system

Abstract

We provide the system. [Solution] A means for receiving and pre-processing microscope images, A means for analyzing pre-processed images and detecting abnormal areas, A means of generating diagnostic results by comparing them with a database of past cases, A means of proposing appropriate treatment methods by referring to medical guidelines, A method for creating a report using natural language generation technology, A means of providing feedback to train an AI model, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern medical fields, pathologists need to analyze a large number of microscopic images and medical data, which takes time for diagnosis and requires improvement in diagnostic accuracy. In addition, there is a lack of specialized diagnostic support in regions with insufficient medical resources. It is required to solve these problems and provide high-precision and rapid pathological diagnosis.

Means for Solving the Problems

[0005] This invention provides means for receiving and pre-processing microscope images, and means for analyzing pre-processed images to detect abnormal areas. Furthermore, it includes means for generating diagnostic results by comparing them with a database of past cases, and means for proposing the optimal treatment method by referring to medical guidelines. It also includes means for generating reports using natural language generation technology and has a feedback function for continuously training an AI model. This enables highly accurate and efficient diagnostic support, significantly reducing the burden on medical professionals.

[0006] A "microscopic image" is an image obtained using a microscope that contains detailed visual information about living tissues and cells.

[0007] "Preprocessing" refers to initial processing such as noise reduction and resolution adjustment to convert image data into a format that is easy to analyze.

[0008] "Analysis" is the process of performing pattern recognition and anomaly detection on data to extract useful information.

[0009] An "abnormal area" refers to a region that deviates from normal biological structure and is a part that may be diseased or abnormal.

[0010] A "case database" is a digital archive that collects past medical diagnosis results and patient information.

[0011] "Medical guidelines" are documents or guidelines that define standard diagnostic and treatment procedures in the medical field.

[0012] "Natural language generation" is a technology that uses computer algorithms to generate text in human natural language.

[0013] "Feedback" is the process of evaluating the results of a system's execution and using that information for improvement and learning in the future.

[0014] An "AI model" is a set of algorithms designed to perform specific tasks using artificial intelligence technology. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is implemented as an AI-based system to support pathological diagnosis in medical settings. This system allows for highly accurate detection of abnormal areas by having a server receive medical data, such as microscope images, perform preprocessing, and then having an AI agent analyze the data. This process helps medical professionals make rapid and accurate diagnoses.

[0037] The server compares the analyzed image data with an existing case database to generate a diagnosis. This provides an objective diagnosis based on similar past cases. The server also refers to the latest medical guidelines to suggest the most appropriate treatment for the patient. This information is compiled into a report using natural language generation technology and delivered to the user or device.

[0038] As a concrete example, consider a scenario where a CT scan image of a patient suspected of having lung cancer is sent to a server. The server analyzes this image to identify the location and size of the tumor within the lung. Next, based on past case data, it diagnoses the lesion as small cell lung cancer. Based on these results, a chemotherapy plan in accordance with the latest treatment guidelines is proposed. The report is generated in natural language and provided in a format that allows physicians to discuss the detailed treatment plan with the patient.

[0039] The server updates the AI ​​model based on continuous feedback, improving the accuracy of medical image analysis. This information is accessible on the user's terminal, contributing to the efficiency of medical treatment. In this way, the present invention enables the optimization of medical processes and realizes a form that dramatically improves the accuracy and efficiency of pathological diagnosis.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server automatically reads microscope images and CT scan images received from medical institutions. After receiving the images, it performs preprocessing to remove noise and convert them into a format that is easy for AI to analyze.

[0043] Step 2:

[0044] The server's AI agent performs abnormal area detection based on the pre-processed images. Using a deep learning algorithm, it identifies potentially diseased areas at the pixel level and visually highlights them.

[0045] Step 3:

[0046] The server compares the detected abnormal area information with an existing case database. It references past similar case data and applies a statistical model to generate a diagnosis.

[0047] Step 4:

[0048] The system uses the diagnostic results generated by the server to automatically suggest appropriate treatment methods based on medical guidelines. The suggested treatments are customized according to the patient's individual health condition.

[0049] Step 5:

[0050] The server integrates the diagnostic results and suggested treatments, and generates a detailed report using natural language generation technology. This report includes the location of any lesions found and recommended treatment options.

[0051] Step 6:

[0052] The server sends the generated report to the terminal. As a result, the user, a medical professional, can review the diagnostic results and obtain the information needed to develop the best treatment plan for the patient.

[0053] Step 7:

[0054] The server leverages a feedback loop to supply new diagnostic results and treatment outcomes to the AI ​​model, continuously improving the accuracy of the algorithm.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In medical settings, rapid and accurate pathological diagnosis is crucial, but image data noise and complex diagnostic processes can be obstacles. Furthermore, there is a need for objective diagnoses based on comparisons with past cases and for treatment methods based on the latest medical standards. Additionally, there is a need for a method to provide generated diagnostic results in natural language reports, allowing users to efficiently utilize the information.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for receiving and pre-processing image information, means for analyzing the pre-processed image information and detecting abnormal elements, means for comparing it with a database of past cases and generating analysis results, means for proposing appropriate treatment methods by referring to medical standards, means for creating reports using natural language generation technology, means for conducting evaluations to update the learning model, and means for displaying processing progress and notifying information. This enables rapid and objective diagnosis and proposal of treatment methods, and allows medical professionals to make appropriate decisions by utilizing the generated information.

[0060] "Image information" refers to visual data acquired for use in medical or scientific analysis, including microscopic images and CT scan images.

[0061] "Preprocessing" refers to the process of adjusting data to a state suitable for analysis, and includes steps such as noise reduction and standardization.

[0062] "Abnormal elements" refer to characteristics of cells or tissues that deviate from a normal state, and are the parts that are subject to pathological diagnosis.

[0063] A "case database" is a source of information that collects data on past medical cases and patient data, and is used for matching and analyzing diagnostic results.

[0064] "Medical standards" refer to guidelines and protocols for diagnosis and treatment, and serve as the criteria for applying the treatment methods provided to patients.

[0065] "Natural language generation technology" is a technology that allows computers to represent information using human language, and is used for creating reports and explanatory texts.

[0066] A "learning model" is a computational model that learns patterns from data using machine learning algorithms, and its purpose is to improve the accuracy of analysis.

[0067] "Means for displaying progress and notifying information" refers to interfaces and functions for communicating the current progress and results of data processing to the user.

[0068] This invention relates to a system for supporting diagnosis in the medical field. Specific embodiments thereof are described below.

[0069] The server receives image information from medical institutions, such as microscope images and CT scan images. This image information is crucial for accurate diagnosis, and the server first performs data preprocessing. At this stage, noise is removed from the images, and contrast and brightness are adjusted to appropriate levels. The preprocessed data is then analyzed by an AI agent using a general-purpose machine learning framework such as TENSORFLOW®, which runs on common hardware. The analysis identifies abnormal elements, which are then used to efficiently aid in diagnosis.

[0070] Subsequently, the server accesses an SQL database built to compare the analysis results with a case database. In this process, the server reinforces the diagnosis based on past case information, supporting objective decision-making. Once the comparison is complete, the server proposes the optimal treatment method based on medical guidelines. This information is compiled into a report using natural language generation technology and delivered to the terminal. The user can then easily use this to explain the situation to the patient.

[0071] As a concrete example, consider a case where an image of a patient with lung abnormalities is sent to the server. The server analyzes the image and detects the shape and location of the abnormal shadow. Next, by comparing this with a case database, it diagnoses the possibility of small cell lung cancer and proposes appropriate chemotherapy. This information is generated as a natural language report and provided to the user.

[0072] An example of a prompt for a generative AI model is: "Analyze the patient's lung CT scan, describe the tumor details, and generate a report suggesting the best treatment options."

[0073] As described above, this system supports the efficiency and accuracy of diagnosis in medical settings, helping healthcare professionals make objective and rapid decisions.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server receives image information transmitted from medical institutions. Input includes microscope images and CT scan images, which the server stores in its data storage. Next, it removes noise from the received raw data and standardizes the image contrast and brightness. This prepares the data for easier image analysis. The output is pre-processed image information.

[0077] Step 2:

[0078] The server passes pre-processed image information to the AI ​​agent. The input here is the pre-processed image, which is analyzed by a neural network using TensorFlow. The server analyzes each pixel and identifies abnormal elements. This process calculates the location and size of the abnormal areas. The output is the analysis result with the abnormal areas identified.

[0079] Step 3:

[0080] The server uses the analysis results as queries to access the case database. The input includes data that is considered characteristic information of the abnormal elements, and the server compares it with past case information stored in the SQL database. This searches for similar past cases and retrieves information to reinforce the diagnosis. The output is diagnostic information compared with past cases.

[0081] Step 4:

[0082] The server consults a medical guideline database based on the diagnostic information obtained through matching. The input includes diagnostic information, and the server performs calculations to propose the most suitable treatment method based on the corresponding guidelines. As a result, a list of candidate treatment methods deemed medically appropriate is generated. The output is information on the proposed treatment methods.

[0083] Step 5:

[0084] The server integrates the generated diagnostic information and treatment methods, and creates a report using natural language generation technology. The input consists of diagnostic information and suggested treatment methods, which the server uses to create a natural language report based on a generative AI model such as GPT-3(registered trademark). The output is a report presented in a format that is easy for users and healthcare professionals to understand.

[0085] Step 6:

[0086] The terminal receives the provided report and notifies the user. The input here is the generated report, which the terminal visualizes and displays. The user reviews the report and uses the diagnostic results and treatment methods to make decisions in the medical setting. The output is the detailed diagnostic report actually displayed on the screen.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] In nursing care settings, efficiently managing residents' health and promptly proposing appropriate treatments is often challenging. There is a need for support systems that enable even care staff without medical expertise to perform highly accurate health management. To address this, a system is needed that can accurately identify abnormalities and quickly propose treatments based on past cases and medical guidelines.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for acquiring microscopic images and performing data preprocessing, means for analyzing the preprocessed images and identifying abnormal areas, means for outputting diagnostic results by comparing them with a case database, means for proposing appropriate treatment methods based on medical guidelines, and means for providing the analysis results as a health management plan according to the care setting. This enables the rapid provision of highly accurate health checkup results and the automatic proposal of individual medical plans for residents, even in care facilities.

[0092] A "microscope image" is image data showing fine structures, captured using an optical microscope or an electron microscope.

[0093] "Data preprocessing" is the process of removing noise and adjusting contrast in image data in order to improve the accuracy of the analysis.

[0094] An "abnormal area" is a region that exhibits different characteristics or structures compared to standard pathological tissue, suggesting the presence of a potential disease or lesion.

[0095] A "case database" is a dataset containing past similar diagnostic results and subsequent progress information, serving as a useful source of information for diagnosis and treatment selection.

[0096] "Medical guidelines" are guidelines that outline standard diagnostic methods and treatment strategies for specific diseases or cases, formulated based on the latest medical research and expert consensus.

[0097] "Analysis results" refer to detailed information about abnormal areas derived from the analysis of image data, and are used for diagnosis and treatment decisions.

[0098] A "health management plan" is a specific action plan proposed to maintain or improve the health status of a patient or resident, based on analysis results and diagnoses.

[0099] To realize this invention, it is necessary to build a system specifically designed for health management in nursing care facilities. This system will function through the coordinated operation of a server, mobile terminals, and users.

[0100] The server first receives microscope images and performs preprocessing for analysis. This preprocessing includes denoising and contrast adjustment of the images. The preprocessed images are then analyzed by an AI model implementing deep learning to identify anomalies. This AI model is typically built using software such as TensorFlow or PyTorch.

[0101] The analysis results are compared with a case database, and a diagnosis is automatically generated. This information, combined with medical guidelines, allows for the suggestion of the most suitable treatment for the patient. The suggested treatment is then compiled into a report in natural language using a generative AI model and sent to the user's mobile device. This enables care staff and medical professionals to use this information to propose specific health management plans for residents.

[0102] As a concrete example, when image data of a resident is sent to the server, the server automatically analyzes this image data and generates a health management plan based on the results. The generated plan is created based on a prompt that reads, "Analyze the health check data of the following patient and generate a health management plan in natural language, comparing it with past cases." By following this prompt and using advanced natural language generation technology, an easily interpretable report is created, enabling efficient health management in nursing facilities.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server receives microscope image data transmitted from nursing care facilities. Using this received data as input, it performs image noise reduction and contrast adjustment to output image data suitable for analysis. This enables highly accurate identification of abnormal areas.

[0106] Step 2:

[0107] The server inputs pre-processed image data into a deep learning model to identify anomalies. During this process, an AI model built using TensorFlow or PyTorch analyzes the image data and outputs information indicating the anomalies. The analysis detects abnormal patterns and structures within the image.

[0108] Step 3:

[0109] The server compares the analysis results with a case database and generates a diagnosis. Based on the data of abnormal locations obtained as input, it searches the database for similar past cases and makes a diagnosis based on them. This result is highly reliable because it is based on past data.

[0110] Step 4:

[0111] Based on the generated diagnostic results, the server refers to medical guidelines and proposes the optimal treatment method. In this step, it selects the most suitable treatment method from several options according to the characteristics of the abnormal area and outputs it as information for a report.

