are also adjusted depending on the user's emotional state. For example, if the user is tired, information is presented in an easy-to-understand bullet point format. The input data are the suspected disease name and the medical knowledge database. The output data is the generated report.

[0367] Step 6:

[0368] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor) and provides additional support as needed. The emotion engine analyzes the user's emotions even while the report is being displayed, and provides additional explanations and suggested measures in real time. As a specific example, a user who is feeling anxious is provided with more detailed explanations and visualized data. The input data is the generated report. The output data is the report displayed to the user and the content of additional support.

[0369] (Application example 2)

[0370] 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."

[0371] In the medical field, non-specialist physicians are required to make quick and accurate diagnoses, but the physician's emotions and stress can affect the diagnostic results. In particular, in telemedicine, more effective medical services are required by appropriately recognizing the emotions of the physician and patient and adjusting the diagnosis and treatment methods. The present invention aims to solve this problem and improve the accuracy and efficiency of diagnoses by providing an interface and information that reflects the user's emotional state.

[0372] 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.

[0373] In this invention, the server includes a means for inputting medical image data and patient medical history information, a means for uploading the data to a database, and a means for searching the database for similar cases, which makes it possible to recognize the user's emotions and adjust the interface and information presentation method based on the results.

[0374] "Medical image data" refers to image data taken for the purpose of diagnosing or treating a patient, and includes X-ray images, CT images, MRI images, etc.

[0375] "Patient medical history information" refers to detailed information about a patient's past health condition and illnesses, including medical records, medical history, allergy history, and so on.

[0376] A "database" is a collection of information that stores medical image data and patient medical history information and is used to search for similar cases.

[0377] "Similar cases" refers to past cases that have similar medical images and medical history information to those being analyzed, and are useful in providing diagnoses and countermeasures.

[0378] A "suspected disease name" is a possible diagnosis result generated based on medical image data and a patient's medical history information, and includes specific symptoms and disease names.

[0379] A "medical knowledge database" is a source of medical knowledge necessary for diagnosis and treatment, including information extracted from medical papers and medical books.

[0380] "Generative AI" is a system that uses artificial intelligence technology to analyze medical image data and medical history information, and is used to provide new diagnoses and countermeasures.

[0381] An "emotion engine" is software that analyzes a user's facial expressions, voice, and gestures to recognize their emotional state and adjusts the interface and the way information is presented.

[0382] An "interface" is a platform through which users interact with a system, adaptively adjusting based on emotion recognition.

[0383] System configuration

[0384] The present invention combines a system that analyzes medical image data and patient history information to provide diagnosis and treatment with an emotion engine that recognizes the user's emotions. The main components of the system include a terminal, a server, and a database. The emotion engine is used to analyze the user's emotional state in real time.

[0385] Terminal

[0386] Configuration: A device for doctors to input medical image data and patient medical history information. Specifically, it includes devices equipped with a camera and microphone, such as smartphones, smart glasses, and head-mounted displays, and has an emotion engine built in.

[0387] server

[0388] Configuration: A central processing unit that receives medical images and medical history information uploaded from the terminal and uses generative AI to search and analyze the database.

[0389] Database

[0390] Structure: The system consists of a medical image database and a medical knowledge database. The former stores medical image data and corresponding medical history information, while the latter stores knowledge extracted from medical papers and medical books.

[0391] Emotion Engine

[0392] Configuration: Software that analyzes the user's facial expressions, voice, and gestures to recognize emotions. It has the ability to adjust the system's response method based on the analysis results.

[0393] System Operation

[0394] Entering medical images and medical history information

[0395] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. The emotion engine analyzes the user's facial expressions and voice during this input process and recognizes their emotional state in real time.

[0396] Uploading data

[0397] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[0398] Data analysis and exploration

[0399] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (such as abnormal areas and the location and shape of lesions). It then identifies similar cases from the medical image database and compares them with the uploaded medical history information.

[0400] Generation of suspected disease names

[0401] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data generated by the emotion engine.

[0402] Providing diagnostics and solutions

[0403] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected diagnoses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[0404] Providing reports

[0405] The server sends the generated report to the terminal, which then displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0406] Specific examples

[0407] Suspected acute stroke

[0408] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[0409] 2. The device uploads the entered data to the server.

[0410] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0411] 4. Based on the results, the server generates a suspected illness name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that immediate action is required.

[0412] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0413] Diagnosis of pneumonia

[0414] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[0415] 2. The device uploads the data to the server.

[0416] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[0417] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[0418] 5. The device displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0419] Prompt Sentence Examples

[0420] "Upload a medical image (e.g., CT scan)

[0421] Please provide your diagnosis and suggest a course of action."

[0422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0423] Step 1:

[0424] The user (doctor) inputs medical image data and the patient's medical history information acquired during the consultation into the terminal. This input includes, for example, CT images and X-ray images, as well as information about the patient's medical history and current symptoms. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions and voice in real time. The emotion engine collects the input data and the user's facial and vocal characteristics to recognize the user's emotional state.

[0425] Step 2:

[0426] The terminal packages medical image data and patient history information and uploads them to a server using secure communication methods. At this time, the emotional data analyzed by the emotion engine is also included in the package. The terminal inputs medical image data, medical history information, and the user's emotional data, and outputs a package containing this information.

[0427] Step 3:

[0428] The server receives medical image data and patient medical history information uploaded from the device. This data is preprocessed and input into the generative AI model. The server analyzes the data and extracts features (such as abnormal areas and the location and shape of lesions) from the medical images. The input data are medical images and medical history information, and the output is the feature extraction results.

[0429] Step 4:

[0430] The server searches for similar cases in a medical image database and compares them with the uploaded medical history information. The generative AI model identifies similar cases from past cases in the database based on the features. The input data are the features and medical history information, and the output is a list of similar cases.

[0431] Step 5:

[0432] The server generates a suspected disease name based on similar cases. It uses a generative AI model to estimate the most appropriate disease name and outputs this name. The input data is a list of similar cases, and the output is a suspected disease name. It also takes into account the user's emotional data from an emotion engine.

[0433] Step 6:

[0434] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database. Based on the suspected disease name and the patient's medical history, it uses a generative AI to search for appropriate diagnostic information and countermeasures. The input data is the suspected disease name and medical history information, and the output is diagnostic information and countermeasures.

[0435] Step 7:

[0436] The server generates a detailed report, including suspected diagnosis, detected features, and recommended treatment. The emotion engine adjusts the presentation and content of the report according to the user's emotional state. The input data are diagnostic information and countermeasures, and the output is the generated report.

[0437] Step 8:

[0438] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests measures as needed. The input data is the generated report, and the output is the report and additional explanations presented to the user.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] [Second embodiment]

[0443] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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).

[0449] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] In the smart glasses 214, the 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.

[0454] 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."

[0455] This invention is a system that enables even non-specialist doctors to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the function of providing effective diagnoses using generative AI.

[0456] System configuration and operation

[0457] System configuration

[0458] 1. Terminal

[0459] A device for users (doctors) to input medical image data and patient history information.

[0460] Examples include computers, tablets, and smartphones.

[0461] 2. Server

[0462] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[0463] Generative AI is used to search and analyze the database.

[0464] 3. Database

[0465] Medical image database: A database that stores medical image data and corresponding medical history information.

[0466] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[0467] System Operation

[0468] Entering medical images and medical history information

[0469] The user (doctor) inputs medical image data acquired during medical examination and the patient's medical history information into the terminal, thereby obtaining digital data.

[0470] Uploading data

[0471] The terminal packages the medical image data and medical history information and uploads them to a server using secure communication means.

[0472] Data analysis and exploration

[0473] The server analyzes the received medical images and medical history information, extracts features from these data using generative AI, and then searches the medical image database for the most similar cases.

[0474] Generation of suspected disease names

[0475] The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the new patient's medical history information as a query to search a medical knowledge database.

[0476] Providing diagnostics and solutions

[0477] The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and compiles them into a report. The report is detailed and includes suspected disease names, findings, medical knowledge, and countermeasures. It is then sent to the terminal and displayed to the user (doctor).

[0478] Specific examples

[0479] Suspected acute stroke

[0480] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[0481] 2. The terminal uploads the entered data to the server.

[0482] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0483] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database.

[0484] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0485] Diagnosis of pneumonia

[0486] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[0487] 2. The device uploads the data to the server.

[0488] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[0489] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database.

[0490] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0491] This system allows even non-specialist physicians to quickly and accurately evaluate medical images and take appropriate measures, thereby improving the quality and safety of patient care.

[0492] The processing flow will be explained below.

[0493] Step 1:

[0494] The user (doctor) obtains the patient's medical images (e.g., CT scans, X-ray images) and inputs the corresponding patient's medical history information into the terminal. The input data is saved as an image file, and the medical history information is saved in text format.

[0495] Step 2:

[0496] The device packages the acquired medical images and medical history information and uploads them to a server via a secure communication protocol, where the data is encrypted to protect privacy.

[0497] Step 3:

[0498] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion locations, and shapes).

[0499] Step 4:

[0500] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to further improve the similarity.

[0501] Step 5:

[0502] The server generates suspected disease names based on similar cases, which involves using a generative AI to estimate the most appropriate disease name based on the diagnostic results of similar cases.

[0503] Step 6:

[0504] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[0505] Step 7:

[0506] The server uses information retrieved from the medical knowledge database to generate a detailed report containing diagnostic results and treatment options, including suspected illnesses, detected features, and recommended treatments.

[0507] Step 8:

[0508] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[0509] Step 9:

[0510] The terminal displays the received report to the user (doctor), who can use the report to make a quick and accurate diagnosis and treatment plan.

[0511] This specific process enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses, resulting in appropriate treatment for patients and improving work efficiency and the quality of treatment in medical settings.

[0512] Example 1

[0513] 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."

[0514] Even physicians without specialized expertise often have difficulty quickly and accurately evaluating medical images to obtain an appropriate diagnosis and treatment. This increases the risk of misdiagnosis and delayed treatment. The time and effort required to access appropriate information and make the right treatment decisions is also a significant burden.

[0515] 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.

[0516] In this invention, the server includes a means for inputting medical images, a means for inputting patient medical history, a means for uploading the medical images and the patient medical history to a cloud server, a means for performing preprocessing on the cloud server, a means for searching a database for similar cases from the cloud server and extracting features, a means for using a generative AI model to generate a suspected disease name based on the similar cases, a means for searching a medical knowledge database using the generated suspected disease name and the patient medical history, a means for acquiring diagnostic and treatment information from the medical knowledge database, and a means for displaying the acquired diagnostic and treatment information. This enables even non-specialist physicians to quickly and accurately evaluate medical images and quickly obtain an appropriate diagnosis and countermeasure.

[0517] "Medical images" are image data taken for medical purposes using radiation, ultrasound, magnetic resonance, etc.

[0518] "Patient medical history" refers to information that records a patient's past and present medical condition and treatment history.

[0519] A "cloud server" is a server system that provides distributed computing resources over the Internet.

[0520] A "generative AI model" is an artificial intelligence model that analyzes medical data and automatically generates diagnosis results and disease names.

[0521] "Preprocessing" refers to the initial processing operations performed on the data to be analyzed, and includes processes such as data normalization, filtering, and resizing.

[0522] "Feature extraction" is the process of extracting useful statistical or structural features from data.

[0523] "Suspected disease name" refers to the name of a disease that may be a candidate as a result of the analysis.

[0524] A "medical knowledge database" is a database that centrally manages knowledge and information extracted from medical papers and books.

[0525] "Diagnostic and treatment information" refers to information on diagnostic results and countermeasures or treatment methods based on medical knowledge.

[0526] This invention is a system that enables even non-specialist physicians to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the ability to provide effective diagnoses using generative AI models.

[0527] System configuration

[0528] 1. Terminal

[0529] The terminal is a device where users (doctors) input medical image data and patient medical history information. Examples include PCs, tablets, and smartphones. Each terminal runs application software that securely uploads the input data to a cloud server.

[0530] 2. Server

[0531] The server is a central processing unit that receives and analyzes medical images and medical history information uploaded from the device. The analysis is performed using a generative AI model. The server performs image preprocessing and feature extraction using deep learning frameworks such as TensorFlow and PyTorch.

[0532] 3. Database

[0533] The database manages two types of data:

[0534] Medical image database: stores medical image data and corresponding medical history information.

[0535] Medical knowledge database: Stores knowledge extracted from medical papers and medical books.

[0536] System Operation

[0537] 1. The user inputs medical image data acquired during medical treatment and the patient's medical history information into the terminal, which generates digital data.

[0538] 2. The device encrypts this data and uploads it to the server using a secure communication method (e.g., HTTPS).

[0539] 3. The server analyzes the received medical images and medical history information, specifically preprocessing the images (e.g., normalizing and resizing) and extracting features using a generative AI model.

[0540] 4. The server uses the extracted features to search for the most similar cases from the medical image database.

[0541] 5. The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the patient's medical history information as a query to search a medical knowledge database.

[0542] 6. The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and generates a report containing them. This report includes suspected diagnosis, findings, medical knowledge, and countermeasures.

[0543] 7. The terminal displays the report to the user, allowing the user to quickly and accurately diagnose and plan treatment.

[0544] Specific examples

[0545] Suspected acute stroke

[0546] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[0547] Sample prompt: "Analyze this patient's CT scans to assess whether they indicate acute stroke."

[0548] 2. The terminal uploads the entered data to the server.

[0549] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "acute stroke."

[0550] 4. The server retrieves the appropriate response from the medical knowledge database.

[0551] 5. The device displays a report to the user containing the diagnosis and recommended solutions.

[0552] Diagnosis of pneumonia

[0553] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[0554] Sample prompt: "Analyze this patient's chest x-ray to assess the possibility of pneumonia."

[0555] 2. The device uploads the data to the server.

[0556] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "pneumonia."

[0557] 4. The server retrieves appropriate treatments and recommended tests from the medical knowledge database.

[0558] 5. The device displays this information to the user and supports appropriate treatment planning.