[0112] Step 5:

[0113] The server uses a generation AI model to construct a natural language report containing the analysis results and proposed treatments, and sends it to the mobile device. The generated report is output in easy-to-understand natural language based on the prompt. An example of a prompt is: "Analyze the health check data of the following patient and generate a health management plan in natural language, comparing it with past cases."

[0114] Step 6:

[0115] Users with terminals (care staff and medical professionals) receive natural language reports sent from the server. Based on these reports, they can review the residents' health management plans and develop specific action plans for implementation.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention provides an AI system that supports pathological diagnosis in medical settings. In addition to conventional techniques for analyzing and diagnosing microscopic images, it incorporates an emotion engine to enhance the user experience. The system includes a server that receives medical data, preprocesses the images, and then an AI agent that detects abnormal areas. Subsequently, it generates a diagnosis result by comparing it with a case database and proposes the optimal treatment method based on medical guidelines.

[0118] The emotion engine analyzes the emotional states of various users. Based on this analysis, the server selects an appropriate method for presenting diagnostic results and adjusts the interface to suit the user. For example, if the emotion engine detects anxiety or stress in a user, the server takes this information into consideration and prioritizes suggesting reassuring language and treatment options.

[0119] As a concrete example, consider a scenario where a diagnostic report for a cancer patient is generated. The server analyzes the patient's microscopic images and detects abnormal areas indicating cancer cells. Next, it diagnoses the patient by comparing them to past cases and proposes the optimal treatment. If the emotion engine highly values ​​the patient's anxiety, the server generates a report that carefully presents treatment options and also includes advice on psychological support.

[0120] The server sends reports to the user's terminal, enabling healthcare professionals and patients to make situation-appropriate decisions. Furthermore, user responses via the emotion engine are fed back to the AI ​​model as feedback, helping to further improve the system. In this way, the present invention can simultaneously provide advanced diagnostic support and medical support that takes user emotions into consideration.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The server receives microscope image data transmitted from medical facilities. The image data is preprocessed, including noise reduction and resolution standardization, to make it easier for AI to process.

[0124] Step 2:

[0125] The server's AI agent analyzes the pre-processed images and uses deep learning algorithms to detect abnormal areas. This analysis marks suspicious lesions, providing the foundational data needed to proceed.

[0126] Step 3:

[0127] The server compares the detected abnormal area data with a database of similar past cases. A statistical model is used to infer the diagnosis and generate a reliable result.

[0128] Step 4:

[0129] Based on the generated diagnostic results, the server selects and proposes the most appropriate treatment method from medical guidelines for the patient's condition. This information is then compiled into a comprehensive treatment plan.

[0130] Step 5:

[0131] The server uses an emotion engine to analyze the user's emotional state. Based on the user's stress and anxiety levels, it adjusts how the results are presented and provides reassuring information.

[0132] Step 6:

[0133] The server compiles the diagnostic results and treatment suggestions into a report using natural language generation technology. The content is then adjusted based on sentiment analysis and delivered from the server to the user's terminal.

[0134] Step 7:

[0135] The system assists users in receiving reports and developing treatment plans while providing appropriate information to patients. User feedback is used by the server to further improve the emotion engine and AI models.

[0136] (Example 2)

[0137] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0138] Pathological diagnosis in medical settings relies on conventional technologies, resulting in limitations in accuracy and efficiency. Furthermore, there is a lack of means to alleviate the emotional burden on patients receiving diagnoses. Continuous improvement of AI models using feedback on diagnostic results is also insufficient. Therefore, it is necessary to simultaneously achieve more accurate diagnostic support and provide information that considers the user's emotions.

[0139] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0140] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, and means for analyzing the user's emotions using an emotion analysis function. This enables highly accurate diagnostic support and the provision of emotionally sensitive information tailored to the user.

[0141] A "microscope image" is a high-magnification image generated by optical instruments used in medical settings, enabling detailed observation of cells and tissues for pathological diagnosis.

[0142] "Preprocessing" refers to a series of processes performed before data analysis, aimed at removing image noise and adjusting contrast to improve analysis accuracy.

[0143] An "abnormal area" refers to a part that deviates from a standard healthy state or structure, and is an area where lesions, abnormal cells, or other abnormalities are detected through image analysis.

[0144] A "case database" is a collection of information that organizes and stores medical data collected in the past, and it plays a role in providing information about similar medical conditions and treatment outcomes.

[0145] "Medical guidelines" are evidence-based treatment guidelines and recommendations provided as standards for healthcare professionals to perform appropriate medical procedures in clinical practice.

[0146] "Emotional analysis" is a technology for quantifying or classifying a user's emotional state, and is a means of extracting emotional characteristics from data such as text and audio.

[0147] An "AI model" is a computational model formed by an artificial intelligence learning algorithm, and is used to perform predictions, classifications, and optimizations for specific tasks.

[0148] "Feedback" refers to the opinions and reactions received from users, and the provision of information that is used to improve and adjust the system.

[0149] This invention is a system that provides advanced diagnostic support and medical support that takes into account the patient's feelings. It mainly consists of a server, terminals, and users.

[0150] The server processes microscope images received from terminals in medical facilities. This image data undergoes preprocessing such as noise reduction and contrast adjustment. Specifically, open-source image processing software (e.g., OpenCV) is used to improve image quality.

[0151] Subsequently, the server performs image analysis and utilizes deep learning technology to detect abnormal areas. In this process, AI models using machine learning frameworks such as TensorFlow are employed to automatically identify the abnormal parts.

[0152] The analysis results are cross-referenced with a case database. Using an SQL database, the system generates the optimal diagnosis based on similar past cases. Based on the diagnosis, the server selects the recommended treatment, referencing medical guidelines. This process enables evidence-based treatment recommendations.

[0153] Furthermore, the server utilizes an emotion analysis engine to evaluate the user's emotions obtained from the device and other data. It uses natural language processing algorithms to analyze the emotional state from the user's text and voice.

[0154] As a result, the server generates a report that takes emotional states into account and provides feedback to the user using reassuring language. The generated report is output in PDF or HTML format and securely sent to the terminal.

[0155] As a concrete example, consider the diagnostic process for cancer patients. After detecting abnormal sites indicating cancer cells, the optimal treatment method is proposed by comparing them with past cases. If emotional analysis reveals that the patient is showing high levels of anxiety, the server explains the treatment method in reassuring language and provides a report that includes advice on psychological support.

[0156] An example of a prompt for the generating AI model is, "Generate treatment suggestions that take patient anxiety into consideration, based on cancer case data." In this way, the system integrates technical support in medical diagnosis with human-centered emotional care.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The server receives microscope images from terminals installed in medical facilities. This received image data is stored in a format suitable for diagnostic analysis. The input here is raw microscope image data, and the output is image data subject to preprocessing.

[0160] Step 2:

[0161] The server performs image preprocessing. Specifically, it removes noise and adjusts contrast using algorithms from open-source libraries. This process improves image quality and increases the accuracy of AI analysis. The input is the preprocessed image data obtained in step 1, and the output is the preprocessed, high-quality image data.

[0162] Step 3:

[0163] The server analyzes pre-processed image data using an AI agent. A deep learning model, such as TensorFlow, identifies abnormal areas in the input image. The input is pre-processed image data, and the output is the analysis result showing the abnormal areas.

[0164] Step 4:

[0165] The server compares the analysis results with the case database. It uses SQL queries to search past case information and generates diagnostic results corresponding to the abnormal areas. This comparison provides the most relevant case information to be used as a basis for judgment. The input is the analysis results, and the output is the confirmed diagnostic result.

[0166] Step 5:

[0167] Based on the diagnostic results, the server refers to medical guidelines and presents recommended treatments. It performs comparative calculations with the treatment procedures described in the guidelines to select the optimal treatment. The input is the diagnostic result, and the output is a suggested treatment plan.

[0168] Step 6:

[0169] The server uses an emotion engine to analyze the user's emotional state. It applies natural language processing to analyze text or audio data from the terminal to determine the user's emotions. The input is the user's text or audio data, and the output is the result of the emotion analysis.

[0170] Step 7:

[0171] The server generates a report designed to provide reassurance based on the sentiment analysis results. Using natural language generation technology, it explains the diagnosis and treatment plan in a way that is appropriate for the user. Inputs include the diagnosis results, recommended treatment plan, and sentiment analysis results, while output is an emotionally sensitive diagnosis report.

[0172] Step 8:

[0173] The server sends the generated report to the terminal. The terminal user makes decisions as a healthcare professional based on the received report. The input is an emotionally sensitive diagnostic report, and the output is a diagnostic report displayed on the user's terminal.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0176] In modern medical settings, while highly accurate pathological diagnoses are demanded, the psychological burden on patients and healthcare professionals remains a challenge. In particular, appropriate communication that takes into account patients' anxiety and stress is essential during the diagnostic process. However, existing technologies do not adequately address these psychological aspects, increasing the burden on healthcare professionals. Therefore, a system is needed that can improve diagnostic accuracy while simultaneously providing psychological care for patients and healthcare professionals.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, means for generating diagnostic results by comparing them with a database of past cases, means for suggesting appropriate treatment methods by referring to medical guidelines, means for creating reports using natural language generation technology, means for analyzing emotional states, means for adjusting the interface according to emotional states, means for making suggestions to provide psychological support to the user, and means for providing feedback to train an AI model. This makes it possible to improve diagnostic accuracy and reduce the psychological burden on the user.

[0179] A "microscope image" is image data of a fine structure obtained using a microscope.

[0180] "Preprocessing" refers to the initial processing operations performed to make microscope images easier to analyze.

[0181] An "abnormal area" refers to a part of a microscopic image that is different from normal, indicating a lesion or abnormality.

[0182] A "case database" is a collection of data that systematically collects and stores past patient information and diagnostic results.

[0183] A "diagnosis" is a decision or judgment regarding a patient's health status, obtained by comparing it with case data.

[0184] "Medical guidelines" are guidelines that show the appropriate methods for performing medical procedures.

[0185] "Natural language generation technology" is a technology that enables computers to generate text in human language.

[0186] "Emotional state" refers to elements that indicate an individual's current psychological and emotional condition.

[0187] An "interface" refers to the means or environment for exchanging information between a system and a user.

[0188] "Psychological support" refers to advice and care provided to maintain or improve an individual's mental health.

[0189] "Feedback" is the process by which data and responses entered into a system are used to improve or adapt that system.

[0190] The system that realizes this invention consists of a server, a user terminal, and a series of programs that use an emotion analysis algorithm.

[0191] The server first receives microscope images and then preprocesses them. This preprocessing includes noise reduction and image shaping to prepare the images for highly accurate pathological diagnosis. The data obtained through this process is then subjected to analysis using advanced deep learning algorithms to identify abnormal areas. This ensures accurate detection of areas deemed pathologically abnormal.

[0192] Next, the server compares the detected abnormal areas with past cases in the database and generates a diagnosis. At this point, it also refers to relevant medical guidelines and suggests the optimal treatment. The generated diagnosis and treatment are compiled into a report using natural language generation technology. This technology is essential for providing information in a format that is easy for users to understand.

[0193] Furthermore, the server integrates emotion analysis capabilities. This allows for the analysis of the user's emotional state and real-time assessment of their psychological condition. Based on the analysis results, the interface is adjusted and psychological support is suggested. This may include, for example, the presentation of relaxing content and guidance on stress reduction measures. User feedback is also sent to the server and used for the continuous learning and improvement of the AI ​​model.

[0194] As a concrete example, in the diagnostic process for cancer patients, after microscopic image analysis, a diagnostic result is generated based on that analysis, and a report is presented in an interface tailored to the patient's emotional state. If the emotional analysis detects anxiety, the server presents treatment options using language that is particularly reassuring. Furthermore, if the need for psychological support is determined, related actions are recommended.

[0195] An example of a prompt statement is: "Describe the algorithm of an application that detects signs of stress and anxiety from the facial expressions and voice of elderly individuals through an emotion engine, and notifies care staff in real time with care suggestions." This enables continuous care that takes emotional states into account.

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server receives image data acquired from the microscope. This data is used as input for preprocessing to remove noise and enhance clarity. The preprocessed image data is then shaped into an output format suitable for detecting abnormal areas.

[0199] Step 2:

[0200] The server inputs the pre-processed image data into a deep learning algorithm. This algorithm uses a pre-trained model to detect potentially abnormal areas in the image and outputs them. Detailed coordinate information and characteristics of the abnormal areas are obtained.

[0201] Step 3:

[0202] The server cross-references the detected abnormal area information with a case database. This cross-referencing searches for similar past cases and outputs corresponding diagnostic results and treatment information. This process is implemented through database queries.

[0203] Step 4:

[0204] The server uses natural language generation technology to create a report based on the diagnostic results and treatment information obtained through matching. This process generates text-based information, which is output in an easily understandable format.

[0205] Step 5:

[0206] The server executes an emotion analysis algorithm to analyze the user's emotional state. Facial expression data and voice data acquired from the user's terminal are input, stress and anxiety are detected, and the analysis results are output.

[0207] Step 6:

[0208] Based on the sentiment analysis results, the server adjusts the user interface and the way reports are presented. This adjustment suggests appropriate wording and reassuring content to reduce psychological burden.

[0209] Step 7:

[0210] The server collects user feedback and feeds it to the AI ​​model. This feedback is used as data to improve the accuracy of subsequent analyses and interface adjustments.

[0211] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0212] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0213] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0217] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0218] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0219] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0220] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0221] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0222] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0223] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0225] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0226] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0227] This invention is implemented as an AI-based system to support pathological diagnosis in medical settings. This system allows for highly accurate detection of abnormal areas by having a server receive medical data, such as microscope images, perform preprocessing, and then having an AI agent analyze the data. This process helps medical professionals make rapid and accurate diagnoses.

[0228] The server compares the analyzed image data with an existing case database to generate a diagnosis. This provides an objective diagnosis based on similar past cases. The server also refers to the latest medical guidelines to suggest the most appropriate treatment for the patient. This information is compiled into a report using natural language generation technology and delivered to the user or device.

[0229] As a concrete example, consider a scenario where a CT scan image of a patient suspected of having lung cancer is sent to a server. The server analyzes this image to identify the location and size of the tumor within the lung. Next, based on past case data, it diagnoses the lesion as small cell lung cancer. Based on these results, a chemotherapy plan in accordance with the latest treatment guidelines is proposed. The report is generated in natural language and provided in a format that allows physicians to discuss the detailed treatment plan with the patient.

[0230] The server updates the AI ​​model based on continuous feedback, improving the accuracy of medical image analysis. This information is accessible on the user's terminal, contributing to the efficiency of medical treatment. In this way, the present invention enables the optimization of medical processes and realizes a form that dramatically improves the accuracy and efficiency of pathological diagnosis.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The server automatically reads microscope images and CT scan images received from medical institutions. After receiving the images, it performs preprocessing to remove noise and convert them into a format that is easy for AI to analyze.

[0234] Step 2:

[0235] The server's AI agent performs abnormal area detection based on the pre-processed images. Using a deep learning algorithm, it identifies potentially diseased areas at the pixel level and visually highlights them.

[0236] Step 3:

[0237] The server compares the detected abnormal area information with an existing case database. It references past similar case data and applies a statistical model to generate a diagnosis.

[0238] Step 4:

[0239] The system uses the diagnostic results generated by the server to automatically suggest appropriate treatment methods based on medical guidelines. The suggested treatments are customized according to the patient's individual health condition.

[0240] Step 5:

[0241] The server integrates the diagnostic results and suggested treatments, and generates a detailed report using natural language generation technology. This report includes the location of any lesions found and recommended treatment options.

[0242] Step 6:

[0243] The server sends the generated report to the terminal. As a result, the user, a medical professional, can review the diagnostic results and obtain the information needed to develop the best treatment plan for the patient.

[0244] Step 7:

[0245] The server leverages a feedback loop to supply new diagnostic results and treatment outcomes to the AI ​​model, continuously improving the accuracy of the algorithm.

[0246] (Example 1)

[0247] Next, we will describe Example 1. 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."

[0248] In medical settings, rapid and accurate pathological diagnosis is crucial, but image data noise and complex diagnostic processes can be obstacles. Furthermore, there is a need for objective diagnoses based on comparisons with past cases and for treatment methods based on the latest medical standards. Additionally, there is a need for a method to provide generated diagnostic results in natural language reports, allowing users to efficiently utilize the information.

[0249] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0250] In this invention, the server includes means for receiving and pre-processing image information, means for analyzing the pre-processed image information and detecting abnormal elements, means for comparing it with a database of past cases and generating analysis results, means for proposing appropriate treatment methods by referring to medical standards, means for creating reports using natural language generation technology, means for conducting evaluations to update the learning model, and means for displaying processing progress and notifying information. This enables rapid and objective diagnosis and proposal of treatment methods, and allows medical professionals to make appropriate decisions by utilizing the generated information.

[0251] "Image information" refers to visual data acquired for use in medical or scientific analysis, including microscopic images and CT scan images.

[0252] "Preprocessing" refers to the process of adjusting data to a state suitable for analysis, and includes steps such as noise reduction and standardization.

[0253] "Abnormal elements" refer to characteristics of cells or tissues that deviate from a normal state, and are the parts that are subject to pathological diagnosis.

[0254] A "case database" is a source of information that collects data on past medical cases and patient data, and is used for matching and analyzing diagnostic results.

[0255] "Medical standards" refer to guidelines and protocols for diagnosis and treatment, and serve as the criteria for applying the treatment methods provided to patients.

[0256] "Natural language generation technology" is a technology that allows computers to represent information using human language, and is used for creating reports and explanatory texts.

[0257] A "learning model" is a computational model that learns patterns from data using machine learning algorithms, and its purpose is to improve the accuracy of analysis.

[0258] "Means for displaying progress and notifying information" refers to interfaces and functions for communicating the current progress and results of data processing to the user.

[0259] This invention relates to a system for supporting diagnosis in the medical field. Specific embodiments thereof are described below.

[0260] The server receives image information from medical institutions, such as microscope images and CT scan images. This image information is crucial for accurate diagnosis, and the server first performs data preprocessing. At this stage, noise is removed from the images, and contrast and brightness are adjusted to appropriate levels. The preprocessed data is then analyzed by an AI agent using a general-purpose machine learning framework such as TensorFlow, which runs on common hardware. The analysis identifies abnormal elements, which are then used to efficiently aid in diagnosis.

[0261] Subsequently, the server accesses an SQL database built to compare the analysis results with a case database. In this process, the server reinforces the diagnosis based on past case information, supporting objective decision-making. Once the comparison is complete, the server proposes the optimal treatment method based on medical guidelines. This information is compiled into a report using natural language generation technology and delivered to the terminal. The user can then easily use this to explain the situation to the patient.

[0262] As a concrete example, consider a case where an image of a patient with lung abnormalities is sent to the server. The server analyzes the image and detects the shape and location of the abnormal shadow. Next, by comparing this with a case database, it diagnoses the possibility of small cell lung cancer and proposes appropriate chemotherapy. This information is generated as a natural language report and provided to the user.

[0263] An example of a prompt for a generative AI model is: "Analyze the patient's lung CT scan, describe the tumor details, and generate a report suggesting the best treatment options."

[0264] As described above, this system supports the efficiency and accuracy of diagnosis in medical settings, helping healthcare professionals make objective and rapid decisions.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] The server receives image information transmitted from medical institutions. Input includes microscope images and CT scan images, which the server stores in its data storage. Next, it removes noise from the received raw data and standardizes the image contrast and brightness. This prepares the data for easier image analysis. The output is pre-processed image information.

[0268] Step 2:

[0269] The server passes pre-processed image information to the AI ​​agent. The input here is the pre-processed image, which is analyzed by a neural network using TensorFlow. The server analyzes each pixel and identifies abnormal elements. This process calculates the location and size of the abnormal areas. The output is the analysis result with the abnormal areas identified.

[0270] Step 3:

[0271] The server uses the analysis results as queries to access the case database. The input includes data that is considered characteristic information of the abnormal elements, and the server compares it with past case information stored in the SQL database. This searches for similar past cases and retrieves information to reinforce the diagnosis. The output is diagnostic information compared with past cases.

[0272] Step 4:

[0273] The server consults a medical guideline database based on the diagnostic information obtained through matching. The input includes diagnostic information, and the server performs calculations to propose the most suitable treatment method based on the corresponding guidelines. As a result, a list of candidate treatment methods deemed medically appropriate is generated. The output is information on the proposed treatment methods.

[0274] Step 5:

[0275] The server integrates the generated diagnostic information and treatment methods, and creates a report using natural language generation technology. The input consists of diagnostic information and suggested treatment methods, which the server uses to create a natural language report based on a generative AI model such as GPT-3. The output is a report presented in a format easily understood by users and healthcare professionals.

[0276] Step 6:

[0277] The terminal receives the provided report and notifies the user. The input here is the generated report, which the terminal visualizes and displays. The user reviews the report and uses the diagnostic results and treatment methods to make decisions in the medical setting. The output is the detailed diagnostic report actually displayed on the screen.

[0278] (Application Example 1)

[0279] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0280] In a caregiving facility, it is often difficult to efficiently manage the health status of residents and promptly propose appropriate treatment methods. There is a need for support means that enable caregivers without medical expertise to perform highly accurate health management. In contrast, it is necessary to realize a system that can accurately identify abnormal areas and promptly propose treatment methods based on past cases and medical guidelines.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0282] In this invention, the server includes means for acquiring a microscopic image and performing data preprocessing, means for analyzing the preprocessed image to identify abnormal areas, means for outputting a diagnosis result by comparing with a case database, means for proposing an appropriate treatment method by referring to medical guidelines, and means for providing the analysis result as a health management plan according to the caregiving site. As a result, it becomes possible to promptly provide highly accurate health diagnosis results and automatically propose a medical plan for each resident even in a caregiving facility.

[0283] The "microscopic image" is image data showing a fine structure photographed using an optical microscope or an electron microscope.

[0284] The "data preprocessing" is a process of performing noise removal and contrast adjustment on image data in order to improve the accuracy of analysis.

[0285] The "abnormal area" is an area showing different characteristics or structures compared to a standard pathological tissue, and suggests the presence of a potential disease or lesion.

[0286] The "case database" is a dataset in which past similar diagnosis results and subsequent progress information are accumulated, and is an information source useful for diagnosis and selection of treatment methods.

[0287] "Medical Guidelines" are guidelines that indicate standard diagnostic methods and treatment guidelines for specific diseases or cases, formulated based on the latest medical research and expert consensus.

[0288] "Analysis Results" are detailed information regarding abnormal sites derived from the analysis of image data, which are used for making diagnostic and treatment decisions.

[0289] "Health Management Plan" is a specific action plan proposed to maintain or improve the health status of patients or residents based on analysis results and diagnoses.

[0290] To realize this invention, it is necessary to construct a system specialized for health management in nursing facilities. This system functions in cooperation with a server, a mobile terminal, and users.

[0291] The server first receives microscopic images and performs preprocessing for analyzing them. This preprocessing includes noise removal and contrast adjustment of the images. The preprocessed images are analyzed by an AI model implemented with deep learning, and abnormal locations are identified. This AI model is generally constructed using software such as TensorFlow or PyTorch.

[0292] The analysis results are compared with the case database, and a diagnostic result is automatically generated. By referring to medical guidelines, the optimal treatment method for the patient is proposed. The proposed content is reported in natural language using a generation AI model and sent to the user's mobile terminal. Thereby, nursing staff and medical professionals can propose a specific health management plan to the residents based on this information.

[0293] As a concrete example, when image data of a resident is sent to the server, the server automatically analyzes this image data and generates a health management plan based on the results. The generated plan is created based on a prompt that reads, "Analyze the health check data of the following patient and generate a health management plan in natural language, comparing it with past cases." By following this prompt and using advanced natural language generation technology, an easily interpretable report is created, enabling efficient health management in nursing facilities.

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The server receives microscope image data transmitted from nursing care facilities. Using this received data as input, it performs image noise reduction and contrast adjustment to output image data suitable for analysis. This enables highly accurate identification of abnormal areas.

[0297] Step 2:

[0298] The server inputs pre-processed image data into a deep learning model to identify anomalies. During this process, an AI model built using TensorFlow or PyTorch analyzes the image data and outputs information indicating the anomalies. The analysis detects abnormal patterns and structures within the image.

[0299] Step 3:

[0300] The server compares the analysis results with a case database and generates a diagnosis. Based on the data of abnormal locations obtained as input, it searches the database for similar past cases and makes a diagnosis based on them. This result is highly reliable because it is based on past data.

[0301] Step 4:

[0302] Based on the generated diagnosis results, the server refers to medical guidelines and proposes the optimal treatment method. In this step, the optimal one is selected from multiple treatment methods according to the characteristics of the abnormal part and output as information for the report.

[0303] Step 5:

[0304] The server uses the analysis results and the proposed treatment method to compose them into a natural language report using the generation AI model and transmits it to the mobile terminal. The generated report is output in an easy-to-understand natural language form based on the prompt sentence. As an example of the prompt sentence, "Please analyze the following patient's health diagnosis data and generate a health management plan in natural language in comparison with past cases." is used.

[0305] Step 6:

[0306] The user (care staff or medical professional) with the terminal receives the natural language report sent from the server. Based on this report, the user can check the health management plan for the resident and make a specific action plan for implementation.

[0307] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0308] The present invention is an AI system for supporting pathological diagnosis in the medical field, and in addition to the conventional technology for analyzing microscopic images and making diagnoses, it provides a form of improving the user experience by incorporating an emotion engine. This system includes a process in which the server receives medical data, the AI agent detects abnormal parts after preprocessing the images, then generates a diagnosis result by comparing with the case database, and proposes an optimal treatment method based on medical guidelines.

[0309] The emotion engine analyzes the emotional states of various users. Based on this analysis, the server selects an appropriate method for presenting diagnostic results and adjusts the interface to suit the user. For example, if the emotion engine detects anxiety or stress in a user, the server takes this information into consideration and prioritizes suggesting reassuring language and treatment options.

[0310] As a concrete example, consider a scenario where a diagnostic report for a cancer patient is generated. The server analyzes the patient's microscopic images and detects abnormal areas indicating cancer cells. Next, it diagnoses the patient by comparing them to past cases and proposes the optimal treatment. If the emotion engine highly values ​​the patient's anxiety, the server generates a report that carefully presents treatment options and also includes advice on psychological support.

[0311] The server sends reports to the user's terminal, enabling healthcare professionals and patients to make situation-appropriate decisions. Furthermore, user responses via the emotion engine are fed back to the AI ​​model as feedback, helping to further improve the system. In this way, the present invention can simultaneously provide advanced diagnostic support and medical support that takes user emotions into consideration.