[0559] This allows even non-specialist doctors to quickly and accurately evaluate medical images and take appropriate measures. Specific embodiments of the invention can improve the quality and safety of patient care.

[0560] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0561] Step 1:

[0562] The user inputs medical image data and patient history information.

[0563] Input: Medical image data (e.g., CT scans, X-rays), patient history information

[0564] How it works: The user enters the required information into the input form displayed on the screen of their computer or tablet and clicks the button to upload the image data.

[0565] Output: Digital medical image data and patient history information are stored on the terminal.

[0566] Step 2:

[0567] The terminal uploads medical image data and patient medical history information to a cloud server.

[0568] Input: Digital medical image data and patient history information entered in step 1

[0569] How it works: The device encrypts input data and sends it securely to the cloud server using the HTTPS protocol.

[0570] Output: The encrypted data is uploaded to the cloud server.

[0571] Step 3:

[0572] The server analyzes and preprocesses the uploaded data.

[0573] Input: Encrypted and uploaded medical image data and patient history information

[0574] How it works: The server decrypts the data, preprocesses the images (e.g., normalizes, resizes), and extracts features from the medical images using deep learning models (e.g., TensorFlow, PyTorch).

[0575] Output: Preprocessed image data and extracted features

[0576] Step 4:

[0577] The server uses the generated AI model to search for similar cases.

[0578] Input: Features extracted in step 3

[0579] Operation: The server searches for similar cases in a medical image database using a similarity search algorithm such as K-Nearest Neighbors.

[0580] Output: A list of the most similar cases and their corresponding features

[0581] Step 5:

[0582] The server generates a suspected disease name based on similar cases.

[0583] Input: List of similar cases obtained in step 4 and feature values

[0584] How it works: The server uses a generative AI model to generate suspected disease names from similar cases.

[0585] Output: Generated suspected disease name

[0586] Step 6:

[0587] The server generates a suspected disease name and uses the patient's medical history information to search a medical knowledge database.

[0588] Input: Generated suspected disease name, patient medical history information

[0589] Operation: The server uses NLP techniques to search a medical knowledge database and extract relevant diagnostic information and treatment options.

[0590] Output: Diagnostic information and remedial actions

[0591] Step 7:

[0592] The device displays diagnostic and remediation information.

[0593] Input: Diagnostic information and remedial action taken in step 6

[0594] Operation: The device generates a report in PDF or HTML format containing diagnostic results and countermeasures, and displays it through the user interface.

[0595] Output: Diagnostic report displayed to the user

[0596] (Application example 1)

[0597] 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."

[0598] Maintaining normal operation of industrial equipment requires early detection of abnormalities and appropriate maintenance. However, it is difficult for engineers without specialized knowledge to quickly and accurately detect abnormalities and take appropriate countermeasures. Conventional methods take time to diagnose abnormalities and provide countermeasures, which can lead to reduced production efficiency and increased maintenance costs. The present invention aims to solve these problems and provide a system that supports optimal operation and maintenance of industrial equipment.

[0599] 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.

[0600] In this invention, the server includes a means for inputting the operation data of the industrial equipment, a means for inputting the maintenance history of the industrial equipment, and a means for uploading the operation data and the maintenance history to the database, which enables even an engineer without specialized knowledge to quickly and accurately detect an abnormality and provide an appropriate countermeasure.

[0601] "Industrial equipment" means machinery and equipment used in the manufacturing process.

[0602] "Operation data" refers to data that indicates information about the operating status and operating state of industrial equipment.

[0603] "Maintenance history" refers to a record of past maintenance work and repairs performed on industrial equipment.

[0604] A "database" is a system for storing large amounts of data in an organized manner and facilitating search and access.

[0605] "Similar cases" are cases similar to the operating conditions and maintenance history of industrial equipment stored in the past database.

[0606] A "suspected abnormality" is a condition that is predicted to indicate a potential problem with industrial equipment based on operational data and maintenance history.

[0607] The "maintenance knowledge database" is a database that stores information collected from technical documents and papers related to the maintenance of industrial equipment.

[0608] "Diagnosis" is the process of assessing the condition of industrial equipment and identifying potential problems.

[0609] "Countermeasures" are specific measures recommended to solve problems in industrial equipment based on the diagnosis results.

[0610] "Generative AI" is a type of artificial intelligence technology and a machine learning model for data analysis and predictive modeling.

[0611] To implement the invention, it is necessary to build a system that utilizes the operational data and maintenance history of industrial equipment. This system is realized using the following hardware and software.

[0612] Hardware used

[0613] 1. Server: A central processing unit that analyzes and stores data.

[0614] 2. Terminal: A device such as a computer, tablet, or smartphone that allows technicians to input and view data.

[0615] Software used

[0616] 1. Data format: JSON format

[0617] 2. AI libraries: TensorFlow or PyTorch (used to build generative AI models)

[0618] 3. Communication method: HTTPS protocol

[0619] System configuration and operation

[0620] Data Entry and Upload

[0621] Technicians input the operational data and maintenance history of industrial equipment into a terminal, which then captures the data in digital format. The terminal then packages the data and uploads it to a server using secure communications.

[0622] Feature Extraction and Search

[0623] The server analyzes the received operational data and maintenance history and uses generative AI to extract features from these data. It then searches the database for the most similar cases, allowing it to compare past data with new data.

[0624] Anomaly generation and database search

[0625] The server generates a suspected anomaly based on the most similar cases, and uses this suspected anomaly and the maintenance history as a query to search a maintenance knowledge database, from which relevant diagnostic information and countermeasures are extracted.

[0626] Report Generation and Viewing

[0627] The server generates a report containing the diagnosis and countermeasures. This report, which includes suspected abnormalities, findings, maintenance knowledge, and countermeasures, is sent to the terminal. Technicians can use this report to make quick and accurate maintenance decisions.

[0628] Specific examples

[0629] When a technician inputs data to detect abnormalities in the robot, the data is sent to a server, where the generative AI detects the abnormality, compares it with the most similar past data, and provides appropriate maintenance methods.

[0630] Prompt Sentence Examples

[0631] "The robot's operating data and maintenance history have been entered as follows:

[0632] Operational data: {sensor_data}

[0633] Maintenance history: {maintenance_history}

[0634] Based on this, generate a diagnosis of the anomaly and provide appropriate remedial action."

[0635] As described above, this system enables even engineers without specialized knowledge to quickly and accurately detect abnormalities and provide appropriate countermeasures, thereby improving factory production efficiency and reducing maintenance costs.

[0636] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0637] Step 1:

[0638] The user inputs the operation data and maintenance history of industrial equipment into the terminal. This input includes operating status data obtained from sensors and past maintenance records. This allows the terminal to collect digital data. To process the input data, the operation data is converted into JSON format, and the maintenance history is also converted into the same format.

[0639] Step 2:

[0640] The device packages the operation data and maintenance history and uploads them to the server using a secure communication method (HTTPS protocol). The data packaging involves combining various data fields and adding metadata. The packaged data is sent to the server in JSON format.

[0641] Step 3:

[0642] The server analyzes the received operational data and maintenance history. This involves using a generative AI model to extract features from the data. Specifically, the model, trained using TensorFlow or PyTorch, identifies important features from the input data (for example, vibration patterns or temperature fluctuations). The output is stored as a feature vector.

[0643] Step 4:

[0644] The server uses the extracted feature vector to search for similar cases in the database. Here, it matches past operation data and maintenance history with similar features to find the most similar entry. The search algorithm used is, for example, cosine similarity, and calculates the similarity to output a list of similar cases.

[0645] Step 5:

[0646] The server generates suspected anomalies based on the most similar cases. A generative AI model is used to generate predictions about abnormal conditions based on new feature vectors and past cases. The output is a number of suspected anomalies and their probabilities.

[0647] Step 6:

[0648] The server uses the suspected anomaly and maintenance history as a query to search a maintenance knowledge database. This search extracts relevant diagnostic information and countermeasures. The knowledge database contains technical documentation and past maintenance cases, and provides a list of countermeasures.

[0649] Step 7:

[0650] The server generates a diagnostic and actionable report, which includes suspected anomalies, findings, and recommended actions. The report is generated in JSON format and sent to the device.

[0651] Step 8:

[0652] The terminal displays the received report to the technician, allowing the technician to quickly and accurately detect anomalies and implement appropriate countermeasures. UI components are generally used for display, making the report contents visually easy to understand.

[0653] 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.

[0654] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[0655] System configuration and operation

[0656] System configuration

[0657] 1. Terminal

[0658] A device for users (doctors) to input medical image data and patient history information.

[0659] Examples include computers, tablets, and smartphones.

[0660] It has a built-in emotion engine and is equipped with a camera and microphone to analyze the user's facial expressions, voice, and gestures.

[0661] 2. Server

[0662] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[0663] Generative AI is used to search and analyze the database.

[0664] 3. Database

[0665] Medical image database: A database that stores medical image data and corresponding medical history information.

[0666] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[0667] 4. Emotion Engine

[0668] Software that analyzes a user's facial expressions, voice, and gestures to recognize emotions.

[0669] It has the ability to adjust the system's response method based on the analysis results.

[0670] System Operation

[0671] Entering medical images and medical history information

[0672] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[0673] Uploading data

[0674] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[0675] Data analysis and exploration

[0676] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion location, shape, etc.). It then identifies similar past cases from the medical image database and compares them with the uploaded medical history information.

[0677] Generation of suspected disease names

[0678] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data from an emotion engine.

[0679] Providing diagnostics and solutions

[0680] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[0681] Providing reports

[0682] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0683] Specific examples

[0684] Suspected acute stroke

[0685] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[0686] 2. The terminal uploads the entered data to the server.

[0687] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0688] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[0689] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0690] Diagnosis of pneumonia

[0691] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[0692] 2. The device uploads the data to the server.

[0693] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[0694] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[0695] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0696] The system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Its emotion engine recognizes the user's emotional state and adjusts its response accordingly, reducing the burden on doctors and enabling more effective support.

[0697] The processing flow will be explained below.

[0698] Step 1:

[0699] The user (doctor) acquires a patient's medical images (e.g., CT scans, X-ray images) and inputs the patient's corresponding medical history information into the terminal. The terminal saves the medical image data as an image file and the medical history information in text format.

[0700] Step 2:

[0701] The device packages the acquired medical image data and medical history information and uploads them to a server via a secure communication protocol. The data is encrypted during the upload process. An emotion engine also analyzes the user's facial expressions and voice to generate emotion data.

[0702] Step 3:

[0703] The server receives the uploaded medical image data and medical history information and begins analysis using generative AI. First, it extracts features from the medical image (abnormal areas, lesion location, shape, etc.).

[0704] Step 4:

[0705] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to obtain a more accurate similarity score.

[0706] Step 5:

[0707] The server generates suspected disease names based on similar cases. This process includes disease names estimated from past cases using generative AI, and also takes into account the user's emotional data using an emotion engine.

[0708] Step 6:

[0709] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[0710] Step 7:

[0711] The server generates a detailed report containing the diagnosis and treatment plan based on the information retrieved from the medical knowledge database. The report includes the suspected disease, detected features, and recommended treatment. The presentation and content of the report are adjusted according to the user's emotional state.

[0712] Step 8:

[0713] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[0714] Step 9:

[0715] The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0716] This specific processing enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses. The emotion engine provides flexible support according to the user's emotional state, improving the user experience.

[0717] Example 2

[0718] 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."

[0719] In modern medicine, even physicians without specialized expertise are required to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. However, achieving this is not easy due to the breadth of medical knowledge and the complexity of diagnoses. Another issue is that the physician's emotional state can affect the efficiency and accuracy of diagnostic work. To solve these problems, a diagnostic support system is needed that can efficiently and accurately analyze medical image data and patient medical history information, and that also takes the user's emotional state into account.

[0720] 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.

[0721] In this invention, the server includes a means for inputting medical image data, a means for inputting patient medical history information, a means for uploading the medical image data and the patient medical history information to a database, a means for searching the database for similar cases, a means for generating a suspected disease name based on the similar cases, a means for searching a comprehensive medical knowledge database using the suspected disease name and the patient's medical history information, a means for obtaining a diagnosis and countermeasures from the medical knowledge database, a means for providing the diagnosis and countermeasures, a means for recognizing a user's emotional state, and a means for adjusting a response method based on the user's emotional state. This enables doctors to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. Furthermore, by recognizing a user's emotional state and adjusting a response method accordingly, the efficiency and accuracy of diagnostic work can be improved.

[0722] "Medical image data" is data that visually records the state of the inside of the human body, obtained using medical equipment such as radiation or ultrasound.

[0723] "Patient medical history information" is a record of a patient's past diagnoses, treatments, and surgeries, as well as detailed information about their current symptoms and medical history.

[0724] A "database" is a collection of information that is systematically organized to efficiently store, retrieve, and manipulate specific information.

[0725] A "similar case" is a case from previously recorded medical information that is similar to the symptoms and medical image data of a current patient.

[0726] The "suspected disease name" is a disease name that is highly likely to be estimated based on medical image data and the patient's medical history information.

[0727] A "medical knowledge database" is a collection of diagnostic and treatment knowledge extracted from medical treatises, medical books, and other reliable medical sources.

[0728] "Diagnosis and countermeasures" refers to the diagnosis results generated based on medical image data and medical history information, as well as the recommended treatment and testing methods.

[0729] The "user's emotional state" is an emotional state based on the user's facial expressions, voice, gestures, etc., recognized through input devices such as a camera or microphone.

[0730] "Adjusting the response method" refers to a method for providing more appropriate support by changing the method and content of information presentation depending on the user's emotional state.

[0731] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[0732] System configuration

[0733] 1. Terminal

[0734] A device that allows users (doctors) to input medical image data and patient history information. Examples include PCs, tablets, and smartphones. The device is equipped with a camera and microphone, and an emotion engine analyzes the user's facial expressions, voice, and gestures. Specific examples include using tools such as Microsoft Azure Face API and Google Cloud Speech-to-Text.