[0312] The following describes the processing flow.

[0313] Step 1:

[0314] The server receives microscope image data transmitted from medical facilities. The image data is preprocessed, including noise reduction and resolution standardization, to make it easier for AI to process.

[0315] Step 2:

[0316] The server's AI agent analyzes the pre-processed images and uses deep learning algorithms to detect abnormal areas. This analysis marks suspicious lesions, providing the foundational data needed to proceed.

[0317] Step 3:

[0318] The server compares the detected abnormal area data with a database of similar past cases. A statistical model is used to infer the diagnosis and generate a reliable result.

[0319] Step 4:

[0320] Based on the generated diagnostic results, the server selects and proposes the most appropriate treatment method from medical guidelines for the patient's condition. This information is then compiled into a comprehensive treatment plan.

[0321] Step 5:

[0322] The server uses an emotion engine to analyze the user's emotional state. Based on the user's stress and anxiety levels, it adjusts how the results are presented and provides reassuring information.

[0323] Step 6:

[0324] The server compiles the diagnostic results and treatment suggestions into a report using natural language generation technology. The content is then adjusted based on sentiment analysis and delivered from the server to the user's terminal.

[0325] Step 7:

[0326] The system assists users in receiving reports and developing treatment plans while providing appropriate information to patients. User feedback is used by the server to further improve the emotion engine and AI models.

[0327] (Example 2)

[0328] Next, we will describe Example 2. 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".

[0329] Pathological diagnosis in medical settings relies on conventional technologies, resulting in limitations in accuracy and efficiency. Furthermore, there is a lack of means to alleviate the emotional burden on patients receiving diagnoses. Continuous improvement of AI models using feedback on diagnostic results is also insufficient. Therefore, it is necessary to simultaneously achieve more accurate diagnostic support and provide information that considers the user's emotions.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, and means for analyzing the user's emotions using an emotion analysis function. This enables highly accurate diagnostic support and the provision of emotionally sensitive information tailored to the user.

[0332] A "microscope image" is a high-magnification image generated by optical instruments used in medical settings, enabling detailed observation of cells and tissues for pathological diagnosis.

[0333] "Preprocessing" refers to a series of processes performed before data analysis, aimed at removing image noise and adjusting contrast to improve analysis accuracy.

[0334] An "abnormal area" refers to a part that deviates from a standard healthy state or structure, and is an area where lesions, abnormal cells, or other abnormalities are detected through image analysis.

[0335] A "case database" is a collection of information that organizes and stores medical data collected in the past, and it plays a role in providing information about similar medical conditions and treatment outcomes.

[0336] "Medical guidelines" are evidence-based treatment guidelines and recommendations provided as standards for healthcare professionals to perform appropriate medical procedures in clinical practice.

[0337] "Emotional analysis" is a technology for quantifying or classifying a user's emotional state, and is a means of extracting emotional characteristics from data such as text and audio.

[0338] An "AI model" is a computational model formed by an artificial intelligence learning algorithm, and is used to perform predictions, classifications, and optimizations for specific tasks.

[0339] "Feedback" refers to the opinions and reactions received from users, and the provision of information that is used to improve and adjust the system.

[0340] This invention is a system that provides advanced diagnostic support and medical support that takes into account the patient's feelings. It mainly consists of a server, terminals, and users.

[0341] The server processes microscope images received from terminals in medical facilities. This image data undergoes preprocessing such as noise reduction and contrast adjustment. Specifically, open-source image processing software (e.g., OpenCV) is used to improve image quality.

[0342] Subsequently, the server performs image analysis and utilizes deep learning technology to detect abnormal areas. In this process, AI models using machine learning frameworks such as TensorFlow are employed to automatically identify the abnormal parts.

[0343] The analysis results are cross-referenced with a case database. Using an SQL database, the system generates the optimal diagnosis based on similar past cases. Based on the diagnosis, the server selects the recommended treatment, referencing medical guidelines. This process enables evidence-based treatment recommendations.

[0344] Furthermore, the server utilizes an emotion analysis engine to evaluate the user's emotions obtained from the device and other data. It uses natural language processing algorithms to analyze the emotional state from the user's text and voice.

[0345] As a result, the server generates a report that takes emotional states into account and provides feedback to the user using reassuring language. The generated report is output in PDF or HTML format and securely sent to the terminal.

[0346] As a concrete example, consider the diagnostic process for cancer patients. After detecting abnormal sites indicating cancer cells, the optimal treatment method is proposed by comparing them with past cases. If emotional analysis reveals that the patient is showing high levels of anxiety, the server explains the treatment method in reassuring language and provides a report that includes advice on psychological support.

[0347] An example of a prompt for the generating AI model is, "Generate treatment suggestions that take patient anxiety into consideration, based on cancer case data." In this way, the system integrates technical support in medical diagnosis with human-centered emotional care.

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] The server receives microscope images from terminals installed in medical facilities. This received image data is stored in a format suitable for diagnostic analysis. The input here is raw microscope image data, and the output is image data subject to preprocessing.

[0351] Step 2:

[0352] The server performs image preprocessing. Specifically, it removes noise and adjusts contrast using algorithms from open-source libraries. This process improves image quality and increases the accuracy of AI analysis. The input is the preprocessed image data obtained in step 1, and the output is the preprocessed, high-quality image data.

[0353] Step 3:

[0354] The server analyzes pre-processed image data using an AI agent. A deep learning model, such as TensorFlow, identifies abnormal areas in the input image. The input is pre-processed image data, and the output is the analysis result showing the abnormal areas.

[0355] Step 4:

[0356] The server compares the analysis results with the case database. It uses SQL queries to search past case information and generates diagnostic results corresponding to the abnormal areas. This comparison provides the most relevant case information to be used as a basis for judgment. The input is the analysis results, and the output is the confirmed diagnostic result.

[0357] Step 5:

[0358] Based on the diagnostic results, the server refers to medical guidelines and presents recommended treatments. It performs comparative calculations with the treatment procedures described in the guidelines to select the optimal treatment. The input is the diagnostic result, and the output is a suggested treatment plan.

[0359] Step 6:

[0360] The server uses an emotion engine to analyze the user's emotional state. It applies natural language processing to analyze text or audio data from the terminal to determine the user's emotions. The input is the user's text or audio data, and the output is the result of the emotion analysis.

[0361] Step 7:

[0362] The server generates a report designed to provide reassurance based on the sentiment analysis results. Using natural language generation technology, it explains the diagnosis and treatment plan in a way that is appropriate for the user. Inputs include the diagnosis results, recommended treatment plan, and sentiment analysis results, while output is an emotionally sensitive diagnosis report.

[0363] Step 8:

[0364] The server sends the generated report to the terminal. The terminal user makes decisions as a healthcare professional based on the received report. The input is an emotionally sensitive diagnostic report, and the output is a diagnostic report displayed on the user's terminal.

[0365] (Application Example 2)

[0366] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0367] In modern medical settings, while highly accurate pathological diagnoses are demanded, the psychological burden on patients and healthcare professionals remains a challenge. In particular, appropriate communication that takes into account patients' anxiety and stress is essential during the diagnostic process. However, existing technologies do not adequately address these psychological aspects, increasing the burden on healthcare professionals. Therefore, a system is needed that can improve diagnostic accuracy while simultaneously providing psychological care for patients and healthcare professionals.

[0368] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0369] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, means for generating diagnostic results by comparing them with a database of past cases, means for suggesting appropriate treatment methods by referring to medical guidelines, means for creating reports using natural language generation technology, means for analyzing emotional states, means for adjusting the interface according to emotional states, means for making suggestions to provide psychological support to the user, and means for providing feedback to train an AI model. This makes it possible to improve diagnostic accuracy and reduce the psychological burden on the user.

[0370] A "microscope image" is image data of a fine structure obtained using a microscope.

[0371] "Preprocessing" refers to the initial processing operations performed to make microscope images easier to analyze.

[0372] An "abnormal area" refers to a part of a microscopic image that is different from normal, indicating a lesion or abnormality.

[0373] A "case database" is a collection of data that systematically collects and stores past patient information and diagnostic results.

[0374] A "diagnosis" is a decision or judgment regarding a patient's health status, obtained by comparing it with case data.

[0375] "Medical guidelines" are guidelines that show the appropriate methods for performing medical procedures.

[0376] "Natural language generation technology" is a technology that enables computers to generate text in human language.

[0377] "Emotional state" refers to elements that indicate an individual's current psychological and emotional condition.

[0378] An "interface" refers to the means or environment for exchanging information between a system and a user.

[0379] "Psychological support" refers to advice and care provided to maintain or improve an individual's mental health.

[0380] "Feedback" is the process by which data and responses entered into a system are used to improve or adapt that system.

[0381] The system that realizes this invention consists of a server, a user terminal, and a series of programs that use an emotion analysis algorithm.

[0382] The server first receives microscope images and then preprocesses them. This preprocessing includes noise reduction and image shaping to prepare the images for highly accurate pathological diagnosis. The data obtained through this process is then subjected to analysis using advanced deep learning algorithms to identify abnormal areas. This ensures accurate detection of areas deemed pathologically abnormal.

[0383] Next, the server compares the detected abnormal areas with past cases in the database and generates a diagnosis. At this point, it also refers to relevant medical guidelines and suggests the optimal treatment. The generated diagnosis and treatment are compiled into a report using natural language generation technology. This technology is essential for providing information in a format that is easy for users to understand.

[0384] Furthermore, the server integrates emotion analysis capabilities. This allows for the analysis of the user's emotional state and real-time assessment of their psychological condition. Based on the analysis results, the interface is adjusted and psychological support is suggested. This may include, for example, the presentation of relaxing content and guidance on stress reduction measures. User feedback is also sent to the server and used for the continuous learning and improvement of the AI ​​model.

[0385] As a concrete example, in the diagnostic process for cancer patients, after microscopic image analysis, a diagnostic result is generated based on that analysis, and a report is presented in an interface tailored to the patient's emotional state. If the emotional analysis detects anxiety, the server presents treatment options using language that is particularly reassuring. Furthermore, if the need for psychological support is determined, related actions are recommended.

[0386] An example of a prompt statement is: "Describe the algorithm of an application that detects signs of stress and anxiety from the facial expressions and voice of elderly individuals through an emotion engine, and notifies care staff in real time with care suggestions." This enables continuous care that takes emotional states into account.

[0387] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0388] Step 1:

[0389] The server receives image data acquired from the microscope. This data is used as input for preprocessing to remove noise and enhance clarity. The preprocessed image data is then shaped into an output format suitable for detecting abnormal areas.

[0390] Step 2:

[0391] The server inputs the pre-processed image data into a deep learning algorithm. This algorithm uses a pre-trained model to detect potentially abnormal areas in the image and outputs them. Detailed coordinate information and characteristics of the abnormal areas are obtained.

[0392] Step 3:

[0393] The server cross-references the detected abnormal area information with a case database. This cross-referencing searches for similar past cases and outputs corresponding diagnostic results and treatment information. This process is implemented through database queries.

[0394] Step 4:

[0395] The server uses natural language generation technology to create a report based on the diagnostic results and treatment information obtained through matching. This process generates text-based information, which is output in an easily understandable format.

[0396] Step 5:

[0397] The server executes an emotion analysis algorithm to analyze the user's emotional state. Facial expression data and voice data acquired from the user's terminal are input, stress and anxiety are detected, and the analysis results are output.

[0398] Step 6:

[0399] Based on the sentiment analysis results, the server adjusts the user interface and the way reports are presented. This adjustment suggests appropriate wording and reassuring content to reduce psychological burden.

[0400] Step 7:

[0401] The server collects user feedback and feeds it to the AI ​​model. This feedback is used as data to improve the accuracy of subsequent analyses and interface adjustments.

[0402] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0403] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0404] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0405] [Third Embodiment]

[0406] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0407] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0408] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0409] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0410] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0411] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0412] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0413] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0414] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0415] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0416] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0417] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0418] This invention is implemented as an AI-based system to support pathological diagnosis in medical settings. This system allows for highly accurate detection of abnormal areas by having a server receive medical data, such as microscope images, perform preprocessing, and then having an AI agent analyze the data. This process helps medical professionals make rapid and accurate diagnoses.

[0419] The server compares the analyzed image data with an existing case database to generate a diagnosis. This provides an objective diagnosis based on similar past cases. The server also refers to the latest medical guidelines to suggest the most appropriate treatment for the patient. This information is compiled into a report using natural language generation technology and delivered to the user or device.

[0420] As a concrete example, consider a scenario where a CT scan image of a patient suspected of having lung cancer is sent to a server. The server analyzes this image to identify the location and size of the tumor within the lung. Next, based on past case data, it diagnoses the lesion as small cell lung cancer. Based on these results, a chemotherapy plan in accordance with the latest treatment guidelines is proposed. The report is generated in natural language and provided in a format that allows physicians to discuss the detailed treatment plan with the patient.

[0421] The server updates the AI ​​model based on continuous feedback, improving the accuracy of medical image analysis. This information is accessible on the user's terminal, contributing to the efficiency of medical treatment. In this way, the present invention enables the optimization of medical processes and realizes a form that dramatically improves the accuracy and efficiency of pathological diagnosis.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The server automatically reads microscope images and CT scan images received from medical institutions. After receiving the images, it performs preprocessing to remove noise and convert them into a format that is easy for AI to analyze.

[0425] Step 2:

[0426] The server's AI agent performs abnormal area detection based on the pre-processed images. Using a deep learning algorithm, it identifies potentially diseased areas at the pixel level and visually highlights them.

[0427] Step 3:

[0428] The server compares the detected abnormal area information with an existing case database. It references past similar case data and applies a statistical model to generate a diagnosis.

[0429] Step 4:

[0430] The system uses the diagnostic results generated by the server to automatically suggest appropriate treatment methods based on medical guidelines. The suggested treatments are customized according to the patient's individual health condition.

[0431] Step 5:

[0432] The server integrates the diagnostic results and suggested treatments, and generates a detailed report using natural language generation technology. This report includes the location of any lesions found and recommended treatment options.

[0433] Step 6:

[0434] The server sends the generated report to the terminal. As a result, the user, a medical professional, can review the diagnostic results and obtain the information needed to develop the best treatment plan for the patient.

[0435] Step 7:

[0436] The server leverages a feedback loop to supply new diagnostic results and treatment outcomes to the AI ​​model, continuously improving the accuracy of the algorithm.

[0437] (Example 1)

[0438] Next, we will describe Example 1. 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."

[0439] In medical settings, rapid and accurate pathological diagnosis is crucial, but image data noise and complex diagnostic processes can be obstacles. Furthermore, there is a need for objective diagnoses based on comparisons with past cases and for treatment methods based on the latest medical standards. Additionally, there is a need for a method to provide generated diagnostic results in natural language reports, allowing users to efficiently utilize the information.

[0440] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0441] In this invention, the server includes means for receiving and pre-processing image information, means for analyzing the pre-processed image information and detecting abnormal elements, means for comparing it with a database of past cases and generating analysis results, means for proposing appropriate treatment methods by referring to medical standards, means for creating reports using natural language generation technology, means for conducting evaluations to update the learning model, and means for displaying processing progress and notifying information. This enables rapid and objective diagnosis and proposal of treatment methods, and allows medical professionals to make appropriate decisions by utilizing the generated information.

[0442] "Image information" refers to visual data acquired for use in medical or scientific analysis, including microscopic images and CT scan images.

[0443] "Preprocessing" refers to the process of adjusting data to a state suitable for analysis, and includes steps such as noise reduction and standardization.

[0444] "Abnormal elements" refer to characteristics of cells or tissues that deviate from a normal state, and are the parts that are subject to pathological diagnosis.

[0445] A "case database" is a source of information that collects data on past medical cases and patient data, and is used for matching and analyzing diagnostic results.

[0446] "Medical standards" refer to guidelines and protocols for diagnosis and treatment, and serve as the criteria for applying the treatment methods provided to patients.

[0447] "Natural language generation technology" is a technology that allows computers to represent information using human language, and is used for creating reports and explanatory texts.

[0448] A "learning model" is a computational model that learns patterns from data using machine learning algorithms, and its purpose is to improve the accuracy of analysis.

[0449] "Means for displaying progress and notifying information" refers to interfaces and functions for communicating the current progress and results of data processing to the user.

[0450] This invention relates to a system for supporting diagnosis in the medical field. Specific embodiments thereof are described below.

[0451] The server receives image information from medical institutions, such as microscope images and CT scan images. This image information is crucial for accurate diagnosis, and the server first performs data preprocessing. At this stage, noise is removed from the images, and contrast and brightness are adjusted to appropriate levels. The preprocessed data is then analyzed by an AI agent using a general-purpose machine learning framework such as TensorFlow, which runs on common hardware. The analysis identifies abnormal elements, which are then used to efficiently aid in diagnosis.

[0452] Subsequently, the server accesses an SQL database built to compare the analysis results with a case database. In this process, the server reinforces the diagnosis based on past case information, supporting objective decision-making. Once the comparison is complete, the server proposes the optimal treatment method based on medical guidelines. This information is compiled into a report using natural language generation technology and delivered to the terminal. The user can then easily use this to explain the situation to the patient.

[0453] As a concrete example, consider a case where an image of a patient with lung abnormalities is sent to the server. The server analyzes the image and detects the shape and location of the abnormal shadow. Next, by comparing this with a case database, it diagnoses the possibility of small cell lung cancer and proposes appropriate chemotherapy. This information is generated as a natural language report and provided to the user.

[0454] An example of a prompt for a generative AI model is: "Analyze the patient's lung CT scan, describe the tumor details, and generate a report suggesting the best treatment options."

[0455] As described above, this system supports the efficiency and accuracy of diagnosis in medical settings, helping healthcare professionals make objective and rapid decisions.

[0456] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0457] Step 1:

[0458] The server receives image information transmitted from medical institutions. Input includes microscope images and CT scan images, which the server stores in its data storage. Next, it removes noise from the received raw data and standardizes the image contrast and brightness. This prepares the data for easier image analysis. The output is pre-processed image information.

[0459] Step 2:

[0460] The server passes pre-processed image information to the AI ​​agent. The input here is the pre-processed image, which is analyzed by a neural network using TensorFlow. The server analyzes each pixel and identifies abnormal elements. This process calculates the location and size of the abnormal areas. The output is the analysis result with the abnormal areas identified.

[0461] Step 3:

[0462] The server uses the analysis results as queries to access the case database. The input includes data that is considered characteristic information of the abnormal elements, and the server compares it with past case information stored in the SQL database. This searches for similar past cases and retrieves information to reinforce the diagnosis. The output is diagnostic information compared with past cases.

[0463] Step 4:

[0464] The server consults a medical guideline database based on the diagnostic information obtained through matching. The input includes diagnostic information, and the server performs calculations to propose the most suitable treatment method based on the corresponding guidelines. As a result, a list of candidate treatment methods deemed medically appropriate is generated. The output is information on the proposed treatment methods.

[0465] Step 5:

[0466] The server integrates the generated diagnostic information and treatment methods, and creates a report using natural language generation technology. The input consists of diagnostic information and suggested treatment methods, which the server uses to create a natural language report based on a generative AI model such as GPT-3. The output is a report presented in a format easily understood by users and healthcare professionals.

[0467] Step 6:

[0468] The terminal receives the provided report and notifies the user. The input here is the generated report, which the terminal visualizes and displays. The user reviews the report and uses the diagnostic results and treatment methods to make decisions in the medical setting. The output is the detailed diagnostic report actually displayed on the screen.

[0469] (Application Example 1)

[0470] Next, we will explain Application Example 1. In the following explanation, 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."

[0471] In nursing care settings, efficiently managing residents' health and promptly proposing appropriate treatments is often challenging. There is a need for support systems that enable even care staff without medical expertise to perform highly accurate health management. To address this, a system is needed that can accurately identify abnormalities and quickly propose treatments based on past cases and medical guidelines.

[0472] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0473] In this invention, the server includes means for acquiring microscopic images and performing data preprocessing, means for analyzing the preprocessed images and identifying abnormal areas, means for outputting diagnostic results by comparing them with a case database, means for proposing appropriate treatment methods based on medical guidelines, and means for providing the analysis results as a health management plan according to the care setting. This enables the rapid provision of highly accurate health checkup results and the automatic proposal of individual medical plans for residents, even in care facilities.

[0474] A "microscope image" is image data showing fine structures, captured using an optical microscope or an electron microscope.

[0475] "Data preprocessing" is the process of removing noise and adjusting contrast in image data in order to improve the accuracy of the analysis.

[0476] An "abnormal area" is a region that exhibits different characteristics or structures compared to standard pathological tissue, suggesting the presence of a potential disease or lesion.

[0477] A "case database" is a dataset containing past similar diagnostic results and subsequent progress information, serving as a useful source of information for diagnosis and treatment selection.

[0478] "Medical guidelines" are guidelines that outline standard diagnostic methods and treatment strategies for specific diseases or cases, formulated based on the latest medical research and expert consensus.

[0479] "Analysis results" refer to detailed information about abnormal areas derived from the analysis of image data, and are used for diagnosis and treatment decisions.

[0480] A "health management plan" is a specific action plan proposed to maintain or improve the health status of a patient or resident, based on analysis results and diagnoses.

[0481] To realize this invention, it is necessary to build a system specifically designed for health management in nursing care facilities. This system will function through the coordinated operation of a server, mobile terminals, and users.

[0482] The server first receives microscope images and performs preprocessing for analysis. This preprocessing includes denoising and contrast adjustment of the images. The preprocessed images are then analyzed by an AI model implementing deep learning to identify anomalies. This AI model is typically built using software such as TensorFlow or PyTorch.

[0483] The analysis results are compared with a case database, and a diagnosis is automatically generated. This information, combined with medical guidelines, allows for the suggestion of the most suitable treatment for the patient. The suggested treatment is then compiled into a report in natural language using a generative AI model and sent to the user's mobile device. This enables care staff and medical professionals to use this information to propose specific health management plans for residents.

[0484] As a concrete example, when image data of a resident is sent to the server, the server automatically analyzes this image data and generates a health management plan based on the results. The generated plan is created based on a prompt that reads, "Analyze the health check data of the following patient and generate a health management plan in natural language, comparing it with past cases." By following this prompt and using advanced natural language generation technology, an easily interpretable report is created, enabling efficient health management in nursing facilities.

[0485] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0486] Step 1:

[0487] The server receives microscope image data transmitted from nursing care facilities. Using this received data as input, it performs image noise reduction and contrast adjustment to output image data suitable for analysis. This enables highly accurate identification of abnormal areas.

[0488] Step 2:

[0489] The server inputs pre-processed image data into a deep learning model to identify anomalies. During this process, an AI model built using TensorFlow or PyTorch analyzes the image data and outputs information indicating the anomalies. The analysis detects abnormal patterns and structures within the image.

[0490] Step 3:

[0491] The server compares the analysis results with a case database and generates a diagnosis. Based on the data of abnormal locations obtained as input, it searches the database for similar past cases and makes a diagnosis based on them. This result is highly reliable because it is based on past data.

[0492] Step 4:

[0493] Based on the generated diagnostic results, the server refers to medical guidelines and proposes the optimal treatment method. In this step, it selects the most suitable treatment method from several options according to the characteristics of the abnormal area and outputs it as information for a report.

[0494] Step 5:

[0495] The server uses a generation AI model to construct a natural language report containing the analysis results and proposed treatments, and sends it to the mobile device. The generated report is output in easy-to-understand natural language based on the prompt. An example of a prompt is: "Analyze the health check data of the following patient and generate a health management plan in natural language, comparing it with past cases."

[0496] Step 6:

[0497] Users with terminals (care staff and medical professionals) receive natural language reports sent from the server. Based on these reports, they can review the residents' health management plans and develop specific action plans for implementation.

[0498] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0499] This invention provides an AI system that supports pathological diagnosis in medical settings. In addition to conventional techniques for analyzing and diagnosing microscopic images, it incorporates an emotion engine to enhance the user experience. The system includes a server that receives medical data, preprocesses the images, and then an AI agent that detects abnormal areas. Subsequently, it generates a diagnosis result by comparing it with a case database and proposes the optimal treatment method based on medical guidelines.

[0500] The emotion engine analyzes the emotional states of various users. Based on this analysis, the server selects an appropriate method for presenting diagnostic results and adjusts the interface to suit the user. For example, if the emotion engine detects anxiety or stress in a user, the server takes this information into consideration and prioritizes suggesting reassuring language and treatment options.

[0501] As a concrete example, consider a scenario where a diagnostic report for a cancer patient is generated. The server analyzes the patient's microscopic images and detects abnormal areas indicating cancer cells. Next, it diagnoses the patient by comparing them to past cases and proposes the optimal treatment. If the emotion engine highly values ​​the patient's anxiety, the server generates a report that carefully presents treatment options and also includes advice on psychological support.

[0502] The server sends reports to the user's terminal, enabling healthcare professionals and patients to make situation-appropriate decisions. Furthermore, user responses via the emotion engine are fed back to the AI ​​model as feedback, helping to further improve the system. In this way, the present invention can simultaneously provide advanced diagnostic support and medical support that takes user emotions into consideration.

[0503] The following describes the processing flow.

[0504] Step 1:

[0505] The server receives microscope image data transmitted from medical facilities. The image data is preprocessed, including noise reduction and resolution standardization, to make it easier for AI to process.

[0506] Step 2:

[0507] The server's AI agent analyzes the pre-processed images and uses deep learning algorithms to detect abnormal areas. This analysis marks suspicious lesions, providing the foundational data needed to proceed.

[0508] Step 3:

[0509] The server compares the detected abnormal area data with a database of similar past cases. A statistical model is used to infer the diagnosis and generate a reliable result.

[0510] Step 4:

[0511] Based on the generated diagnostic results, the server selects and proposes the most appropriate treatment method from medical guidelines for the patient's condition. This information is then compiled into a comprehensive treatment plan.

[0512] Step 5:

[0513] The server uses an emotion engine to analyze the user's emotional state. Based on the user's stress and anxiety levels, it adjusts how the results are presented and provides reassuring information.

[0514] Step 6:

[0515] The server compiles the diagnostic results and treatment suggestions into a report using natural language generation technology. The content is then adjusted based on sentiment analysis and delivered from the server to the user's terminal.

[0516] Step 7:

[0517] The system assists users in receiving reports and developing treatment plans while providing appropriate information to patients. User feedback is used by the server to further improve the emotion engine and AI models.