[0735] 2. Server

[0736] A central processing unit that receives and analyzes medical images and medical history information uploaded from devices. It searches and analyzes the database using generative AI models (e.g., OpenAI's GPT series). Specifically, it uses medical image analysis software (e.g., Google DeepMind's AlphaFold).

[0737] 3. Database

[0738] Medical image database: A database that stores medical image data and corresponding medical history information.

[0739] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[0740] 4. Emotion Engine

[0741] Software that recognizes emotions by analyzing the user's facial expressions, voice, and gestures, and has the ability to adjust the system's response method based on the analysis results.

[0742] System Operation

[0743] This system analyzes medical image data and patient medical history information using the following procedure to provide an appropriate diagnosis and treatment.

[0744] 1. Entering medical images and medical history information

[0745] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[0746] 2. Uploading data

[0747] The device packages the medical image data and medical history information and uploads them to the server using a secure communication method (e.g., HTTPS), including the emotion data obtained from the emotion engine.

[0748] 3. Data analysis and retrieval

[0749] The server receives the uploaded medical images and medical history information and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, medical image analysis software is used to extract features from the images (e.g., abnormal areas, lesion location, shape, etc.). Similar past cases are then identified from a medical image database and compared with the input medical history information.

[0750] 4. Generation of suspected disease names

[0751] The server generates suspected disease names based on similar cases, including disease names predicted using a generative AI model, and also takes into account the user's emotional data from an emotion engine.

[0752] 5. Providing diagnosis and solutions

[0753] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[0754] 6. Providing reports

[0755] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0756] Specific examples

[0757] Suspected acute stroke

[0758] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[0759] 2. The terminal uploads the entered data to the server.

[0760] 3. The server uses the generative AI model to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0761] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[0762] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0763] Prompt Sentence Examples

[0764] "Enter the CT scan and medical history information of a patient suspected of having an acute stroke. The system will recommend emergency treatment."

[0765] Diagnosis of pneumonia

[0766] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[0767] 2. The device uploads the data to the server.

[0768] 3. The server uses the generative AI model to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[0769] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[0770] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0771] Prompt Sentence Examples

[0772] "Enter a chest x-ray and medical history of a patient with a fever and cough. We'll provide the information in an easy-to-understand format, taking into account the user's fatigue level."

[0773] This system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Furthermore, the emotion engine recognizes the user's emotional state and adjusts the response accordingly, reducing the burden on doctors and providing more effective support.

[0774] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0775] Step 1:

[0776] The user inputs medical image data and the patient's medical history information into the terminal. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions, voice, and gestures in real time. Specifically, the terminal receives CT images and X-ray images as medical image data and text data as medical history information. The emotion engine also uses AI-based facial recognition software and voice analysis tools. The input data are medical image files and text medical history information. The output data are medical image data, medical history information, and the user's emotional state data.

[0777] Step 2:

[0778] The terminal packages medical image data, medical history information, and emotion data and uploads them to the server using a secure communication method (e.g., HTTPS, SSL / TLS). The terminal converts this data into JSON format and sends it via a secure HTTP POST request. The input data is the packaged medical image data, medical history information, and emotion data. The output data is the securely uploaded packaged data.

[0779] Step 3:

[0780] The server receives the uploaded data and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, the server uses medical image analysis software to extract features from the image (e.g., abnormal areas, location and shape of lesions). A full-text search engine (e.g., Elasticsearch) is used to search for similar cases recorded in the past from a medical image database. The input data are medical image data and medical history information. The output data are feature data and a candidate list of similar cases.

[0781] Step 4:

[0782] The server generates a suspected disease name based on similar cases. The generative AI model estimates multiple diagnostic candidates and selects the most reliable one. The server also takes into account the user's emotional state obtained by the emotion engine. For example, if the user is in a hurry, the server will prioritize the most important information. The input data are feature data, similar case data, and emotion data. The output data is the suspected disease name.

[0783] Step 5:

[0784] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report. The report includes the suspected disease name, detected features, and recommended treatment. The format and presentation of the report are also adjusted depending on the user's emotional state. For example, if the user is tired, information is presented in an easy-to-understand bullet point format. The input data are the suspected disease name and the medical knowledge database. The output data is the generated report.

[0785] Step 6:

[0786] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor) and provides additional support as needed. The emotion engine analyzes the user's emotions even while the report is being displayed, and provides additional explanations and suggested measures in real time. As a specific example, a user who is feeling anxious is provided with more detailed explanations and visualized data. The input data is the generated report. The output data is the report displayed to the user and the content of additional support.

[0787] (Application example 2)

[0788] 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."

[0789] In the medical field, non-specialist physicians are required to make quick and accurate diagnoses, but the physician's emotions and stress can affect the diagnostic results. In particular, in telemedicine, more effective medical services are required by appropriately recognizing the emotions of the physician and patient and adjusting the diagnosis and treatment methods. The present invention aims to solve this problem and improve the accuracy and efficiency of diagnoses by providing an interface and information that reflects the user's emotional state.

[0790] 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.

[0791] In this invention, the server includes a means for inputting medical image data and patient medical history information, a means for uploading the data to a database, and a means for searching the database for similar cases, which makes it possible to recognize the user's emotions and adjust the interface and information presentation method based on the results.

[0792] "Medical image data" refers to image data taken for the purpose of diagnosing or treating a patient, and includes X-ray images, CT images, MRI images, etc.

[0793] "Patient medical history information" refers to detailed information about a patient's past health condition and illnesses, including medical records, medical history, allergy history, and so on.

[0794] A "database" is a collection of information that stores medical image data and patient medical history information and is used to search for similar cases.

[0795] "Similar cases" refers to past cases that have similar medical images and medical history information to those being analyzed, and are useful in providing diagnoses and countermeasures.

[0796] A "suspected disease name" is a possible diagnosis result generated based on medical image data and a patient's medical history information, and includes specific symptoms and disease names.

[0797] A "medical knowledge database" is a source of medical knowledge necessary for diagnosis and treatment, including information extracted from medical papers and medical books.

[0798] "Generative AI" is a system that uses artificial intelligence technology to analyze medical image data and medical history information, and is used to provide new diagnoses and countermeasures.

[0799] An "emotion engine" is software that analyzes a user's facial expressions, voice, and gestures to recognize their emotional state and adjusts the interface and the way information is presented.

[0800] An "interface" is a platform through which users interact with a system, adaptively adjusting based on emotion recognition.

[0801] System configuration

[0802] The present invention combines a system that analyzes medical image data and patient history information to provide diagnosis and treatment with an emotion engine that recognizes the user's emotions. The main components of the system include a terminal, a server, and a database. The emotion engine is used to analyze the user's emotional state in real time.

[0803] Terminal

[0804] Configuration: A device for doctors to input medical image data and patient medical history information. Specifically, it includes devices equipped with a camera and microphone, such as smartphones, smart glasses, and head-mounted displays, and has an emotion engine built in.

[0805] server

[0806] Configuration: A central processing unit that receives medical images and medical history information uploaded from the terminal and uses generative AI to search and analyze the database.

[0807] Database

[0808] Structure: The system consists of a medical image database and a medical knowledge database. The former stores medical image data and corresponding medical history information, while the latter stores knowledge extracted from medical papers and medical books.

[0809] Emotion Engine

[0810] Configuration: Software that analyzes the user's facial expressions, voice, and gestures to recognize emotions. It has the ability to adjust the system's response method based on the analysis results.

[0811] System Operation

[0812] Entering medical images and medical history information

[0813] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. The emotion engine analyzes the user's facial expressions and voice during this input process and recognizes their emotional state in real time.

[0814] Uploading data

[0815] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[0816] Data analysis and exploration

[0817] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (such as abnormal areas and the location and shape of lesions). It then identifies similar cases from the medical image database and compares them with the uploaded medical history information.

[0818] Generation of suspected disease names

[0819] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data generated by the emotion engine.

[0820] Providing diagnostics and solutions

[0821] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected diagnoses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[0822] Providing reports

[0823] The server sends the generated report to the terminal, which then displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[0824] Specific examples

[0825] Suspected acute stroke

[0826] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[0827] 2. The device uploads the entered data to the server.

[0828] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0829] 4. Based on the results, the server generates a suspected illness name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that immediate action is required.

[0830] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0831] Diagnosis of pneumonia

[0832] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[0833] 2. The device uploads the data to the server.

[0834] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[0835] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[0836] 5. The device displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0837] Prompt Sentence Examples

[0838] "Upload a medical image (e.g., CT scan)

[0839] Please provide your diagnosis and suggest a course of action."

[0840] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0841] Step 1:

[0842] The user (doctor) inputs medical image data and the patient's medical history information acquired during the consultation into the terminal. This input includes, for example, CT images and X-ray images, as well as information about the patient's medical history and current symptoms. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions and voice in real time. The emotion engine collects the input data and the user's facial and vocal characteristics to recognize the user's emotional state.

[0843] Step 2:

[0844] The terminal packages medical image data and patient history information and uploads them to a server using secure communication methods. At this time, the emotional data analyzed by the emotion engine is also included in the package. The terminal inputs medical image data, medical history information, and the user's emotional data, and outputs a package containing this information.

[0845] Step 3:

[0846] The server receives medical image data and patient medical history information uploaded from the device. This data is preprocessed and input into the generative AI model. The server analyzes the data and extracts features (such as abnormal areas and the location and shape of lesions) from the medical images. The input data are medical images and medical history information, and the output is the feature extraction results.

[0847] Step 4:

[0848] The server searches for similar cases in a medical image database and compares them with the uploaded medical history information. The generative AI model identifies similar cases from past cases in the database based on the features. The input data are the features and medical history information, and the output is a list of similar cases.

[0849] Step 5:

[0850] The server generates a suspected disease name based on similar cases. It uses a generative AI model to estimate the most appropriate disease name and outputs this name. The input data is a list of similar cases, and the output is a suspected disease name. It also takes into account the user's emotional data from an emotion engine.

[0851] Step 6:

[0852] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database. Based on the suspected disease name and the patient's medical history, it uses a generative AI to search for appropriate diagnostic information and countermeasures. The input data is the suspected disease name and medical history information, and the output is diagnostic information and countermeasures.

[0853] Step 7:

[0854] The server generates a detailed report, including suspected diagnosis, detected features, and recommended treatment. The emotion engine adjusts the presentation and content of the report according to the user's emotional state. The input data are diagnostic information and countermeasures, and the output is the generated report.

[0855] Step 8:

[0856] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests measures as needed. The input data is the generated report, and the output is the report and additional explanations presented to the user.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] [Third embodiment]

[0861] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0862] 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.

[0863] 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).

[0864] 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.

[0865] 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.

[0866] 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).

[0867] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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."

[0873] This invention is a system that enables even non-specialist doctors to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the function of providing effective diagnoses using generative AI.

[0874] System configuration and operation

[0875] System configuration

[0876] 1. Terminal

[0877] A device for users (doctors) to input medical image data and patient history information.

[0878] Examples include computers, tablets, and smartphones.

[0879] 2. Server

[0880] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[0881] Generative AI is used to search and analyze the database.

[0882] 3. Database

[0883] Medical image database: A database that stores medical image data and corresponding medical history information.

[0884] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[0885] System Operation

[0886] Entering medical images and medical history information

[0887] The user (doctor) inputs medical image data acquired during medical examination and the patient's medical history information into the terminal, thereby obtaining digital data.

[0888] Uploading data

[0889] The terminal packages the medical image data and medical history information and uploads them to a server using secure communication means.

[0890] Data analysis and exploration

[0891] The server analyzes the received medical images and medical history information, extracts features from these data using generative AI, and then searches the medical image database for the most similar cases.

[0892] Generation of suspected disease names

[0893] The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the new patient's medical history information as a query to search a medical knowledge database.

[0894] Providing diagnostics and solutions

[0895] The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and compiles them into a report. The report is detailed and includes suspected disease names, findings, medical knowledge, and countermeasures. It is then sent to the terminal and displayed to the user (doctor).

[0896] Specific examples

[0897] Suspected acute stroke

[0898] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[0899] 2. The terminal uploads the entered data to the server.

[0900] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[0901] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database.

[0902] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[0903] Diagnosis of pneumonia

[0904] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[0905] 2. The device uploads the data to the server.

[0906] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[0907] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database.

[0908] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[0909] This system allows even non-specialist physicians to quickly and accurately evaluate medical images and take appropriate measures, thereby improving the quality and safety of patient care.

[0910] The processing flow will be explained below.

[0911] Step 1:

[0912] The user (doctor) obtains the patient's medical images (e.g., CT scans, X-ray images) and inputs the corresponding patient's medical history information into the terminal. The input data is saved as an image file, and the medical history information is saved in text format.

[0913] Step 2:

[0914] The device packages the acquired medical images and medical history information and uploads them to a server via a secure communication protocol, where the data is encrypted to protect privacy.

[0915] Step 3:

[0916] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion locations, and shapes).

[0917] Step 4:

[0918] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to further improve the similarity.

[0919] Step 5:

[0920] The server generates suspected disease names based on similar cases, which involves using a generative AI to estimate the most appropriate disease name based on the diagnostic results of similar cases.

[0921] Step 6:

[0922] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[0923] Step 7:

[0924] The server uses information retrieved from the medical knowledge database to generate a detailed report containing diagnostic results and treatment options, including suspected illnesses, detected features, and recommended treatments.

[0925] Step 8:

[0926] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[0927] Step 9:

[0928] The terminal displays the received report to the user (doctor), who can use the report to make a quick and accurate diagnosis and treatment plan.

[0929] This specific process enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses, resulting in appropriate treatment for patients and improving work efficiency and the quality of treatment in medical settings.

[0930] Example 1

[0931] 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."

[0932] Even physicians without specialized expertise often have difficulty quickly and accurately evaluating medical images to obtain an appropriate diagnosis and treatment. This increases the risk of misdiagnosis and delayed treatment. The time and effort required to access appropriate information and make the right treatment decisions is also a significant burden.

[0933] 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.

[0934] In this invention, the server includes a means for inputting medical images, a means for inputting patient medical history, a means for uploading the medical images and the patient medical history to a cloud server, a means for performing preprocessing on the cloud server, a means for searching a database for similar cases from the cloud server and extracting features, a means for using a generative AI model to generate a suspected disease name based on the similar cases, a means for searching a medical knowledge database using the generated suspected disease name and the patient medical history, a means for acquiring diagnostic and treatment information from the medical knowledge database, and a means for displaying the acquired diagnostic and treatment information. This enables even non-specialist physicians to quickly and accurately evaluate medical images and quickly obtain an appropriate diagnosis and countermeasure.

[0935] "Medical images" are image data taken for medical purposes using radiation, ultrasound, magnetic resonance, etc.

[0936] "Patient medical history" refers to information that records a patient's past and present medical condition and treatment history.

[0937] A "cloud server" is a server system that provides distributed computing resources over the Internet.

[0938] A "generative AI model" is an artificial intelligence model that analyzes medical data and automatically generates diagnosis results and disease names.

[0939] "Preprocessing" refers to the initial processing operations performed on the data to be analyzed, and includes processes such as data normalization, filtering, and resizing.

[0940] "Feature extraction" is the process of extracting useful statistical or structural features from data.

[0941] "Suspected disease name" refers to the name of a disease that may be a candidate as a result of the analysis.

[0942] A "medical knowledge database" is a database that centrally manages knowledge and information extracted from medical papers and books.

[0943] "Diagnostic and treatment information" refers to information on diagnostic results and countermeasures or treatment methods based on medical knowledge.

[0944] This invention is a system that enables even non-specialist physicians to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the ability to provide effective diagnoses using generative AI models.

[0945] System configuration

[0946] 1. Terminal

[0947] The terminal is a device where users (doctors) input medical image data and patient medical history information. Examples include PCs, tablets, and smartphones. Each terminal runs application software that securely uploads the input data to a cloud server.

[0948] 2. Server

[0949] The server is a central processing unit that receives and analyzes medical images and medical history information uploaded from the device. The analysis is performed using a generative AI model. The server performs image preprocessing and feature extraction using deep learning frameworks such as TensorFlow and PyTorch.

[0950] 3. Database

[0951] The database manages two types of data:

[0952] Medical image database: stores medical image data and corresponding medical history information.

[0953] Medical knowledge database: Stores knowledge extracted from medical papers and medical books.

[0954] System Operation

[0955] 1. The user inputs medical image data acquired during medical treatment and the patient's medical history information into the terminal, which generates digital data.

[0956] 2. The device encrypts this data and uploads it to the server using a secure communication method (e.g., HTTPS).

[0957] 3. The server analyzes the received medical images and medical history information, specifically preprocessing the images (e.g., normalizing and resizing) and extracting features using a generative AI model.

[0958] 4. The server uses the extracted features to search for the most similar cases from the medical image database.

[0959] 5. The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the patient's medical history information as a query to search a medical knowledge database.

[0960] 6. The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and generates a report containing them. This report includes suspected diagnosis, findings, medical knowledge, and countermeasures.

[0961] 7. The terminal displays the report to the user, allowing the user to quickly and accurately diagnose and plan treatment.

[0962] Specific examples

[0963] Suspected acute stroke

[0964] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[0965] Sample prompt: "Analyze this patient's CT scans to assess whether they indicate acute stroke."

[0966] 2. The terminal uploads the entered data to the server.

[0967] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "acute stroke."

[0968] 4. The server retrieves the appropriate response from the medical knowledge database.

[0969] 5. The device displays a report to the user containing the diagnosis and recommended solutions.

[0970] Diagnosis of pneumonia

[0971] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[0972] Sample prompt: "Analyze this patient's chest x-ray to assess the possibility of pneumonia."

[0973] 2. The device uploads the data to the server.

[0974] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "pneumonia."

[0975] 4. The server retrieves appropriate treatments and recommended tests from the medical knowledge database.

[0976] 5. The device displays this information to the user and supports appropriate treatment planning.

[0977] This allows even non-specialist doctors to quickly and accurately evaluate medical images and take appropriate measures. Specific embodiments of the invention can improve the quality and safety of patient care.

[0978] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0979] Step 1:

[0980] The user inputs medical image data and patient history information.

[0981] Input: Medical image data (e.g., CT scans, X-rays), patient history information

[0982] How it works: The user enters the required information into the input form displayed on the screen of their computer or tablet and clicks the button to upload the image data.

[0983] Output: Digital medical image data and patient history information are stored on the terminal.

[0984] Step 2:

[0985] The terminal uploads medical image data and patient medical history information to a cloud server.

[0986] Input: Digital medical image data and patient history information entered in step 1

[0987] How it works: The device encrypts input data and sends it securely to the cloud server using the HTTPS protocol.

[0988] Output: The encrypted data is uploaded to the cloud server.

[0989] Step 3:

[0990] The server analyzes and preprocesses the uploaded data.

[0991] Input: Encrypted and uploaded medical image data and patient history information

[0992] How it works: The server decrypts the data, preprocesses the images (e.g., normalizes, resizes), and extracts features from the medical images using deep learning models (e.g., TensorFlow, PyTorch).

[0993] Output: Preprocessed image data and extracted features

[0994] Step 4:

[0995] The server uses the generated AI model to search for similar cases.

[0996] Input: Features extracted in step 3

[0997] Operation: The server searches for similar cases in a medical image database using a similarity search algorithm such as K-Nearest Neighbors.

[0998] Output: A list of the most similar cases and their corresponding features

[0999] Step 5:

[1000] The server generates a suspected disease name based on similar cases.

[1001] Input: List of similar cases obtained in step 4 and feature values

[1002] How it works: The server uses a generative AI model to generate suspected disease names from similar cases.

[1003] Output: Generated suspected disease name

[1004] Step 6:

[1005] The server generates a suspected disease name and uses the patient's medical history information to search a medical knowledge database.

[1006] Input: Generated suspected disease name, patient medical history information

[1007] Operation: The server uses NLP techniques to search a medical knowledge database and extract relevant diagnostic information and treatment options.

[1008] Output: Diagnostic information and remedial actions

[1009] Step 7:

[1010] The device displays diagnostic and remediation information.

[1011] Input: Diagnostic information and remedial action taken in step 6

[1012] Operation: The device generates a report in PDF or HTML format containing diagnostic results and countermeasures, and displays it through the user interface.

[1013] Output: Diagnostic report displayed to the user

[1014] (Application example 1)

[1015] 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."

[1016] Maintaining normal operation of industrial equipment requires early detection of abnormalities and appropriate maintenance. However, it is difficult for engineers without specialized knowledge to quickly and accurately detect abnormalities and take appropriate countermeasures. Conventional methods take time to diagnose abnormalities and provide countermeasures, which can lead to reduced production efficiency and increased maintenance costs. The present invention aims to solve these problems and provide a system that supports optimal operation and maintenance of industrial equipment.

[1017] 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.

[1018] In this invention, the server includes a means for inputting the operation data of the industrial equipment, a means for inputting the maintenance history of the industrial equipment, and a means for uploading the operation data and the maintenance history to the database, which enables even an engineer without specialized knowledge to quickly and accurately detect an abnormality and provide an appropriate countermeasure.

[1019] "Industrial equipment" means machinery and equipment used in the manufacturing process.

[1020] "Operation data" refers to data that indicates information about the operating status and operating state of industrial equipment.

[1021] "Maintenance history" refers to a record of past maintenance work and repairs performed on industrial equipment.

[1022] A "database" is a system for storing large amounts of data in an organized manner and facilitating search and access.

[1023] "Similar cases" are cases similar to the operating conditions and maintenance history of industrial equipment stored in the past database.

[1024] A "suspected abnormality" is a condition that is predicted to indicate a potential problem with industrial equipment based on operational data and maintenance history.

[1025] The "maintenance knowledge database" is a database that stores information collected from technical documents and papers related to the maintenance of industrial equipment.

[1026] "Diagnosis" is the process of assessing the condition of industrial equipment and identifying potential problems.

[1027] "Countermeasures" are specific measures recommended to solve problems in industrial equipment based on the diagnosis results.

[1028] "Generative AI" is a type of artificial intelligence technology and a machine learning model for data analysis and predictive modeling.

[1029] To implement the invention, it is necessary to build a system that utilizes the operational data and maintenance history of industrial equipment. This system is realized using the following hardware and software.

[1030] Hardware used

[1031] 1. Server: A central processing unit that analyzes and stores data.

[1032] 2. Terminal: A device such as a computer, tablet, or smartphone that allows technicians to input and view data.

[1033] Software used

[1034] 1. Data format: JSON format

[1035] 2. AI libraries: TensorFlow or PyTorch (used to build generative AI models)

[1036] 3. Communication method: HTTPS protocol

[1037] System configuration and operation

[1038] Data Entry and Upload

[1039] Technicians input the operational data and maintenance history of industrial equipment into a terminal, which then captures the data in digital format. The terminal then packages the data and uploads it to a server using secure communications.

[1040] Feature Extraction and Search

[1041] The server analyzes the received operational data and maintenance history and uses generative AI to extract features from these data. It then searches the database for the most similar cases, allowing it to compare past data with new data.

[1042] Anomaly generation and database search

[1043] The server generates a suspected anomaly based on the most similar cases, and uses this suspected anomaly and the maintenance history as a query to search a maintenance knowledge database, from which relevant diagnostic information and countermeasures are extracted.

[1044] Report Generation and Viewing

[1045] The server generates a report containing the diagnosis and countermeasures. This report, which includes suspected abnormalities, findings, maintenance knowledge, and countermeasures, is sent to the terminal. Technicians can use this report to make quick and accurate maintenance decisions.

[1046] Specific examples

[1047] When a technician inputs data to detect abnormalities in the robot, the data is sent to a server, where the generative AI detects the abnormality, compares it with the most similar past data, and provides appropriate maintenance methods.

[1048] Prompt Sentence Examples

[1049] "The robot's operating data and maintenance history have been entered as follows:

[1050] Operational data: {sensor_data}

[1051] Maintenance history: {maintenance_history}

[1052] Based on this, generate a diagnosis of the anomaly and provide appropriate remedial action."

[1053] As described above, this system enables even engineers without specialized knowledge to quickly and accurately detect abnormalities and provide appropriate countermeasures, thereby improving factory production efficiency and reducing maintenance costs.

[1054] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1055] Step 1:

[1056] The user inputs the operation data and maintenance history of industrial equipment into the terminal. This input includes operating status data obtained from sensors and past maintenance records. This allows the terminal to collect digital data. To process the input data, the operation data is converted into JSON format, and the maintenance history is also converted into the same format.

[1057] Step 2:

[1058] The device packages the operation data and maintenance history and uploads them to the server using a secure communication method (HTTPS protocol). The data packaging involves combining various data fields and adding metadata. The packaged data is sent to the server in JSON format.

[1059] Step 3:

[1060] The server analyzes the received operational data and maintenance history. This involves using a generative AI model to extract features from the data. Specifically, the model, trained using TensorFlow or PyTorch, identifies important features from the input data (for example, vibration patterns or temperature fluctuations). The output is stored as a feature vector.

[1061] Step 4:

[1062] The server uses the extracted feature vector to search for similar cases in the database. Here, it matches past operation data and maintenance history with similar features to find the most similar entry. The search algorithm used is, for example, cosine similarity, and calculates the similarity to output a list of similar cases.

[1063] Step 5:

[1064] The server generates suspected anomalies based on the most similar cases. A generative AI model is used to generate predictions about abnormal conditions based on new feature vectors and past cases. The output is a number of suspected anomalies and their probabilities.

[1065] Step 6:

[1066] The server uses the suspected anomaly and maintenance history as a query to search a maintenance knowledge database. This search extracts relevant diagnostic information and countermeasures. The knowledge database contains technical documentation and past maintenance cases, and provides a list of countermeasures.

[1067] Step 7:

[1068] The server generates a diagnostic and actionable report, which includes suspected anomalies, findings, and recommended actions. The report is generated in JSON format and sent to the device.

[1069] Step 8:

[1070] The terminal displays the received report to the technician, allowing the technician to quickly and accurately detect anomalies and implement appropriate countermeasures. UI components are generally used for display, making the report contents visually easy to understand.

[1071] 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.

[1072] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[1073] System configuration and operation

[1074] System configuration

[1075] 1. Terminal

[1076] A device for users (doctors) to input medical image data and patient history information.

[1077] Examples include computers, tablets, and smartphones.

[1078] It has a built-in emotion engine and is equipped with a camera and microphone to analyze the user's facial expressions, voice, and gestures.

[1079] 2. Server

[1080] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[1081] Generative AI is used to search and analyze the database.

[1082] 3. Database

[1083] Medical image database: A database that stores medical image data and corresponding medical history information.

[1084] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[1085] 4. Emotion Engine

[1086] Software that analyzes a user's facial expressions, voice, and gestures to recognize emotions.

[1087] It has the ability to adjust the system's response method based on the analysis results.

[1088] System Operation

[1089] Entering medical images and medical history information

[1090] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[1091] Uploading data

[1092] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[1093] Data analysis and exploration

[1094] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion location, shape, etc.). It then identifies similar past cases from the medical image database and compares them with the uploaded medical history information.

[1095] Generation of suspected disease names

[1096] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data from an emotion engine.

[1097] Providing diagnostics and solutions

[1098] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[1099] Providing reports

[1100] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1101] Specific examples

[1102] Suspected acute stroke

[1103] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[1104] 2. The terminal uploads the entered data to the server.

[1105] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[1106] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[1107] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[1108] Diagnosis of pneumonia

[1109] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[1110] 2. The device uploads the data to the server.

[1111] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[1112] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[1113] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[1114] The system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Its emotion engine recognizes the user's emotional state and adjusts its response accordingly, reducing the burden on doctors and enabling more effective support.

[1115] The processing flow will be explained below.