[0518] (Example 2)

[0519] Next, we will describe Example 2. 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."

[0520] Pathological diagnosis in medical settings relies on conventional technologies, resulting in limitations in accuracy and efficiency. Furthermore, there is a lack of means to alleviate the emotional burden on patients receiving diagnoses. Continuous improvement of AI models using feedback on diagnostic results is also insufficient. Therefore, it is necessary to simultaneously achieve more accurate diagnostic support and provide information that considers the user's emotions.

[0521] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0522] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, and means for analyzing the user's emotions using an emotion analysis function. This enables highly accurate diagnostic support and the provision of emotionally sensitive information tailored to the user.

[0523] A "microscope image" is a high-magnification image generated by optical instruments used in medical settings, enabling detailed observation of cells and tissues for pathological diagnosis.

[0524] "Preprocessing" refers to a series of processes performed before data analysis, aimed at removing image noise and adjusting contrast to improve analysis accuracy.

[0525] An "abnormal area" refers to a part that deviates from a standard healthy state or structure, and is an area where lesions, abnormal cells, or other abnormalities are detected through image analysis.

[0526] A "case database" is a collection of information that organizes and stores medical data collected in the past, and it plays a role in providing information about similar medical conditions and treatment outcomes.

[0527] "Medical guidelines" are evidence-based treatment guidelines and recommendations provided as standards for healthcare professionals to perform appropriate medical procedures in clinical practice.

[0528] "Emotional analysis" is a technology for quantifying or classifying a user's emotional state, and is a means of extracting emotional characteristics from data such as text and audio.

[0529] An "AI model" is a computational model formed by an artificial intelligence learning algorithm, and is used to perform predictions, classifications, and optimizations for specific tasks.

[0530] "Feedback" refers to the opinions and reactions received from users, and the provision of information that is used to improve and adjust the system.

[0531] This invention is a system that provides advanced diagnostic support and medical support that takes into account the patient's feelings. It mainly consists of a server, terminals, and users.

[0532] The server processes microscope images received from terminals in medical facilities. This image data undergoes preprocessing such as noise reduction and contrast adjustment. Specifically, open-source image processing software (e.g., OpenCV) is used to improve image quality.

[0533] Subsequently, the server performs image analysis and utilizes deep learning technology to detect abnormal areas. In this process, AI models using machine learning frameworks such as TensorFlow are employed to automatically identify the abnormal parts.

[0534] The analysis results are cross-referenced with a case database. Using an SQL database, the system generates the optimal diagnosis based on similar past cases. Based on the diagnosis, the server selects the recommended treatment, referencing medical guidelines. This process enables evidence-based treatment recommendations.

[0535] Furthermore, the server utilizes an emotion analysis engine to evaluate the user's emotions obtained from the device and other data. It uses natural language processing algorithms to analyze the emotional state from the user's text and voice.

[0536] As a result, the server generates a report that takes emotional states into account and provides feedback to the user using reassuring language. The generated report is output in PDF or HTML format and securely sent to the terminal.

[0537] As a concrete example, consider the diagnostic process for cancer patients. After detecting abnormal sites indicating cancer cells, the optimal treatment method is proposed by comparing them with past cases. If emotional analysis reveals that the patient is showing high levels of anxiety, the server explains the treatment method in reassuring language and provides a report that includes advice on psychological support.

[0538] An example of a prompt for the generating AI model is, "Generate treatment suggestions that take patient anxiety into consideration, based on cancer case data." In this way, the system integrates technical support in medical diagnosis with human-centered emotional care.

[0539] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0540] Step 1:

[0541] The server receives microscope images from terminals installed in medical facilities. This received image data is stored in a format suitable for diagnostic analysis. The input here is raw microscope image data, and the output is image data subject to preprocessing.

[0542] Step 2:

[0543] The server performs image preprocessing. Specifically, it removes noise and adjusts contrast using algorithms from open-source libraries. This process improves image quality and increases the accuracy of AI analysis. The input is the preprocessed image data obtained in step 1, and the output is the preprocessed, high-quality image data.

[0544] Step 3:

[0545] The server analyzes pre-processed image data using an AI agent. A deep learning model, such as TensorFlow, identifies abnormal areas in the input image. The input is pre-processed image data, and the output is the analysis result showing the abnormal areas.

[0546] Step 4:

[0547] The server compares the analysis results with the case database. It uses SQL queries to search past case information and generates diagnostic results corresponding to the abnormal areas. This comparison provides the most relevant case information to be used as a basis for judgment. The input is the analysis results, and the output is the confirmed diagnostic result.

[0548] Step 5:

[0549] Based on the diagnostic results, the server refers to medical guidelines and presents recommended treatments. It performs comparative calculations with the treatment procedures described in the guidelines to select the optimal treatment. The input is the diagnostic result, and the output is a suggested treatment plan.

[0550] Step 6:

[0551] The server uses an emotion engine to analyze the user's emotional state. It applies natural language processing to analyze text or audio data from the terminal to determine the user's emotions. The input is the user's text or audio data, and the output is the result of the emotion analysis.

[0552] Step 7:

[0553] The server generates a report designed to provide reassurance based on the sentiment analysis results. Using natural language generation technology, it explains the diagnosis and treatment plan in a way that is appropriate for the user. Inputs include the diagnosis results, recommended treatment plan, and sentiment analysis results, while output is an emotionally sensitive diagnosis report.

[0554] Step 8:

[0555] The server sends the generated report to the terminal. The terminal user makes decisions as a healthcare professional based on the received report. The input is an emotionally sensitive diagnostic report, and the output is a diagnostic report displayed on the user's terminal.

[0556] (Application Example 2)

[0557] Next, we will explain application example 2. In the following explanation, 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."

[0558] In modern medical settings, while highly accurate pathological diagnoses are demanded, the psychological burden on patients and healthcare professionals remains a challenge. In particular, appropriate communication that takes into account patients' anxiety and stress is essential during the diagnostic process. However, existing technologies do not adequately address these psychological aspects, increasing the burden on healthcare professionals. Therefore, a system is needed that can improve diagnostic accuracy while simultaneously providing psychological care for patients and healthcare professionals.

[0559] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0560] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, means for generating diagnostic results by comparing them with a database of past cases, means for suggesting appropriate treatment methods by referring to medical guidelines, means for creating reports using natural language generation technology, means for analyzing emotional states, means for adjusting the interface according to emotional states, means for making suggestions to provide psychological support to the user, and means for providing feedback to train an AI model. This makes it possible to improve diagnostic accuracy and reduce the psychological burden on the user.

[0561] A "microscope image" is image data of a fine structure obtained using a microscope.

[0562] "Preprocessing" refers to the initial processing operations performed to make microscope images easier to analyze.

[0563] An "abnormal area" refers to a part of a microscopic image that is different from normal, indicating a lesion or abnormality.

[0564] A "case database" is a collection of data that systematically collects and stores past patient information and diagnostic results.

[0565] A "diagnosis" is a decision or judgment regarding a patient's health status, obtained by comparing it with case data.

[0566] "Medical guidelines" are guidelines that show the appropriate methods for performing medical procedures.

[0567] "Natural language generation technology" is a technology that enables computers to generate text in human language.

[0568] "Emotional state" refers to elements that indicate an individual's current psychological and emotional condition.

[0569] An "interface" refers to the means or environment for exchanging information between a system and a user.

[0570] "Psychological support" refers to advice and care provided to maintain or improve an individual's mental health.

[0571] "Feedback" is the process by which data and responses entered into a system are used to improve or adapt that system.

[0572] The system that realizes this invention consists of a server, a user terminal, and a series of programs that use an emotion analysis algorithm.

[0573] The server first receives microscope images and then preprocesses them. This preprocessing includes noise reduction and image shaping to prepare the images for highly accurate pathological diagnosis. The data obtained through this process is then subjected to analysis using advanced deep learning algorithms to identify abnormal areas. This ensures accurate detection of areas deemed pathologically abnormal.

[0574] Next, the server compares the detected abnormal areas with past cases in the database and generates a diagnosis. At this point, it also refers to relevant medical guidelines and suggests the optimal treatment. The generated diagnosis and treatment are compiled into a report using natural language generation technology. This technology is essential for providing information in a format that is easy for users to understand.

[0575] Furthermore, the server integrates emotion analysis capabilities. This allows for the analysis of the user's emotional state and real-time assessment of their psychological condition. Based on the analysis results, the interface is adjusted and psychological support is suggested. This may include, for example, the presentation of relaxing content and guidance on stress reduction measures. User feedback is also sent to the server and used for the continuous learning and improvement of the AI ​​model.

[0576] As a concrete example, in the diagnostic process for cancer patients, after microscopic image analysis, a diagnostic result is generated based on that analysis, and a report is presented in an interface tailored to the patient's emotional state. If the emotional analysis detects anxiety, the server presents treatment options using language that is particularly reassuring. Furthermore, if the need for psychological support is determined, related actions are recommended.

[0577] An example of a prompt statement is: "Describe the algorithm of an application that detects signs of stress and anxiety from the facial expressions and voice of elderly individuals through an emotion engine, and notifies care staff in real time with care suggestions." This enables continuous care that takes emotional states into account.

[0578] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0579] Step 1:

[0580] The server receives image data acquired from the microscope. This data is used as input for preprocessing to remove noise and enhance clarity. The preprocessed image data is then shaped into an output format suitable for detecting abnormal areas.

[0581] Step 2:

[0582] The server inputs the pre-processed image data into a deep learning algorithm. This algorithm uses a pre-trained model to detect potentially abnormal areas in the image and outputs them. Detailed coordinate information and characteristics of the abnormal areas are obtained.

[0583] Step 3:

[0584] The server cross-references the detected abnormal area information with a case database. This cross-referencing searches for similar past cases and outputs corresponding diagnostic results and treatment information. This process is implemented through database queries.

[0585] Step 4:

[0586] The server uses natural language generation technology to create a report based on the diagnostic results and treatment information obtained through matching. This process generates text-based information, which is output in an easily understandable format.

[0587] Step 5:

[0588] The server executes an emotion analysis algorithm to analyze the user's emotional state. Facial expression data and voice data acquired from the user's terminal are input, stress and anxiety are detected, and the analysis results are output.

[0589] Step 6:

[0590] Based on the sentiment analysis results, the server adjusts the user interface and the way reports are presented. This adjustment suggests appropriate wording and reassuring content to reduce psychological burden.

[0591] Step 7:

[0592] The server collects user feedback and feeds it to the AI ​​model. This feedback is used as data to improve the accuracy of subsequent analyses and interface adjustments.

[0593] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0594] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0595] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0596] [Fourth Embodiment]

[0597] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0598] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0599] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0600] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0601] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0602] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0603] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0604] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0605] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0606] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0607] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0608] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0609] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0610] This invention is implemented as an AI-based system to support pathological diagnosis in medical settings. This system allows for highly accurate detection of abnormal areas by having a server receive medical data, such as microscope images, perform preprocessing, and then having an AI agent analyze the data. This process helps medical professionals make rapid and accurate diagnoses.

[0611] The server compares the analyzed image data with an existing case database to generate a diagnosis. This provides an objective diagnosis based on similar past cases. The server also refers to the latest medical guidelines to suggest the most appropriate treatment for the patient. This information is compiled into a report using natural language generation technology and delivered to the user or device.

[0612] As a concrete example, consider a scenario where a CT scan image of a patient suspected of having lung cancer is sent to a server. The server analyzes this image to identify the location and size of the tumor within the lung. Next, based on past case data, it diagnoses the lesion as small cell lung cancer. Based on these results, a chemotherapy plan in accordance with the latest treatment guidelines is proposed. The report is generated in natural language and provided in a format that allows physicians to discuss the detailed treatment plan with the patient.

[0613] The server updates the AI ​​model based on continuous feedback, improving the accuracy of medical image analysis. This information is accessible on the user's terminal, contributing to the efficiency of medical treatment. In this way, the present invention enables the optimization of medical processes and realizes a form that dramatically improves the accuracy and efficiency of pathological diagnosis.

[0614] The following describes the processing flow.

[0615] Step 1:

[0616] The server automatically reads microscope images and CT scan images received from medical institutions. After receiving the images, it performs preprocessing to remove noise and convert them into a format that is easy for AI to analyze.

[0617] Step 2:

[0618] The server's AI agent performs abnormal area detection based on the pre-processed images. Using a deep learning algorithm, it identifies potentially diseased areas at the pixel level and visually highlights them.

[0619] Step 3:

[0620] The server compares the detected abnormal area information with an existing case database. It references past similar case data and applies a statistical model to generate a diagnosis.

[0621] Step 4:

[0622] The system uses the diagnostic results generated by the server to automatically suggest appropriate treatment methods based on medical guidelines. The suggested treatments are customized according to the patient's individual health condition.

[0623] Step 5:

[0624] The server integrates the diagnostic results and suggested treatments, and generates a detailed report using natural language generation technology. This report includes the location of any lesions found and recommended treatment options.

[0625] Step 6:

[0626] The server sends the generated report to the terminal. As a result, the user, a medical professional, can review the diagnostic results and obtain the information needed to develop the best treatment plan for the patient.

[0627] Step 7:

[0628] The server leverages a feedback loop to supply new diagnostic results and treatment outcomes to the AI ​​model, continuously improving the accuracy of the algorithm.