[1116] Step 1:

[1117] The user (doctor) acquires a patient's medical images (e.g., CT scans, X-ray images) and inputs the patient's corresponding medical history information into the terminal. The terminal saves the medical image data as an image file and the medical history information in text format.

[1118] Step 2:

[1119] The device packages the acquired medical image data and medical history information and uploads them to a server via a secure communication protocol. The data is encrypted during the upload process. An emotion engine also analyzes the user's facial expressions and voice to generate emotion data.

[1120] Step 3:

[1121] The server receives the uploaded medical image data and medical history information and begins analysis using generative AI. First, it extracts features from the medical image (abnormal areas, lesion location, shape, etc.).

[1122] Step 4:

[1123] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to obtain a more accurate similarity score.

[1124] Step 5:

[1125] The server generates suspected disease names based on similar cases. This process includes disease names estimated from past cases using generative AI, and also takes into account the user's emotional data using an emotion engine.

[1126] Step 6:

[1127] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[1128] Step 7:

[1129] The server generates a detailed report containing the diagnosis and treatment plan based on the information retrieved from the medical knowledge database. The report includes the suspected disease, detected features, and recommended treatment. The presentation and content of the report are adjusted according to the user's emotional state.

[1130] Step 8:

[1131] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[1132] Step 9:

[1133] The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1134] This specific processing enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses. The emotion engine provides flexible support according to the user's emotional state, improving the user experience.

[1135] Example 2

[1136] 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."

[1137] In modern medicine, even physicians without specialized expertise are required to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. However, achieving this is not easy due to the breadth of medical knowledge and the complexity of diagnoses. Another issue is that the physician's emotional state can affect the efficiency and accuracy of diagnostic work. To solve these problems, a diagnostic support system is needed that can efficiently and accurately analyze medical image data and patient medical history information, and that also takes the user's emotional state into account.

[1138] 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.

[1139] In this invention, the server includes a means for inputting medical image data, a means for inputting patient medical history information, a means for uploading the medical image data and the patient medical history information to a database, a means for searching the database for similar cases, a means for generating a suspected disease name based on the similar cases, a means for searching a comprehensive medical knowledge database using the suspected disease name and the patient's medical history information, a means for obtaining a diagnosis and countermeasures from the medical knowledge database, a means for providing the diagnosis and countermeasures, a means for recognizing a user's emotional state, and a means for adjusting a response method based on the user's emotional state. This enables doctors to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. Furthermore, by recognizing a user's emotional state and adjusting a response method accordingly, the efficiency and accuracy of diagnostic work can be improved.

[1140] "Medical image data" is data that visually records the state of the inside of the human body, obtained using medical equipment such as radiation or ultrasound.

[1141] "Patient medical history information" is a record of a patient's past diagnoses, treatments, and surgeries, as well as detailed information about their current symptoms and medical history.

[1142] A "database" is a collection of information that is systematically organized to efficiently store, retrieve, and manipulate specific information.

[1143] A "similar case" is a case from previously recorded medical information that is similar to the symptoms and medical image data of a current patient.

[1144] The "suspected disease name" is a disease name that is highly likely to be estimated based on medical image data and the patient's medical history information.

[1145] A "medical knowledge database" is a collection of diagnostic and treatment knowledge extracted from medical treatises, medical books, and other reliable medical sources.

[1146] "Diagnosis and countermeasures" refers to the diagnosis results generated based on medical image data and medical history information, as well as the recommended treatment and testing methods.

[1147] The "user's emotional state" is an emotional state based on the user's facial expressions, voice, gestures, etc., recognized through input devices such as a camera or microphone.

[1148] "Adjusting the response method" refers to a method for providing more appropriate support by changing the method and content of information presentation depending on the user's emotional state.

[1149] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[1150] System configuration

[1151] 1. Terminal

[1152] A device that allows users (doctors) to input medical image data and patient history information. Examples include PCs, tablets, and smartphones. The device is equipped with a camera and microphone, and an emotion engine analyzes the user's facial expressions, voice, and gestures. Specific examples include using tools such as Microsoft Azure Face API and Google Cloud Speech-to-Text.

[1153] 2. Server

[1154] A central processing unit that receives and analyzes medical images and medical history information uploaded from devices. It searches and analyzes the database using generative AI models (e.g., OpenAI's GPT series). Specifically, it uses medical image analysis software (e.g., Google DeepMind's AlphaFold).

[1155] 3. Database

[1156] Medical image database: A database that stores medical image data and corresponding medical history information.

[1157] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[1158] 4. Emotion Engine

[1159] Software that recognizes emotions by analyzing the user's facial expressions, voice, and gestures, and has the ability to adjust the system's response method based on the analysis results.

[1160] System Operation

[1161] This system analyzes medical image data and patient medical history information using the following procedure to provide an appropriate diagnosis and treatment.

[1162] 1. Entering medical images and medical history information

[1163] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[1164] 2. Uploading data

[1165] The device packages the medical image data and medical history information and uploads them to the server using a secure communication method (e.g., HTTPS), including the emotion data obtained from the emotion engine.

[1166] 3. Data analysis and retrieval

[1167] The server receives the uploaded medical images and medical history information and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, medical image analysis software is used to extract features from the images (e.g., abnormal areas, lesion location, shape, etc.). Similar past cases are then identified from a medical image database and compared with the input medical history information.

[1168] 4. Generation of suspected disease names

[1169] The server generates suspected disease names based on similar cases, including disease names predicted using a generative AI model, and also takes into account the user's emotional data from an emotion engine.

[1170] 5. Providing diagnosis and solutions

[1171] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[1172] 6. Providing reports

[1173] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1174] Specific examples

[1175] Suspected acute stroke

[1176] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[1177] 2. The terminal uploads the entered data to the server.

[1178] 3. The server uses the generative AI model to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[1179] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[1180] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[1181] Prompt Sentence Examples

[1182] "Enter the CT scan and medical history information of a patient suspected of having an acute stroke. The system will recommend emergency treatment."

[1183] Diagnosis of pneumonia

[1184] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[1185] 2. The device uploads the data to the server.

[1186] 3. The server uses the generative AI model to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[1187] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[1188] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[1189] Prompt Sentence Examples

[1190] "Enter a chest x-ray and medical history of a patient with a fever and cough. We'll provide the information in an easy-to-understand format, taking into account the user's fatigue level."

[1191] This system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Furthermore, the emotion engine recognizes the user's emotional state and adjusts the response accordingly, reducing the burden on doctors and providing more effective support.

[1192] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1193] Step 1:

[1194] The user inputs medical image data and the patient's medical history information into the terminal. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions, voice, and gestures in real time. Specifically, the terminal receives CT images and X-ray images as medical image data and text data as medical history information. The emotion engine also uses AI-based facial recognition software and voice analysis tools. The input data are medical image files and text medical history information. The output data are medical image data, medical history information, and the user's emotional state data.

[1195] Step 2:

[1196] The terminal packages medical image data, medical history information, and emotion data and uploads them to the server using a secure communication method (e.g., HTTPS, SSL / TLS). The terminal converts this data into JSON format and sends it via a secure HTTP POST request. The input data is the packaged medical image data, medical history information, and emotion data. The output data is the securely uploaded packaged data.

[1197] Step 3:

[1198] The server receives the uploaded data and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, the server uses medical image analysis software to extract features from the image (e.g., abnormal areas, location and shape of lesions). A full-text search engine (e.g., Elasticsearch) is used to search for similar cases recorded in the past from a medical image database. The input data are medical image data and medical history information. The output data are feature data and a candidate list of similar cases.

[1199] Step 4:

[1200] The server generates a suspected disease name based on similar cases. The generative AI model estimates multiple diagnostic candidates and selects the most reliable one. The server also takes into account the user's emotional state obtained by the emotion engine. For example, if the user is in a hurry, the server will prioritize the most important information. The input data are feature data, similar case data, and emotion data. The output data is the suspected disease name.

[1201] Step 5:

[1202] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report. The report includes the suspected disease name, detected features, and recommended treatment. The format and presentation of the report are also adjusted depending on the user's emotional state. For example, if the user is tired, information is presented in an easy-to-understand bullet point format. The input data are the suspected disease name and the medical knowledge database. The output data is the generated report.

[1203] Step 6:

[1204] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor) and provides additional support as needed. The emotion engine analyzes the user's emotions even while the report is being displayed, and provides additional explanations and suggested measures in real time. As a specific example, a user who is feeling anxious is provided with more detailed explanations and visualized data. The input data is the generated report. The output data is the report displayed to the user and the content of additional support.

[1205] (Application example 2)

[1206] 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."

[1207] In the medical field, non-specialist physicians are required to make quick and accurate diagnoses, but the physician's emotions and stress can affect the diagnostic results. In particular, in telemedicine, more effective medical services are required by appropriately recognizing the emotions of the physician and patient and adjusting the diagnosis and treatment methods. The present invention aims to solve this problem and improve the accuracy and efficiency of diagnoses by providing an interface and information that reflects the user's emotional state.

[1208] 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.

[1209] In this invention, the server includes a means for inputting medical image data and patient medical history information, a means for uploading the data to a database, and a means for searching the database for similar cases, which makes it possible to recognize the user's emotions and adjust the interface and information presentation method based on the results.

[1210] "Medical image data" refers to image data taken for the purpose of diagnosing or treating a patient, and includes X-ray images, CT images, MRI images, etc.

[1211] "Patient medical history information" refers to detailed information about a patient's past health condition and illnesses, including medical records, medical history, allergy history, and so on.

[1212] A "database" is a collection of information that stores medical image data and patient medical history information and is used to search for similar cases.

[1213] "Similar cases" refers to past cases that have similar medical images and medical history information to those being analyzed, and are useful in providing diagnoses and countermeasures.

[1214] A "suspected disease name" is a possible diagnosis result generated based on medical image data and a patient's medical history information, and includes specific symptoms and disease names.

[1215] A "medical knowledge database" is a source of medical knowledge necessary for diagnosis and treatment, including information extracted from medical papers and medical books.

[1216] "Generative AI" is a system that uses artificial intelligence technology to analyze medical image data and medical history information, and is used to provide new diagnoses and countermeasures.

[1217] An "emotion engine" is software that analyzes a user's facial expressions, voice, and gestures to recognize their emotional state and adjusts the interface and the way information is presented.

[1218] An "interface" is a platform through which users interact with a system, adaptively adjusting based on emotion recognition.

[1219] System configuration

[1220] The present invention combines a system that analyzes medical image data and patient history information to provide diagnosis and treatment with an emotion engine that recognizes the user's emotions. The main components of the system include a terminal, a server, and a database. The emotion engine is used to analyze the user's emotional state in real time.

[1221] Terminal

[1222] Configuration: A device for doctors to input medical image data and patient medical history information. Specifically, it includes devices equipped with a camera and microphone, such as smartphones, smart glasses, and head-mounted displays, and has an emotion engine built in.

[1223] server

[1224] Configuration: A central processing unit that receives medical images and medical history information uploaded from the terminal and uses generative AI to search and analyze the database.

[1225] Database

[1226] Structure: The system consists of a medical image database and a medical knowledge database. The former stores medical image data and corresponding medical history information, while the latter stores knowledge extracted from medical papers and medical books.

[1227] Emotion Engine

[1228] Configuration: Software that analyzes the user's facial expressions, voice, and gestures to recognize emotions. It has the ability to adjust the system's response method based on the analysis results.

[1229] System Operation

[1230] Entering medical images and medical history information

[1231] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. The emotion engine analyzes the user's facial expressions and voice during this input process and recognizes their emotional state in real time.

[1232] Uploading data

[1233] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[1234] Data analysis and exploration

[1235] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (such as abnormal areas and the location and shape of lesions). It then identifies similar cases from the medical image database and compares them with the uploaded medical history information.

[1236] Generation of suspected disease names

[1237] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data generated by the emotion engine.

[1238] Providing diagnostics and solutions

[1239] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected diagnoses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[1240] Providing reports

[1241] The server sends the generated report to the terminal, which then displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1242] Specific examples

[1243] Suspected acute stroke

[1244] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[1245] 2. The device uploads the entered data to the server.

[1246] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[1247] 4. Based on the results, the server generates a suspected illness name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that immediate action is required.

[1248] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[1249] Diagnosis of pneumonia

[1250] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[1251] 2. The device uploads the data to the server.

[1252] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[1253] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[1254] 5. The device displays this information to the user (general practitioner) and supports appropriate treatment planning.

[1255] Prompt Sentence Examples

[1256] "Upload a medical image (e.g., CT scan)

[1257] Please provide your diagnosis and suggest a course of action."

[1258] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1259] Step 1:

[1260] The user (doctor) inputs medical image data and the patient's medical history information acquired during the consultation into the terminal. This input includes, for example, CT images and X-ray images, as well as information about the patient's medical history and current symptoms. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions and voice in real time. The emotion engine collects the input data and the user's facial and vocal characteristics to recognize the user's emotional state.

[1261] Step 2:

[1262] The terminal packages medical image data and patient history information and uploads them to a server using secure communication methods. At this time, the emotional data analyzed by the emotion engine is also included in the package. The terminal inputs medical image data, medical history information, and the user's emotional data, and outputs a package containing this information.

[1263] Step 3:

[1264] The server receives medical image data and patient medical history information uploaded from the device. This data is preprocessed and input into the generative AI model. The server analyzes the data and extracts features (such as abnormal areas and the location and shape of lesions) from the medical images. The input data are medical images and medical history information, and the output is the feature extraction results.

[1265] Step 4:

[1266] The server searches for similar cases in a medical image database and compares them with the uploaded medical history information. The generative AI model identifies similar cases from past cases in the database based on the features. The input data are the features and medical history information, and the output is a list of similar cases.

[1267] Step 5:

[1268] The server generates a suspected disease name based on similar cases. It uses a generative AI model to estimate the most appropriate disease name and outputs this name. The input data is a list of similar cases, and the output is a suspected disease name. It also takes into account the user's emotional data from an emotion engine.