[0629] (Example 1)

[0630] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0631] In medical settings, rapid and accurate pathological diagnosis is crucial, but image data noise and complex diagnostic processes can be obstacles. Furthermore, there is a need for objective diagnoses based on comparisons with past cases and for treatment methods based on the latest medical standards. Additionally, there is a need for a method to provide generated diagnostic results in natural language reports, allowing users to efficiently utilize the information.

[0632] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0633] In this invention, the server includes means for receiving and pre-processing image information, means for analyzing the pre-processed image information and detecting abnormal elements, means for comparing it with a database of past cases and generating analysis results, means for proposing appropriate treatment methods by referring to medical standards, means for creating reports using natural language generation technology, means for conducting evaluations to update the learning model, and means for displaying processing progress and notifying information. This enables rapid and objective diagnosis and proposal of treatment methods, and allows medical professionals to make appropriate decisions by utilizing the generated information.

[0634] "Image information" refers to visual data acquired for use in medical or scientific analysis, including microscopic images and CT scan images.

[0635] "Preprocessing" refers to the process of adjusting data to a state suitable for analysis, and includes steps such as noise reduction and standardization.

[0636] "Abnormal elements" refer to characteristics of cells or tissues that deviate from a normal state, and are the parts that are subject to pathological diagnosis.

[0637] A "case database" is a source of information that collects data on past medical cases and patient data, and is used for matching and analyzing diagnostic results.

[0638] "Medical standards" refer to guidelines and protocols for diagnosis and treatment, and serve as the criteria for applying the treatment methods provided to patients.

[0639] "Natural language generation technology" is a technology that allows computers to represent information using human language, and is used for creating reports and explanatory texts.

[0640] A "learning model" is a computational model that learns patterns from data using machine learning algorithms, and its purpose is to improve the accuracy of analysis.

[0641] "Means for displaying progress and notifying information" refers to interfaces and functions for communicating the current progress and results of data processing to the user.

[0642] This invention relates to a system for supporting diagnosis in the medical field. Specific embodiments thereof are described below.

[0643] The server receives image information from medical institutions, such as microscope images and CT scan images. This image information is crucial for accurate diagnosis, and the server first performs data preprocessing. At this stage, noise is removed from the images, and contrast and brightness are adjusted to appropriate levels. The preprocessed data is then analyzed by an AI agent using a general-purpose machine learning framework such as TensorFlow, which runs on common hardware. The analysis identifies abnormal elements, which are then used to efficiently aid in diagnosis.

[0644] Subsequently, the server accesses an SQL database built to compare the analysis results with a case database. In this process, the server reinforces the diagnosis based on past case information, supporting objective decision-making. Once the comparison is complete, the server proposes the optimal treatment method based on medical guidelines. This information is compiled into a report using natural language generation technology and delivered to the terminal. The user can then easily use this to explain the situation to the patient.

[0645] As a concrete example, consider a case where an image of a patient with lung abnormalities is sent to the server. The server analyzes the image and detects the shape and location of the abnormal shadow. Next, by comparing this with a case database, it diagnoses the possibility of small cell lung cancer and proposes appropriate chemotherapy. This information is generated as a natural language report and provided to the user.

[0646] An example of a prompt for a generative AI model is: "Analyze the patient's lung CT scan, describe the tumor details, and generate a report suggesting the best treatment options."

[0647] As described above, this system supports the efficiency and accuracy of diagnosis in medical settings, helping healthcare professionals make objective and rapid decisions.

[0648] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0649] Step 1:

[0650] The server receives image information transmitted from medical institutions. Input includes microscope images and CT scan images, which the server stores in its data storage. Next, it removes noise from the received raw data and standardizes the image contrast and brightness. This prepares the data for easier image analysis. The output is pre-processed image information.

[0651] Step 2:

[0652] The server passes pre-processed image information to the AI ​​agent. The input here is the pre-processed image, which is analyzed by a neural network using TensorFlow. The server analyzes each pixel and identifies abnormal elements. This process calculates the location and size of the abnormal areas. The output is the analysis result with the abnormal areas identified.

[0653] Step 3:

[0654] The server uses the analysis results as queries to access the case database. The input includes data that is considered characteristic information of the abnormal elements, and the server compares it with past case information stored in the SQL database. This searches for similar past cases and retrieves information to reinforce the diagnosis. The output is diagnostic information compared with past cases.

[0655] Step 4:

[0656] The server consults a medical guideline database based on the diagnostic information obtained through matching. The input includes diagnostic information, and the server performs calculations to propose the most suitable treatment method based on the corresponding guidelines. As a result, a list of candidate treatment methods deemed medically appropriate is generated. The output is information on the proposed treatment methods.

[0657] Step 5:

[0658] The server integrates the generated diagnostic information and treatment methods, and creates a report using natural language generation technology. The input consists of diagnostic information and suggested treatment methods, which the server uses to create a natural language report based on a generative AI model such as GPT-3. The output is a report presented in a format easily understood by users and healthcare professionals.

[0659] Step 6:

[0660] The terminal receives the provided report and notifies the user. The input here is the generated report, which the terminal visualizes and displays. The user reviews the report and uses the diagnostic results and treatment methods to make decisions in the medical setting. The output is the detailed diagnostic report actually displayed on the screen.

[0661] (Application Example 1)

[0662] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] In nursing care settings, efficiently managing residents' health and promptly proposing appropriate treatments is often challenging. There is a need for support systems that enable even care staff without medical expertise to perform highly accurate health management. To address this, a system is needed that can accurately identify abnormalities and quickly propose treatments based on past cases and medical guidelines.

[0664] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0665] In this invention, the server includes means for acquiring microscopic images and performing data preprocessing, means for analyzing the preprocessed images and identifying abnormal areas, means for outputting diagnostic results by comparing them with a case database, means for proposing appropriate treatment methods based on medical guidelines, and means for providing the analysis results as a health management plan according to the care setting. This enables the rapid provision of highly accurate health checkup results and the automatic proposal of individual medical plans for residents, even in care facilities.

[0666] A "microscope image" is image data showing fine structures, captured using an optical microscope or an electron microscope.

[0667] "Data preprocessing" is the process of removing noise and adjusting contrast in image data in order to improve the accuracy of the analysis.

[0668] An "abnormal area" is a region that exhibits different characteristics or structures compared to standard pathological tissue, suggesting the presence of a potential disease or lesion.

[0669] A "case database" is a dataset containing past similar diagnostic results and subsequent progress information, serving as a useful source of information for diagnosis and treatment selection.

[0670] "Medical guidelines" are guidelines that outline standard diagnostic methods and treatment strategies for specific diseases or cases, formulated based on the latest medical research and expert consensus.

[0671] "Analysis results" refer to detailed information about abnormal areas derived from the analysis of image data, and are used for diagnosis and treatment decisions.

[0672] A "health management plan" is a specific action plan proposed to maintain or improve the health status of a patient or resident, based on analysis results and diagnoses.

[0673] To realize this invention, it is necessary to build a system specifically designed for health management in nursing care facilities. This system will function through the coordinated operation of a server, mobile terminals, and users.

[0674] The server first receives microscope images and performs preprocessing for analysis. This preprocessing includes denoising and contrast adjustment of the images. The preprocessed images are then analyzed by an AI model implementing deep learning to identify anomalies. This AI model is typically built using software such as TensorFlow or PyTorch.

[0675] The analysis results are compared with a case database, and a diagnosis is automatically generated. This information, combined with medical guidelines, allows for the suggestion of the most suitable treatment for the patient. The suggested treatment is then compiled into a report in natural language using a generative AI model and sent to the user's mobile device. This enables care staff and medical professionals to use this information to propose specific health management plans for residents.

[0676] As a concrete example, when image data of a resident is sent to the server, the server automatically analyzes this image data and generates a health management plan based on the results. The generated plan is created based on a prompt that reads, "Analyze the health check data of the following patient and generate a health management plan in natural language, comparing it with past cases." By following this prompt and using advanced natural language generation technology, an easily interpretable report is created, enabling efficient health management in nursing facilities.

[0677] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0678] Step 1:

[0679] The server receives microscope image data transmitted from nursing care facilities. Using this received data as input, it performs image noise reduction and contrast adjustment to output image data suitable for analysis. This enables highly accurate identification of abnormal areas.

[0680] Step 2:

[0681] The server inputs pre-processed image data into a deep learning model to identify anomalies. During this process, an AI model built using TensorFlow or PyTorch analyzes the image data and outputs information indicating the anomalies. The analysis detects abnormal patterns and structures within the image.

[0682] Step 3:

[0683] The server compares the analysis results with a case database and generates a diagnosis. Based on the data of abnormal locations obtained as input, it searches the database for similar past cases and makes a diagnosis based on them. This result is highly reliable because it is based on past data.

[0684] Step 4:

[0685] Based on the generated diagnostic results, the server refers to medical guidelines and proposes the optimal treatment method. In this step, it selects the most suitable treatment method from several options according to the characteristics of the abnormal area and outputs it as information for a report.

[0686] Step 5:

[0687] The server uses a generation AI model to construct a natural language report containing the analysis results and proposed treatments, and sends it to the mobile device. The generated report is output in easy-to-understand natural language based on the prompt. An example of a prompt is: "Analyze the health check data of the following patient and generate a health management plan in natural language, comparing it with past cases."

[0688] Step 6:

[0689] Users with terminals (care staff and medical professionals) receive natural language reports sent from the server. Based on these reports, they can review the residents' health management plans and develop specific action plans for implementation.

[0690] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0691] This invention provides an AI system that supports pathological diagnosis in medical settings. In addition to conventional techniques for analyzing and diagnosing microscopic images, it incorporates an emotion engine to enhance the user experience. The system includes a server that receives medical data, preprocesses the images, and then an AI agent that detects abnormal areas. Subsequently, it generates a diagnosis result by comparing it with a case database and proposes the optimal treatment method based on medical guidelines.

[0692] The emotion engine analyzes the emotional states of various users. Based on this analysis, the server selects an appropriate method for presenting diagnostic results and adjusts the interface to suit the user. For example, if the emotion engine detects anxiety or stress in a user, the server takes this information into consideration and prioritizes suggesting reassuring language and treatment options.

[0693] As a concrete example, consider a scenario where a diagnostic report for a cancer patient is generated. The server analyzes the patient's microscopic images and detects abnormal areas indicating cancer cells. Next, it diagnoses the patient by comparing them to past cases and proposes the optimal treatment. If the emotion engine highly values ​​the patient's anxiety, the server generates a report that carefully presents treatment options and also includes advice on psychological support.

[0694] The server sends reports to the user's terminal, enabling healthcare professionals and patients to make situation-appropriate decisions. Furthermore, user responses via the emotion engine are fed back to the AI ​​model as feedback, helping to further improve the system. In this way, the present invention can simultaneously provide advanced diagnostic support and medical support that takes user emotions into consideration.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] The server receives microscope image data transmitted from medical facilities. The image data is preprocessed, including noise reduction and resolution standardization, to make it easier for AI to process.

[0698] Step 2:

[0699] The server's AI agent analyzes the pre-processed images and uses deep learning algorithms to detect abnormal areas. This analysis marks suspicious lesions, providing the foundational data needed to proceed.

[0700] Step 3:

[0701] The server compares the detected abnormal area data with a database of similar past cases. A statistical model is used to infer the diagnosis and generate a reliable result.

[0702] Step 4:

[0703] Based on the generated diagnostic results, the server selects and proposes the most appropriate treatment method from medical guidelines for the patient's condition. This information is then compiled into a comprehensive treatment plan.

[0704] Step 5:

[0705] The server uses an emotion engine to analyze the user's emotional state. Based on the user's stress and anxiety levels, it adjusts how the results are presented and provides reassuring information.

[0706] Step 6:

[0707] The server compiles the diagnostic results and treatment suggestions into a report using natural language generation technology. The content is then adjusted based on sentiment analysis and delivered from the server to the user's terminal.

[0708] Step 7:

[0709] The system assists users in receiving reports and developing treatment plans while providing appropriate information to patients. User feedback is used by the server to further improve the emotion engine and AI models.

[0710] (Example 2)

[0711] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0712] Pathological diagnosis in medical settings relies on conventional technologies, resulting in limitations in accuracy and efficiency. Furthermore, there is a lack of means to alleviate the emotional burden on patients receiving diagnoses. Continuous improvement of AI models using feedback on diagnostic results is also insufficient. Therefore, it is necessary to simultaneously achieve more accurate diagnostic support and provide information that considers the user's emotions.

[0713] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0714] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, and means for analyzing the user's emotions using an emotion analysis function. This enables highly accurate diagnostic support and the provision of emotionally sensitive information tailored to the user.

[0715] A "microscope image" is a high-magnification image generated by optical instruments used in medical settings, enabling detailed observation of cells and tissues for pathological diagnosis.

[0716] "Preprocessing" refers to a series of processes performed before data analysis, aimed at removing image noise and adjusting contrast to improve analysis accuracy.

[0717] An "abnormal area" refers to a part that deviates from a standard healthy state or structure, and is an area where lesions, abnormal cells, or other abnormalities are detected through image analysis.

[0718] A "case database" is a collection of information that organizes and stores medical data collected in the past, and it plays a role in providing information about similar medical conditions and treatment outcomes.

[0719] "Medical guidelines" are evidence-based treatment guidelines and recommendations provided as standards for healthcare professionals to perform appropriate medical procedures in clinical practice.