[1269] Step 6:

[1270] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database. Based on the suspected disease name and the patient's medical history, it uses a generative AI to search for appropriate diagnostic information and countermeasures. The input data is the suspected disease name and medical history information, and the output is diagnostic information and countermeasures.

[1271] Step 7:

[1272] The server generates a detailed report, including suspected diagnosis, detected features, and recommended treatment. The emotion engine adjusts the presentation and content of the report according to the user's emotional state. The input data are diagnostic information and countermeasures, and the output is the generated report.

[1273] Step 8:

[1274] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests measures as needed. The input data is the generated report, and the output is the report and additional explanations presented to the user.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] [Fourth embodiment]

[1279] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1280] 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.

[1281] 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).

[1282] 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.

[1283] 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.

[1284] 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).

[1285] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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."

[1292] This invention is a system that enables even non-specialist doctors to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the function of providing effective diagnoses using generative AI.

[1293] System configuration and operation

[1294] System configuration

[1295] 1. Terminal

[1296] A device for users (doctors) to input medical image data and patient history information.

[1297] Examples include computers, tablets, and smartphones.

[1298] 2. Server

[1299] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[1300] Generative AI is used to search and analyze the database.

[1301] 3. Database

[1302] Medical image database: A database that stores medical image data and corresponding medical history information.

[1303] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[1304] System Operation

[1305] Entering medical images and medical history information

[1306] The user (doctor) inputs medical image data acquired during medical examination and the patient's medical history information into the terminal, thereby obtaining digital data.

[1307] Uploading data

[1308] The terminal packages the medical image data and medical history information and uploads them to a server using secure communication means.

[1309] Data analysis and exploration

[1310] The server analyzes the received medical images and medical history information, extracts features from these data using generative AI, and then searches the medical image database for the most similar cases.

[1311] Generation of suspected disease names

[1312] The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the new patient's medical history information as a query to search a medical knowledge database.

[1313] Providing diagnostics and solutions

[1314] The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and compiles them into a report. The report is detailed and includes suspected disease names, findings, medical knowledge, and countermeasures. It is then sent to the terminal and displayed to the user (doctor).

[1315] Specific examples

[1316] Suspected acute stroke

[1317] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[1318] 2. The terminal uploads the entered data to the server.

[1319] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[1320] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database.

[1321] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[1322] Diagnosis of pneumonia

[1323] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[1324] 2. The device uploads the data to the server.

[1325] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[1326] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database.

[1327] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[1328] This system allows even non-specialist physicians to quickly and accurately evaluate medical images and take appropriate measures, thereby improving the quality and safety of patient care.

[1329] The processing flow will be explained below.

[1330] Step 1:

[1331] The user (doctor) obtains the patient's medical images (e.g., CT scans, X-ray images) and inputs the corresponding patient's medical history information into the terminal. The input data is saved as an image file, and the medical history information is saved in text format.

[1332] Step 2:

[1333] The device packages the acquired medical images and medical history information and uploads them to a server via a secure communication protocol, where the data is encrypted to protect privacy.

[1334] Step 3:

[1335] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion locations, and shapes).

[1336] Step 4:

[1337] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to further improve the similarity.

[1338] Step 5:

[1339] The server generates suspected disease names based on similar cases, which involves using a generative AI to estimate the most appropriate disease name based on the diagnostic results of similar cases.

[1340] Step 6:

[1341] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[1342] Step 7:

[1343] The server uses information retrieved from the medical knowledge database to generate a detailed report containing diagnostic results and treatment options, including suspected illnesses, detected features, and recommended treatments.

[1344] Step 8:

[1345] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[1346] Step 9:

[1347] The terminal displays the received report to the user (doctor), who can use the report to make a quick and accurate diagnosis and treatment plan.

[1348] This specific process enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses, resulting in appropriate treatment for patients and improving work efficiency and the quality of treatment in medical settings.

[1349] Example 1

[1350] 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."

[1351] Even physicians without specialized expertise often have difficulty quickly and accurately evaluating medical images to obtain an appropriate diagnosis and treatment. This increases the risk of misdiagnosis and delayed treatment. The time and effort required to access appropriate information and make the right treatment decisions is also a significant burden.

[1352] 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.

[1353] In this invention, the server includes a means for inputting medical images, a means for inputting patient medical history, a means for uploading the medical images and the patient medical history to a cloud server, a means for performing preprocessing on the cloud server, a means for searching a database for similar cases from the cloud server and extracting features, a means for using a generative AI model to generate a suspected disease name based on the similar cases, a means for searching a medical knowledge database using the generated suspected disease name and the patient medical history, a means for acquiring diagnostic and treatment information from the medical knowledge database, and a means for displaying the acquired diagnostic and treatment information. This enables even non-specialist physicians to quickly and accurately evaluate medical images and quickly obtain an appropriate diagnosis and countermeasure.

[1354] "Medical images" are image data taken for medical purposes using radiation, ultrasound, magnetic resonance, etc.

[1355] "Patient medical history" refers to information that records a patient's past and present medical condition and treatment history.

[1356] A "cloud server" is a server system that provides distributed computing resources over the Internet.

[1357] A "generative AI model" is an artificial intelligence model that analyzes medical data and automatically generates diagnosis results and disease names.

[1358] "Preprocessing" refers to the initial processing operations performed on the data to be analyzed, and includes processes such as data normalization, filtering, and resizing.

[1359] "Feature extraction" is the process of extracting useful statistical or structural features from data.

[1360] "Suspected disease name" refers to the name of a disease that may be a candidate as a result of the analysis.

[1361] A "medical knowledge database" is a database that centrally manages knowledge and information extracted from medical papers and books.

[1362] "Diagnostic and treatment information" refers to information on diagnostic results and countermeasures or treatment methods based on medical knowledge.

[1363] This invention is a system that enables even non-specialist physicians to quickly and accurately evaluate medical images and obtain appropriate diagnoses and treatments. This system centrally manages medical image data and patient medical history information, and has the ability to provide effective diagnoses using generative AI models.

[1364] System configuration

[1365] 1. Terminal

[1366] The terminal is a device where users (doctors) input medical image data and patient medical history information. Examples include PCs, tablets, and smartphones. Each terminal runs application software that securely uploads the input data to a cloud server.

[1367] 2. Server

[1368] The server is a central processing unit that receives and analyzes medical images and medical history information uploaded from the device. The analysis is performed using a generative AI model. The server performs image preprocessing and feature extraction using deep learning frameworks such as TensorFlow and PyTorch.

[1369] 3. Database

[1370] The database manages two types of data:

[1371] Medical image database: stores medical image data and corresponding medical history information.

[1372] Medical knowledge database: Stores knowledge extracted from medical papers and medical books.

[1373] System Operation

[1374] 1. The user inputs medical image data acquired during medical treatment and the patient's medical history information into the terminal, which generates digital data.

[1375] 2. The device encrypts this data and uploads it to the server using a secure communication method (e.g., HTTPS).

[1376] 3. The server analyzes the received medical images and medical history information, specifically preprocessing the images (e.g., normalizing and resizing) and extracting features using a generative AI model.

[1377] 4. The server uses the extracted features to search for the most similar cases from the medical image database.

[1378] 5. The server generates a suspected diagnosis based on the most similar cases, and uses this suspected diagnosis and the patient's medical history information as a query to search a medical knowledge database.

[1379] 6. The server extracts relevant diagnostic information and countermeasures from the medical knowledge database and generates a report containing them. This report includes suspected diagnosis, findings, medical knowledge, and countermeasures.

[1380] 7. The terminal displays the report to the user, allowing the user to quickly and accurately diagnose and plan treatment.

[1381] Specific examples

[1382] Suspected acute stroke

[1383] 1. The user (emergency physician) acquires CT images of a patient suspected of having an acute stroke and inputs the image data and the patient's medical history information into the terminal.

[1384] Sample prompt: "Analyze this patient's CT scans to assess whether they indicate acute stroke."

[1385] 2. The terminal uploads the entered data to the server.

[1386] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "acute stroke."

[1387] 4. The server retrieves the appropriate response from the medical knowledge database.

[1388] 5. The device displays a report to the user containing the diagnosis and recommended solutions.

[1389] Diagnosis of pneumonia

[1390] 1. The user (general practitioner) obtains a chest X-ray image of a patient who complains of fever and cough, and enters the image data and medical history information into the terminal.

[1391] Sample prompt: "Analyze this patient's chest x-ray to assess the possibility of pneumonia."

[1392] 2. The device uploads the data to the server.

[1393] 3. The server uses the generative AI model to search for similar cases in a medical image database and generate the suspected disease name "pneumonia."

[1394] 4. The server retrieves appropriate treatments and recommended tests from the medical knowledge database.

[1395] 5. The device displays this information to the user and supports appropriate treatment planning.

[1396] This allows even non-specialist doctors to quickly and accurately evaluate medical images and take appropriate measures. Specific embodiments of the invention can improve the quality and safety of patient care.

[1397] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1398] Step 1:

[1399] The user inputs medical image data and patient history information.

[1400] Input: Medical image data (e.g., CT scans, X-rays), patient history information

[1401] How it works: The user enters the required information into the input form displayed on the screen of their computer or tablet and clicks the button to upload the image data.

[1402] Output: Digital medical image data and patient history information are stored on the terminal.

[1403] Step 2:

[1404] The terminal uploads medical image data and patient medical history information to a cloud server.

[1405] Input: Digital medical image data and patient history information entered in step 1

[1406] How it works: The device encrypts input data and sends it securely to the cloud server using the HTTPS protocol.

[1407] Output: The encrypted data is uploaded to the cloud server.

[1408] Step 3:

[1409] The server analyzes and preprocesses the uploaded data.

[1410] Input: Encrypted and uploaded medical image data and patient history information

[1411] How it works: The server decrypts the data, preprocesses the images (e.g., normalizes, resizes), and extracts features from the medical images using deep learning models (e.g., TensorFlow, PyTorch).

[1412] Output: Preprocessed image data and extracted features

[1413] Step 4:

[1414] The server uses the generated AI model to search for similar cases.

[1415] Input: Features extracted in step 3

[1416] Operation: The server searches for similar cases in a medical image database using a similarity search algorithm such as K-Nearest Neighbors.

[1417] Output: A list of the most similar cases and their corresponding features

[1418] Step 5:

[1419] The server generates a suspected disease name based on similar cases.

[1420] Input: List of similar cases obtained in step 4 and feature values

[1421] How it works: The server uses a generative AI model to generate suspected disease names from similar cases.

[1422] Output: Generated suspected disease name

[1423] Step 6:

[1424] The server generates a suspected disease name and uses the patient's medical history information to search a medical knowledge database.

[1425] Input: Generated suspected disease name, patient medical history information

[1426] Operation: The server uses NLP techniques to search a medical knowledge database and extract relevant diagnostic information and treatment options.

[1427] Output: Diagnostic information and remedial actions

[1428] Step 7:

[1429] The device displays diagnostic and remediation information.

[1430] Input: Diagnostic information and remedial action taken in step 6

[1431] Operation: The device generates a report in PDF or HTML format containing diagnostic results and countermeasures, and displays it through the user interface.

[1432] Output: Diagnostic report displayed to the user

[1433] (Application example 1)

[1434] 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."

[1435] Maintaining normal operation of industrial equipment requires early detection of abnormalities and appropriate maintenance. However, it is difficult for engineers without specialized knowledge to quickly and accurately detect abnormalities and take appropriate countermeasures. Conventional methods take time to diagnose abnormalities and provide countermeasures, which can lead to reduced production efficiency and increased maintenance costs. The present invention aims to solve these problems and provide a system that supports optimal operation and maintenance of industrial equipment.

[1436] 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.

[1437] In this invention, the server includes a means for inputting the operation data of the industrial equipment, a means for inputting the maintenance history of the industrial equipment, and a means for uploading the operation data and the maintenance history to the database, which enables even an engineer without specialized knowledge to quickly and accurately detect an abnormality and provide an appropriate countermeasure.

[1438] "Industrial equipment" means machinery and equipment used in the manufacturing process.

[1439] "Operation data" refers to data that indicates information about the operating status and operating state of industrial equipment.

[1440] "Maintenance history" refers to a record of past maintenance work and repairs performed on industrial equipment.

[1441] A "database" is a system for storing large amounts of data in an organized manner and facilitating search and access.

[1442] "Similar cases" are cases similar to the operating conditions and maintenance history of industrial equipment stored in the past database.

[1443] A "suspected abnormality" is a condition that is predicted to indicate a potential problem with industrial equipment based on operational data and maintenance history.

[1444] The "maintenance knowledge database" is a database that stores information collected from technical documents and papers related to the maintenance of industrial equipment.

[1445] "Diagnosis" is the process of assessing the condition of industrial equipment and identifying potential problems.

[1446] "Countermeasures" are specific measures recommended to solve problems in industrial equipment based on the diagnosis results.

[1447] "Generative AI" is a type of artificial intelligence technology and a machine learning model for data analysis and predictive modeling.

[1448] To implement the invention, it is necessary to build a system that utilizes the operational data and maintenance history of industrial equipment. This system is realized using the following hardware and software.

[1449] Hardware used

[1450] 1. Server: A central processing unit that analyzes and stores data.

[1451] 2. Terminal: A device such as a computer, tablet, or smartphone that allows technicians to input and view data.

[1452] Software used

[1453] 1. Data format: JSON format

[1454] 2. AI libraries: TensorFlow or PyTorch (used to build generative AI models)

[1455] 3. Communication method: HTTPS protocol

[1456] System configuration and operation

[1457] Data Entry and Upload

[1458] Technicians input the operational data and maintenance history of industrial equipment into a terminal, which then captures the data in digital format. The terminal then packages the data and uploads it to a server using secure communications.

[1459] Feature Extraction and Search

[1460] The server analyzes the received operational data and maintenance history and uses generative AI to extract features from these data. It then searches the database for the most similar cases, allowing it to compare past data with new data.

[1461] Anomaly generation and database search

[1462] The server generates a suspected anomaly based on the most similar cases, and uses this suspected anomaly and the maintenance history as a query to search a maintenance knowledge database, from which relevant diagnostic information and countermeasures are extracted.

[1463] Report Generation and Viewing

[1464] The server generates a report containing the diagnosis and countermeasures. This report, which includes suspected abnormalities, findings, maintenance knowledge, and countermeasures, is sent to the terminal. Technicians can use this report to make quick and accurate maintenance decisions.

[1465] Specific examples

[1466] When a technician inputs data to detect abnormalities in the robot, the data is sent to a server, where the generative AI detects the abnormality, compares it with the most similar past data, and provides appropriate maintenance methods.

[1467] Prompt Sentence Examples

[1468] "The robot's operating data and maintenance history have been entered as follows:

[1469] Operational data: {sensor_data}

[1470] Maintenance history: {maintenance_history}

[1471] Based on this, generate a diagnosis of the anomaly and provide appropriate remedial action."

[1472] As described above, this system enables even engineers without specialized knowledge to quickly and accurately detect abnormalities and provide appropriate countermeasures, thereby improving factory production efficiency and reducing maintenance costs.

[1473] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1474] Step 1:

[1475] The user inputs the operation data and maintenance history of industrial equipment into the terminal. This input includes operating status data obtained from sensors and past maintenance records. This allows the terminal to collect digital data. To process the input data, the operation data is converted into JSON format, and the maintenance history is also converted into the same format.

[1476] Step 2:

[1477] The device packages the operation data and maintenance history and uploads them to the server using a secure communication method (HTTPS protocol). The data packaging involves combining various data fields and adding metadata. The packaged data is sent to the server in JSON format.

[1478] Step 3:

[1479] The server analyzes the received operational data and maintenance history. This involves using a generative AI model to extract features from the data. Specifically, the model, trained using TensorFlow or PyTorch, identifies important features from the input data (for example, vibration patterns or temperature fluctuations). The output is stored as a feature vector.

[1480] Step 4:

[1481] The server uses the extracted feature vector to search for similar cases in the database. Here, it matches past operation data and maintenance history with similar features to find the most similar entry. The search algorithm used is, for example, cosine similarity, and calculates the similarity to output a list of similar cases.

[1482] Step 5:

[1483] The server generates suspected anomalies based on the most similar cases. A generative AI model is used to generate predictions about abnormal conditions based on new feature vectors and past cases. The output is a number of suspected anomalies and their probabilities.

[1484] Step 6:

[1485] The server uses the suspected anomaly and maintenance history as a query to search a maintenance knowledge database. This search extracts relevant diagnostic information and countermeasures. The knowledge database contains technical documentation and past maintenance cases, and provides a list of countermeasures.

[1486] Step 7:

[1487] The server generates a diagnostic and actionable report, which includes suspected anomalies, findings, and recommended actions. The report is generated in JSON format and sent to the device.

[1488] Step 8:

[1489] The terminal displays the received report to the technician, allowing the technician to quickly and accurately detect anomalies and implement appropriate countermeasures. UI components are generally used for display, making the report contents visually easy to understand.

[1490] 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.

[1491] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[1492] System configuration and operation

[1493] System configuration

[1494] 1. Terminal

[1495] A device for users (doctors) to input medical image data and patient history information.

[1496] Examples include computers, tablets, and smartphones.

[1497] It has a built-in emotion engine and is equipped with a camera and microphone to analyze the user's facial expressions, voice, and gestures.

[1498] 2. Server

[1499] A central processing unit that receives and analyzes medical images and medical history information uploaded from the terminal.

[1500] Generative AI is used to search and analyze the database.

[1501] 3. Database

[1502] Medical image database: A database that stores medical image data and corresponding medical history information.

[1503] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[1504] 4. Emotion Engine

[1505] Software that analyzes a user's facial expressions, voice, and gestures to recognize emotions.

[1506] It has the ability to adjust the system's response method based on the analysis results.

[1507] System Operation

[1508] Entering medical images and medical history information

[1509] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[1510] Uploading data

[1511] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[1512] Data analysis and exploration

[1513] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (e.g., abnormal areas, lesion location, shape, etc.). It then identifies similar past cases from the medical image database and compares them with the uploaded medical history information.

[1514] Generation of suspected disease names

[1515] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data from an emotion engine.

[1516] Providing diagnostics and solutions

[1517] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[1518] Providing reports

[1519] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1520] Specific examples

[1521] Suspected acute stroke

[1522] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[1523] 2. The terminal uploads the entered data to the server.

[1524] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[1525] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[1526] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[1527] Diagnosis of pneumonia

[1528] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[1529] 2. The device uploads the data to the server.

[1530] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases that are highly suspected of being pneumonia.

[1531] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[1532] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[1533] The system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Its emotion engine recognizes the user's emotional state and adjusts its response accordingly, reducing the burden on doctors and enabling more effective support.

[1534] The processing flow will be explained below.

[1535] Step 1:

[1536] The user (doctor) acquires a patient's medical images (e.g., CT scans, X-ray images) and inputs the patient's corresponding medical history information into the terminal. The terminal saves the medical image data as an image file and the medical history information in text format.

[1537] Step 2:

[1538] The device packages the acquired medical image data and medical history information and uploads them to a server via a secure communication protocol. The data is encrypted during the upload process. An emotion engine also analyzes the user's facial expressions and voice to generate emotion data.

[1539] Step 3:

[1540] The server receives the uploaded medical image data and medical history information and begins analysis using generative AI. First, it extracts features from the medical image (abnormal areas, lesion location, shape, etc.).

[1541] Step 4:

[1542] The server searches a medical image database based on the extracted features to identify the most similar past cases, and simultaneously compares the uploaded medical history information with the case information in the database to obtain a more accurate similarity score.

[1543] Step 5:

[1544] The server generates suspected disease names based on similar cases. This process includes disease names estimated from past cases using generative AI, and also takes into account the user's emotional data using an emotion engine.

[1545] Step 6:

[1546] The server uses the generated suspected disease name and medical history information as a query to search a medical knowledge database, which stores relevant diagnostic information and treatments.

[1547] Step 7:

[1548] The server generates a detailed report containing the diagnosis and treatment plan based on the information retrieved from the medical knowledge database. The report includes the suspected disease, detected features, and recommended treatment. The presentation and content of the report are adjusted according to the user's emotional state.

[1549] Step 8:

[1550] The server then sends the generated report to the terminal, which transmits the report securely in digital format.

[1551] Step 9:

[1552] The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1553] This specific processing enables even non-specialist doctors to quickly and accurately evaluate medical images and make diagnoses. The emotion engine provides flexible support according to the user's emotional state, improving the user experience.

[1554] Example 2

[1555] 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."

[1556] In modern medicine, even physicians without specialized expertise are required to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. However, achieving this is not easy due to the breadth of medical knowledge and the complexity of diagnoses. Another issue is that the physician's emotional state can affect the efficiency and accuracy of diagnostic work. To solve these problems, a diagnostic support system is needed that can efficiently and accurately analyze medical image data and patient medical history information, and that also takes the user's emotional state into account.

[1557] 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.

[1558] In this invention, the server includes a means for inputting medical image data, a means for inputting patient medical history information, a means for uploading the medical image data and the patient medical history information to a database, a means for searching the database for similar cases, a means for generating a suspected disease name based on the similar cases, a means for searching a comprehensive medical knowledge database using the suspected disease name and the patient's medical history information, a means for obtaining a diagnosis and countermeasures from the medical knowledge database, a means for providing the diagnosis and countermeasures, a means for recognizing a user's emotional state, and a means for adjusting a response method based on the user's emotional state. This enables doctors to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. Furthermore, by recognizing a user's emotional state and adjusting a response method accordingly, the efficiency and accuracy of diagnostic work can be improved.

[1559] "Medical image data" is data that visually records the state of the inside of the human body, obtained using medical equipment such as radiation or ultrasound.

[1560] "Patient medical history information" is a record of a patient's past diagnoses, treatments, and surgeries, as well as detailed information about their current symptoms and medical history.

[1561] A "database" is a collection of information that is systematically organized to efficiently store, retrieve, and manipulate specific information.

[1562] A "similar case" is a case from previously recorded medical information that is similar to the symptoms and medical image data of a current patient.

[1563] The "suspected disease name" is a disease name that is highly likely to be estimated based on medical image data and the patient's medical history information.

[1564] A "medical knowledge database" is a collection of diagnostic and treatment knowledge extracted from medical treatises, medical books, and other reliable medical sources.

[1565] "Diagnosis and countermeasures" refers to the diagnosis results generated based on medical image data and medical history information, as well as the recommended treatment and testing methods.

[1566] The "user's emotional state" is an emotional state based on the user's facial expressions, voice, gestures, etc., recognized through input devices such as a camera or microphone.

[1567] "Adjusting the response method" refers to a method for providing more appropriate support by changing the method and content of information presentation depending on the user's emotional state.

[1568] This invention combines a system that analyzes medical image data and patient medical history information to provide appropriate diagnoses and treatments with an emotion engine that recognizes the user's emotions. This system is designed to enable even non-specialist physicians to quickly and accurately evaluate medical images and provide appropriate diagnoses and treatments. The emotion engine also recognizes the user's emotional state and adjusts the interface and information delivery method accordingly, providing more effective support.

[1569] System configuration

[1570] 1. Terminal

[1571] A device that allows users (doctors) to input medical image data and patient history information. Examples include PCs, tablets, and smartphones. The device is equipped with a camera and microphone, and an emotion engine analyzes the user's facial expressions, voice, and gestures. Specific examples include using tools such as Microsoft Azure Face API and Google Cloud Speech-to-Text.

[1572] 2. Server

[1573] A central processing unit that receives and analyzes medical images and medical history information uploaded from devices. It searches and analyzes the database using generative AI models (e.g., OpenAI's GPT series). Specifically, it uses medical image analysis software (e.g., Google DeepMind's AlphaFold).

[1574] 3. Database

[1575] Medical image database: A database that stores medical image data and corresponding medical history information.

[1576] Medical knowledge database: A database that stores knowledge extracted from medical papers and medical books.

[1577] 4. Emotion Engine

[1578] Software that recognizes emotions by analyzing the user's facial expressions, voice, and gestures, and has the ability to adjust the system's response method based on the analysis results.

[1579] System Operation

[1580] This system analyzes medical image data and patient medical history information using the following procedure to provide an appropriate diagnosis and treatment.

[1581] 1. Entering medical images and medical history information

[1582] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. During this input process, the emotion engine analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[1583] 2. Uploading data

[1584] The device packages the medical image data and medical history information and uploads them to the server using a secure communication method (e.g., HTTPS), including the emotion data obtained from the emotion engine.

[1585] 3. Data analysis and retrieval

[1586] The server receives the uploaded medical images and medical history information and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, medical image analysis software is used to extract features from the images (e.g., abnormal areas, lesion location, shape, etc.). Similar past cases are then identified from a medical image database and compared with the input medical history information.

[1587] 4. Generation of suspected disease names

[1588] The server generates suspected disease names based on similar cases, including disease names predicted using a generative AI model, and also takes into account the user's emotional data from an emotion engine.

[1589] 5. Providing diagnosis and solutions

[1590] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected illnesses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[1591] 6. Providing reports

[1592] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1593] Specific examples

[1594] Suspected acute stroke

[1595] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[1596] 2. The terminal uploads the entered data to the server.

[1597] 3. The server uses the generative AI model to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[1598] 4. Based on the results, the server generates a suspected disease name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that a prompt response is required.

[1599] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[1600] Prompt Sentence Examples

[1601] "Enter the CT scan and medical history information of a patient suspected of having an acute stroke. The system will recommend emergency treatment."

[1602] Diagnosis of pneumonia

[1603] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[1604] 2. The device uploads the data to the server.

[1605] 3. The server uses the generative AI model to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[1606] 4. The server generates a suspected disease name "pneumonia" and retrieves treatments and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[1607] 5. The terminal displays this information to the user (general practitioner) and supports appropriate treatment planning.

[1608] Prompt Sentence Examples

[1609] "Enter a chest x-ray and medical history of a patient with a fever and cough. We'll provide the information in an easy-to-understand format, taking into account the user's fatigue level."

[1610] This system supports doctors in quickly and accurately evaluating medical images and providing appropriate diagnoses and treatments. Furthermore, the emotion engine recognizes the user's emotional state and adjusts the response accordingly, reducing the burden on doctors and providing more effective support.

[1611] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1612] Step 1:

[1613] The user inputs medical image data and the patient's medical history information into the terminal. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions, voice, and gestures in real time. Specifically, the terminal receives CT images and X-ray images as medical image data and text data as medical history information. The emotion engine also uses AI-based facial recognition software and voice analysis tools. The input data are medical image files and text medical history information. The output data are medical image data, medical history information, and the user's emotional state data.

[1614] Step 2:

[1615] The terminal packages medical image data, medical history information, and emotion data and uploads them to the server using a secure communication method (e.g., HTTPS, SSL / TLS). The terminal converts this data into JSON format and sends it via a secure HTTP POST request. The input data is the packaged medical image data, medical history information, and emotion data. The output data is the securely uploaded packaged data.

[1616] Step 3:

[1617] The server receives the uploaded data and begins analysis using a generative AI model (e.g., OpenAI GPT-4). First, the server uses medical image analysis software to extract features from the image (e.g., abnormal areas, location and shape of lesions). A full-text search engine (e.g., Elasticsearch) is used to search for similar cases recorded in the past from a medical image database. The input data are medical image data and medical history information. The output data are feature data and a candidate list of similar cases.

[1618] Step 4:

[1619] The server generates a suspected disease name based on similar cases. The generative AI model estimates multiple diagnostic candidates and selects the most reliable one. The server also takes into account the user's emotional state obtained by the emotion engine. For example, if the user is in a hurry, the server will prioritize the most important information. The input data are feature data, similar case data, and emotion data. The output data is the suspected disease name.