[0720] "Emotional analysis" is a technology for quantifying or classifying a user's emotional state, and is a means of extracting emotional characteristics from data such as text and audio.

[0721] An "AI model" is a computational model formed by an artificial intelligence learning algorithm, and is used to perform predictions, classifications, and optimizations for specific tasks.

[0722] "Feedback" refers to the opinions and reactions received from users, and the provision of information that is used to improve and adjust the system.

[0723] This invention is a system that provides advanced diagnostic support and medical support that takes into account the patient's feelings. It mainly consists of a server, terminals, and users.

[0724] The server processes microscope images received from terminals in medical facilities. This image data undergoes preprocessing such as noise reduction and contrast adjustment. Specifically, open-source image processing software (e.g., OpenCV) is used to improve image quality.

[0725] Subsequently, the server performs image analysis and utilizes deep learning technology to detect abnormal areas. In this process, AI models using machine learning frameworks such as TensorFlow are employed to automatically identify the abnormal parts.

[0726] The analysis results are cross-referenced with a case database. Using an SQL database, the system generates the optimal diagnosis based on similar past cases. Based on the diagnosis, the server selects the recommended treatment, referencing medical guidelines. This process enables evidence-based treatment recommendations.

[0727] Furthermore, the server utilizes an emotion analysis engine to evaluate the user's emotions obtained from the device and other data. It uses natural language processing algorithms to analyze the emotional state from the user's text and voice.

[0728] As a result, the server generates a report that takes emotional states into account and provides feedback to the user using reassuring language. The generated report is output in PDF or HTML format and securely sent to the terminal.

[0729] As a concrete example, consider the diagnostic process for cancer patients. After detecting abnormal sites indicating cancer cells, the optimal treatment method is proposed by comparing them with past cases. If emotional analysis reveals that the patient is showing high levels of anxiety, the server explains the treatment method in reassuring language and provides a report that includes advice on psychological support.

[0730] An example of a prompt for the generating AI model is, "Generate treatment suggestions that take patient anxiety into consideration, based on cancer case data." In this way, the system integrates technical support in medical diagnosis with human-centered emotional care.

[0731] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0732] Step 1:

[0733] The server receives microscope images from terminals installed in medical facilities. This received image data is stored in a format suitable for diagnostic analysis. The input here is raw microscope image data, and the output is image data subject to preprocessing.

[0734] Step 2:

[0735] The server performs image preprocessing. Specifically, it removes noise and adjusts contrast using algorithms from open-source libraries. This process improves image quality and increases the accuracy of AI analysis. The input is the preprocessed image data obtained in step 1, and the output is the preprocessed, high-quality image data.

[0736] Step 3:

[0737] The server analyzes pre-processed image data using an AI agent. A deep learning model, such as TensorFlow, identifies abnormal areas in the input image. The input is pre-processed image data, and the output is the analysis result showing the abnormal areas.

[0738] Step 4:

[0739] The server compares the analysis results with the case database. It uses SQL queries to search past case information and generates diagnostic results corresponding to the abnormal areas. This comparison provides the most relevant case information to be used as a basis for judgment. The input is the analysis results, and the output is the confirmed diagnostic result.

[0740] Step 5:

[0741] Based on the diagnostic results, the server refers to medical guidelines and presents recommended treatments. It performs comparative calculations with the treatment procedures described in the guidelines to select the optimal treatment. The input is the diagnostic result, and the output is a suggested treatment plan.

[0742] Step 6:

[0743] The server uses an emotion engine to analyze the user's emotional state. It applies natural language processing to analyze text or audio data from the terminal to determine the user's emotions. The input is the user's text or audio data, and the output is the result of the emotion analysis.

[0744] Step 7:

[0745] The server generates a report designed to provide reassurance based on the sentiment analysis results. Using natural language generation technology, it explains the diagnosis and treatment plan in a way that is appropriate for the user. Inputs include the diagnosis results, recommended treatment plan, and sentiment analysis results, while output is an emotionally sensitive diagnosis report.

[0746] Step 8:

[0747] The server sends the generated report to the terminal. The terminal user makes decisions as a healthcare professional based on the received report. The input is an emotionally sensitive diagnostic report, and the output is a diagnostic report displayed on the user's terminal.

[0748] (Application Example 2)

[0749] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0750] In modern medical settings, while highly accurate pathological diagnoses are demanded, the psychological burden on patients and healthcare professionals remains a challenge. In particular, appropriate communication that takes into account patients' anxiety and stress is essential during the diagnostic process. However, existing technologies do not adequately address these psychological aspects, increasing the burden on healthcare professionals. Therefore, a system is needed that can improve diagnostic accuracy while simultaneously providing psychological care for patients and healthcare professionals.

[0751] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0752] In this invention, the server includes means for receiving and pre-processing microscope images, means for analyzing the pre-processed images and detecting abnormal areas, means for generating diagnostic results by comparing them with a database of past cases, means for suggesting appropriate treatment methods by referring to medical guidelines, means for creating reports using natural language generation technology, means for analyzing emotional states, means for adjusting the interface according to emotional states, means for making suggestions to provide psychological support to the user, and means for providing feedback to train an AI model. This makes it possible to improve diagnostic accuracy and reduce the psychological burden on the user.

[0753] A "microscope image" is image data of a fine structure obtained using a microscope.

[0754] "Preprocessing" refers to the initial processing operations performed to make microscope images easier to analyze.

[0755] An "abnormal area" refers to a part of a microscopic image that is different from normal, indicating a lesion or abnormality.

[0756] A "case database" is a collection of data that systematically collects and stores past patient information and diagnostic results.

[0757] A "diagnosis" is a decision or judgment regarding a patient's health status, obtained by comparing it with case data.

[0758] "Medical guidelines" are guidelines that show the appropriate methods for performing medical procedures.

[0759] "Natural language generation technology" is a technology that enables computers to generate text in human language.

[0760] "Emotional state" refers to elements that indicate an individual's current psychological and emotional condition.

[0761] An "interface" refers to the means or environment for exchanging information between a system and a user.

[0762] "Psychological support" refers to advice and care provided to maintain or improve an individual's mental health.

[0763] "Feedback" is the process by which data and responses entered into a system are used to improve or adapt that system.

[0764] The system that realizes this invention consists of a server, a user terminal, and a series of programs that use an emotion analysis algorithm.

[0765] The server first receives microscope images and then preprocesses them. This preprocessing includes noise reduction and image shaping to prepare the images for highly accurate pathological diagnosis. The data obtained through this process is then subjected to analysis using advanced deep learning algorithms to identify abnormal areas. This ensures accurate detection of areas deemed pathologically abnormal.

[0766] Next, the server compares the detected abnormal areas with past cases in the database and generates a diagnosis. At this point, it also refers to relevant medical guidelines and suggests the optimal treatment. The generated diagnosis and treatment are compiled into a report using natural language generation technology. This technology is essential for providing information in a format that is easy for users to understand.

[0767] Furthermore, the server integrates emotion analysis capabilities. This allows for the analysis of the user's emotional state and real-time assessment of their psychological condition. Based on the analysis results, the interface is adjusted and psychological support is suggested. This may include, for example, the presentation of relaxing content and guidance on stress reduction measures. User feedback is also sent to the server and used for the continuous learning and improvement of the AI ​​model.

[0768] As a concrete example, in the diagnostic process for cancer patients, after microscopic image analysis, a diagnostic result is generated based on that analysis, and a report is presented in an interface tailored to the patient's emotional state. If the emotional analysis detects anxiety, the server presents treatment options using language that is particularly reassuring. Furthermore, if the need for psychological support is determined, related actions are recommended.

[0769] An example of a prompt statement is: "Describe the algorithm of an application that detects signs of stress and anxiety from the facial expressions and voice of elderly individuals through an emotion engine, and notifies care staff in real time with care suggestions." This enables continuous care that takes emotional states into account.

[0770] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0771] Step 1:

[0772] The server receives image data acquired from the microscope. This data is used as input for preprocessing to remove noise and enhance clarity. The preprocessed image data is then shaped into an output format suitable for detecting abnormal areas.

[0773] Step 2:

[0774] The server inputs the pre-processed image data into a deep learning algorithm. This algorithm uses a pre-trained model to detect potentially abnormal areas in the image and outputs them. Detailed coordinate information and characteristics of the abnormal areas are obtained.

[0775] Step 3:

[0776] The server cross-references the detected abnormal area information with a case database. This cross-referencing searches for similar past cases and outputs corresponding diagnostic results and treatment information. This process is implemented through database queries.

[0777] Step 4:

[0778] The server uses natural language generation technology to create a report based on the diagnostic results and treatment information obtained through matching. This process generates text-based information, which is output in an easily understandable format.

[0779] Step 5:

[0780] The server executes an emotion analysis algorithm to analyze the user's emotional state. Facial expression data and voice data acquired from the user's terminal are input, stress and anxiety are detected, and the analysis results are output.

[0781] Step 6:

[0782] Based on the sentiment analysis results, the server adjusts the user interface and the way reports are presented. This adjustment suggests appropriate wording and reassuring content to reduce psychological burden.

[0783] Step 7:

[0784] The server collects user feedback and feeds it to the AI ​​model. This feedback is used as data to improve the accuracy of subsequent analyses and interface adjustments.

[0785] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0786] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0788] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0789] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0790] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0791] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0792] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0793] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0794] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0795] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0796] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0797] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0798] 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.

[0799] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0800] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0801] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0802] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0803] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0804] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0805] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0806] The following is further disclosed regarding the embodiments described above.

[0807] (Claim 1)

[0808] A means for receiving and pre-processing microscope images,

[0809] A means for analyzing pre-processed images and detecting abnormal areas,

[0810] A means of generating diagnostic results by comparing them with a database of past cases,

[0811] A means of proposing appropriate treatment methods by referring to medical guidelines,

[0812] A method for creating a report using natural language generation technology,

[0813] A means of providing feedback to train an AI model,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1 for denoising image data before preprocessing.

[0817] (Claim 3)

[0818] The system according to claim 1, which uses a deep learning algorithm when detecting abnormal parts.

[0819] "Example 1"

[0820] (Claim 1)

[0821] A means for receiving and pre-processing image information,

[0822] A means for analyzing pre-processed image information and detecting abnormal elements,

[0823] A means of generating analysis results by comparing them with a database of past cases,

[0824] A means of proposing appropriate treatment methods by referring to medical standards,

[0825] A means of creating a report using natural language generation technology,

[0826] A means of conducting evaluations to update the learning model,

[0827] A means of displaying processing progress and notifying information,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1 for denoising image information before preprocessing.

[0831] (Claim 3)

[0832] The system according to claim 1, which uses deep learning technology when detecting anomaly elements.

[0833] "Application Example 1"

[0834] (Claim 1)

[0835] A means for acquiring microscope images and performing data preprocessing,

[0836] A means for analyzing pre-processed images and identifying abnormal areas,

[0837] A means of outputting diagnostic results by comparing them with a case database,

[0838] A means of proposing appropriate treatment methods based on medical guidelines,

[0839] A means of constructing a document using natural language generation technology,

[0840] A means of providing feedback to train an AI model,

[0841] A means of providing analysis results as a health management plan tailored to the caregiving setting,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1 for denoising medical data before preprocessing.

[0845] (Claim 3)

[0846] The system according to claim 1, which uses a deep learning algorithm to identify abnormal locations.

[0847] "Example 2 of combining an emotion engine"

[0848] (Claim 1)

[0849] A means for receiving and pre-processing microscope images,

[0850] A means for analyzing pre-processed images and detecting abnormal areas,

[0851] A means of generating diagnostic results by comparing them with a database of past cases,

[0852] A means of proposing appropriate treatment methods by referring to medical guidelines,

[0853] A means of analyzing the user's emotions using emotion analysis functionality,

[0854] A means of presenting adaptive diagnostic information based on the analysis results,

[0855] A method for creating a report using natural language generation technology,

[0856] A means of providing feedback to train an AI model,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1 for denoising image data before preprocessing.

[0860] (Claim 3)

[0861] The system according to claim 1, which uses a deep learning algorithm when detecting abnormal parts.

[0862] "Application example 2 when combining with an emotional engine"

[0863] (Claim 1)

[0864] A means for receiving and pre-processing microscope images,

[0865] A means for analyzing pre-processed images and detecting abnormal areas,

[0866] A means of generating diagnostic results by comparing them with a database of past cases,

[0867] A means of proposing appropriate treatment methods by referring to medical guidelines,

[0868] A method for creating a report using natural language generation technology,

[0869] A means of analyzing emotional states,

[0870] A means of adjusting the interface according to emotional state,

[0871] A means of offering psychological support to users,

[0872] A means of providing feedback to train an AI model,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1 for denoising image data before preprocessing.

[0876] (Claim 3)

[0877] The system according to claim 1, which uses a deep learning algorithm when detecting abnormal parts. [Explanation of symbols]

[0878] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving and pre-processing microscope images, A means for analyzing pre-processed images and detecting abnormal areas, A means of generating diagnostic results by comparing them with a database of past cases, A means of proposing appropriate treatment methods by referring to medical guidelines, A method for creating a report using natural language generation technology, A means of providing feedback to train an AI model, A system that includes this.

2. The system according to claim 1 for denoising image data before preprocessing.

3. The system according to claim 1, which uses a deep learning algorithm when detecting abnormal parts.

Images