[1620] Step 5:

[1621] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report. The report includes the suspected disease name, detected features, and recommended treatment. The format and presentation of the report are also adjusted depending on the user's emotional state. For example, if the user is tired, information is presented in an easy-to-understand bullet point format. The input data are the suspected disease name and the medical knowledge database. The output data is the generated report.

[1622] Step 6:

[1623] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor) and provides additional support as needed. The emotion engine analyzes the user's emotions even while the report is being displayed, and provides additional explanations and suggested measures in real time. As a specific example, a user who is feeling anxious is provided with more detailed explanations and visualized data. The input data is the generated report. The output data is the report displayed to the user and the content of additional support.

[1624] (Application example 2)

[1625] 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."

[1626] In the medical field, non-specialist physicians are required to make quick and accurate diagnoses, but the physician's emotions and stress can affect the diagnostic results. In particular, in telemedicine, more effective medical services are required by appropriately recognizing the emotions of the physician and patient and adjusting the diagnosis and treatment methods. The present invention aims to solve this problem and improve the accuracy and efficiency of diagnoses by providing an interface and information that reflects the user's emotional state.

[1627] 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.

[1628] In this invention, the server includes a means for inputting medical image data and patient medical history information, a means for uploading the data to a database, and a means for searching the database for similar cases, which makes it possible to recognize the user's emotions and adjust the interface and information presentation method based on the results.

[1629] "Medical image data" refers to image data taken for the purpose of diagnosing or treating a patient, and includes X-ray images, CT images, MRI images, etc.

[1630] "Patient medical history information" refers to detailed information about a patient's past health condition and illnesses, including medical records, medical history, allergy history, and so on.

[1631] A "database" is a collection of information that stores medical image data and patient medical history information and is used to search for similar cases.

[1632] "Similar cases" refers to past cases that have similar medical images and medical history information to those being analyzed, and are useful in providing diagnoses and countermeasures.

[1633] A "suspected disease name" is a possible diagnosis result generated based on medical image data and a patient's medical history information, and includes specific symptoms and disease names.

[1634] A "medical knowledge database" is a source of medical knowledge necessary for diagnosis and treatment, including information extracted from medical papers and medical books.

[1635] "Generative AI" is a system that uses artificial intelligence technology to analyze medical image data and medical history information, and is used to provide new diagnoses and countermeasures.

[1636] An "emotion engine" is software that analyzes a user's facial expressions, voice, and gestures to recognize their emotional state and adjusts the interface and the way information is presented.

[1637] An "interface" is a platform through which users interact with a system, adaptively adjusting based on emotion recognition.

[1638] System configuration

[1639] The present invention combines a system that analyzes medical image data and patient history information to provide diagnosis and treatment with an emotion engine that recognizes the user's emotions. The main components of the system include a terminal, a server, and a database. The emotion engine is used to analyze the user's emotional state in real time.

[1640] Terminal

[1641] Configuration: A device for doctors to input medical image data and patient medical history information. Specifically, it includes devices equipped with a camera and microphone, such as smartphones, smart glasses, and head-mounted displays, and has an emotion engine built in.

[1642] server

[1643] Configuration: A central processing unit that receives medical images and medical history information uploaded from the terminal and uses generative AI to search and analyze the database.

[1644] Database

[1645] Structure: The system consists of a medical image database and a medical knowledge database. The former stores medical image data and corresponding medical history information, while the latter stores knowledge extracted from medical papers and medical books.

[1646] Emotion Engine

[1647] Configuration: Software that analyzes the user's facial expressions, voice, and gestures to recognize emotions. It has the ability to adjust the system's response method based on the analysis results.

[1648] System Operation

[1649] Entering medical images and medical history information

[1650] The user (doctor) inputs medical image data and patient history information acquired during consultation into the terminal. The emotion engine analyzes the user's facial expressions and voice during this input process and recognizes their emotional state in real time.

[1651] Uploading data

[1652] The device packages the medical image data and medical history information and uploads them to the server using secure communication means, including the emotion data from the emotion engine.

[1653] Data analysis and exploration

[1654] The server receives the uploaded medical images and medical history information and begins analysis using generative AI. First, it extracts features from the medical images (such as abnormal areas and the location and shape of lesions). It then identifies similar cases from the medical image database and compares them with the uploaded medical history information.

[1655] Generation of suspected disease names

[1656] The server generates suspected disease names based on similar cases, including disease names predicted using generative AI, and also takes into account the user's emotional data generated by the emotion engine.

[1657] Providing diagnostics and solutions

[1658] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database and generates a detailed report, including suspected diagnoses, detected features, and recommended treatments. The presentation and content of the report are adjusted according to the user's emotional state.

[1659] Providing reports

[1660] The server sends the generated report to the terminal, which then displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests countermeasures as necessary.

[1661] Specific examples

[1662] Suspected acute stroke

[1663] 1. The user (emergency physician) acquires a CT image of a patient suspected of acute stroke and inputs the image data and the patient's medical history information into the terminal. The emotion engine recognizes the user's state of tension.

[1664] 2. The device uploads the entered data to the server.

[1665] 3. The server uses generative AI to search for similar cases in a medical image database, and as a result, finds cases that are highly suspected to be acute stroke.

[1666] 4. Based on the results, the server generates a suspected illness name of "acute stroke" and retrieves countermeasures from the medical knowledge database. The emotion engine takes into account the user's state of tension and notifies them that immediate action is required.

[1667] 5. The terminal displays a report containing the diagnosis and countermeasures to the user (emergency physician), helping them make quick treatment decisions.

[1668] Diagnosis of pneumonia

[1669] 1. The user (general practitioner) obtains a chest X-ray image of a patient complaining of fever and cough, and inputs the image data and medical history information into the terminal. The emotion engine recognizes the user's fatigue state.

[1670] 2. The device uploads the data to the server.

[1671] 3. The server uses generative AI to search for similar cases in a medical image database and identify cases with a high probability of pneumonia.

[1672] 4. The server generates a suspected disease name "pneumonia" and retrieves treatment and recommended tests from the medical knowledge database. The emotion engine takes into account the user's fatigue state and provides information in an easy-to-understand format.

[1673] 5. The device displays this information to the user (general practitioner) and supports appropriate treatment planning.

[1674] Prompt Sentence Examples

[1675] "Upload a medical image (e.g., CT scan)

[1676] Please provide your diagnosis and suggest a course of action."

[1677] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1678] Step 1:

[1679] The user (doctor) inputs medical image data and the patient's medical history information acquired during the consultation into the terminal. This input includes, for example, CT images and X-ray images, as well as information about the patient's medical history and current symptoms. The terminal is equipped with a camera and microphone, and the emotion engine analyzes the user's facial expressions and voice in real time. The emotion engine collects the input data and the user's facial and vocal characteristics to recognize the user's emotional state.

[1680] Step 2:

[1681] The terminal packages medical image data and patient history information and uploads them to a server using secure communication methods. At this time, the emotional data analyzed by the emotion engine is also included in the package. The terminal inputs medical image data, medical history information, and the user's emotional data, and outputs a package containing this information.

[1682] Step 3:

[1683] The server receives medical image data and patient medical history information uploaded from the device. This data is preprocessed and input into the generative AI model. The server analyzes the data and extracts features (such as abnormal areas and the location and shape of lesions) from the medical images. The input data are medical images and medical history information, and the output is the feature extraction results.

[1684] Step 4:

[1685] The server searches for similar cases in a medical image database and compares them with the uploaded medical history information. The generative AI model identifies similar cases from past cases in the database based on the features. The input data are the features and medical history information, and the output is a list of similar cases.

[1686] Step 5:

[1687] The server generates a suspected disease name based on similar cases. It uses a generative AI model to estimate the most appropriate disease name and outputs this name. The input data is a list of similar cases, and the output is a suspected disease name. It also takes into account the user's emotional data from an emotion engine.

[1688] Step 6:

[1689] The server retrieves relevant diagnostic information and countermeasures from a medical knowledge database. Based on the suspected disease name and the patient's medical history, it uses a generative AI to search for appropriate diagnostic information and countermeasures. The input data is the suspected disease name and medical history information, and the output is diagnostic information and countermeasures.

[1690] Step 7:

[1691] The server generates a detailed report, including suspected diagnosis, detected features, and recommended treatment. The emotion engine adjusts the presentation and content of the report according to the user's emotional state. The input data are diagnostic information and countermeasures, and the output is the generated report.

[1692] Step 8:

[1693] The server sends the generated report to the terminal. The terminal displays the received report to the user (doctor). The emotion engine analyzes the user's emotions while the report is being displayed, and provides additional information and suggests measures as needed. The input data is the generated report, and the output is the report and additional explanations presented to the user.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] 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).

[1701] 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.

[1702] 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."

[1703] 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.

[1704] 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).

[1705] 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.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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.

[1714] 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.

[1715] The following is further disclosed regarding the above embodiment.

[1716] (Claim 1)

[1717] a means for inputting medical image data;

[1718] a means for inputting patient medical history information;

[1719] means for uploading said medical image data and said patient's medical history information to a database;

[1720] a means for searching for similar cases from the database;

[1721] a means for generating a suspected disease name based on the similar cases;

[1722] means for searching a comprehensive medical knowledge database using the suspected disease name and patient medical history information;

[1723] means for obtaining a diagnosis and a course of action from said medical knowledge database;

[1724] A system including means for providing said diagnosis and remedial action.

[1725] (Claim 2)

[1726] 10. The system of claim 1, wherein the medical knowledge database includes information extracted from medical papers and books.

[1727] (Claim 3)

[1728] The system according to claim 1, wherein the means for searching for similar cases and the means for generating suspected disease names use a generation AI.

[1729] "Example 1"

[1730] (Claim 1)

[1731] a means for inputting medical images;

[1732] a means for inputting a patient's medical history;

[1733] means for uploading the medical images and the patient's medical history to a cloud server;

[1734] means for performing pre-processing on the cloud server;

[1735] a means for searching a database for similar cases from the cloud server and extracting features;

[1736] A means for using a generative AI model to generate a suspected disease name based on the similar cases;

[1737] a means for searching a medical knowledge database using the generated suspected disease name and the patient's medical history;

[1738] means for retrieving diagnostic and treatment information from said medical knowledge database;

[1739] A system including means for displaying said obtained diagnostic and treatment information.

[1740] (Claim 2)

[1741] 10. The system of claim 1, wherein the medical knowledge database includes information extracted from medical papers and books.

[1742] (Claim 3)

[1743] The system according to claim 1, wherein the means for searching for similar cases and the means for generating a suspected disease name use a generative AI model.

[1744] "Application Example 1"

[1745] (Claim 1)

[1746] means for inputting operational data of the industrial equipment;

[1747] a means for inputting the maintenance history of the industrial equipment;

[1748] means for uploading the operational data and the maintenance history to a database;

[1749] a means for searching for similar cases from the database;

[1750] means for generating suspected abnormalities based on the similar cases;

[1751] means for searching a comprehensive maintenance knowledge database using the suspected anomaly and maintenance history;

[1752] means for obtaining a diagnosis and a countermeasure from the maintenance knowledge database;

[1753] A system including means for providing said diagnosis and remedial action.

[1754] (Claim 2)

[1755] 10. The system of claim 1, wherein the maintenance knowledge database includes information extracted from technical documents and papers.

[1756] (Claim 3)

[1757] The system according to claim 1, wherein the means for searching for similar cases and the means for generating suspected abnormalities use a generation AI.

[1758] "Example 2: Combining Emotion Engines"

[1759] (Claim 1)

[1760] a means for inputting medical image data;

[1761] a means for inputting patient medical history information;

[1762] means for uploading said medical image data and said patient's medical history information to a database;

[1763] a means for searching for similar cases from the database;

[1764] a means for generating a suspected disease name based on the similar cases;

[1765] means for searching a comprehensive medical knowledge database using the suspected disease name and patient medical history information;

[1766] means for obtaining a diagnosis and a course of action from said medical knowledge database;

[1767] means for providing said diagnosis and remedial action;

[1768] means for recognizing the emotional state of a user;

[1769] The system includes means for adjusting a response method based on said emotional state.

[1770] (Claim 2)

[1771] 10. The system of claim 1, wherein the medical knowledge database includes information extracted from medical papers and books.

[1772] (Claim 3)

[1773] The system according to claim 1, wherein the means for searching for similar cases and the means for generating suspected disease names use a generation AI.

[1774] "Application example 2 when combining emotion engines"

[1775] (Claim 1)

[1776] a means for inputting medical image data;

[1777] a means for inputting patient medical history information;

[1778] means for uploading said medical image data and said patient's medical history information to a database;

[1779] a means for searching for similar cases from the database;

[1780] a means for generating a suspected disease name based on the similar cases;

[1781] means for searching a comprehensive medical knowledge database using the suspected disease name and patient medical history information;

[1782] means for obtaining a diagnosis and a course of action from said medical knowledge database;

[1783] means for providing said diagnosis and remedial action;

[1784] A means for using a generative AI to search and analyze the database;

[1785] means for recognizing a user's emotion;

[1786] The system includes means for adjusting an interface or a method of providing information based on the results of the emotion recognition.

[1787] (Claim 2)

[1788] 10. The system of claim 1, wherein the medical knowledge database includes information extracted from medical papers and books.

[1789] (Claim 3)

[1790] 10. The system of claim 1, wherein the emotion engine that implements the emotion recognition uses software that analyzes a user's facial expressions, voice, and gestures. [Explanation of symbols]

[1791] 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. a means for inputting medical image data; a means for inputting patient medical history information; means for uploading said medical image data and said patient's medical history information to a database; a means for searching for similar cases from the database; a means for generating a suspected disease name based on the similar cases; means for searching a comprehensive medical knowledge database using the suspected disease name and patient medical history information; means for obtaining a diagnosis and a course of action from said medical knowledge database; A system including means for providing said diagnosis and remedial action.

2. 10. The system of claim 1, wherein the medical knowledge database includes information extracted from medical papers and medical books.

3. The system according to claim 1 , wherein the means for searching for similar cases and the means for generating suspected disease names use a generation AI.

Images