system

Abstract

We provide the system. [Solution] Information gathering means for collecting and integrating biomedical information, An information analysis means for extracting biomedical patterns by applying a machine learning algorithm to the integrated information, Access management means to enhance the authentication process based on the extracted pattern, A repositioning method that explores applicability from multiple information resources, A decision-making support tool that proposes the optimal treatment method based on individual subject information, 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 method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present invention aims to improve the efficiency of the therapeutic drug development process for rare and intractable diseases. There are various problems in the development of therapeutic drugs for these diseases, such as the difficulty of clinical trials due to the small number of patients, the insufficient understanding of disease mechanisms, and the high development costs. Conventional methods require a great deal of time and resources for the identification and development of therapeutic drugs, and have not sufficiently responded to many diseases that require urgent countermeasures.

Means for Solving the Problems

[0005] This invention solves the above problems by providing a system that makes full use of AI technology. This system includes means for collecting and integrating biomedical data, means for extracting biomedical patterns by applying machine learning algorithms, means for identifying patients for clinical trials based on the extracted patterns, means for analyzing existing drug libraries to explore new applicability, and means for proposing optimal treatment methods based on individual patient information. This will accelerate the drug development process and enable the provision of personalized and effective treatments for patients.

[0006] "Biomedical data" refers to datasets containing biological and medical-related information, including patient medical records, genetic information, and clinical trial data.

[0007] A "machine learning algorithm" is a computational method in which a computer automatically learns patterns and rules from given data to perform predictions and classifications.

[0008] A "biomedicinal pattern" refers to a characteristic data structure that exhibits regularity or correlations discovered through the analysis of biomedical data.

[0009] "Patient matching" is the process of identifying groups of patients with similar characteristics based on specific conditions or features.

[0010] "Drug repositioning" is a method of exploring the possibility of repurposing existing drugs for new therapeutic applications.

[0011] "Clinical decision support" refers to a system that provides information and analytical results to assist healthcare professionals in making decisions when developing medical treatment plans.

[0012] A "compound library" is a database that compiles a large number of compounds based on their structure and properties, and is used for screening in the development of new drugs. [Brief explanation of the drawing]

[0013] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (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.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage 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.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] As an embodiment for carrying out the present invention, an innovative drug development system utilizing AI will be described. This system aims to efficiently collect, integrate, and analyze biomedical data to accelerate the development of drugs for rare and intractable diseases.

[0035] Users access the system at startup and specify the necessary datasets according to their research objectives and target diseases. The server then collects vast amounts of biomedical data from internal and external databases, forming a centralized data pool.

[0036] The server analyzes the collected data using machine learning algorithms to extract insights related to biomedical patterns and disease mechanisms. For example, it may discover a correlation between specific gene mutations and disease progression.

[0037] Furthermore, when users plan clinical trials, they can utilize the patient matching function provided by the server. This function helps to efficiently conduct trials by matching data with historical data and identifying highly similar patient groups.

[0038] Furthermore, the system includes a drug repositioning function. The server screens existing compound libraries and explores potential applications for new diseases. This approach can, for example, suggest that an antiviral drug may also be effective against certain types of cancer.

[0039] The terminal is equipped with an interface for inputting individual patient information, which allows the server to suggest the optimal treatment plan. For example, it can predict how effective existing treatments will be for patients with a specific genetic background and develop a treatment plan optimized for that patient.

[0040] This system enables users to effectively approach rare and intractable diseases that were difficult to treat with conventional methods. By combining the collection and analysis of vast amounts of data with AI-powered patient matching and drug repositioning functions, a significant increase in the efficiency of drug development is expected.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user specifies the necessary datasets based on the research objectives and target diseases through the system interface.

[0044] Step 2:

[0045] The server collects biomedical data from internal and external databases based on specified criteria. This data includes patient medical information, genetic information, and research information from public databases.

[0046] Step 3:

[0047] The server integrates the collected data and performs data cleansing. This process corrects missing values ​​and outliers, preparing the data for analysis.

[0048] Step 4:

[0049] The server applies machine learning algorithms to the cleansed data to analyze biomedical patterns, particularly identifying disease-related specific gene mutations and pathological phenomena.

[0050] Step 5:

[0051] Users review the obtained analysis results and use them to formulate research hypotheses and develop experimental plans.

[0052] Step 6:

[0053] The server performs a patient matching process to identify the patient group eligible for clinical trials. It compares current data with past data to extract patients with high similarity.

[0054] Step 7:

[0055] The terminal displays the extracted patient list to the user and assists in its use in clinical trial planning.

[0056] Step 8:

[0057] The server analyzes compound libraries and performs drug repositioning. It identifies newly applicable drugs and predicts their interactions and effects.

[0058] Step 9:

[0059] The terminal provides an interface for entering individual patient data and, based on the information entered by the user, suggests the most suitable treatment plan for the patient.

[0060] Step 10:

[0061] The server generates detailed evaluation results regarding the proposed treatment and presents them to the user via the terminal. This allows the user to obtain the information necessary to determine the optimal treatment plan.

[0062] (Example 1)

[0063] 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."

[0064] In the field of biomedicine, developing treatments for rare and intractable diseases presents challenges with conventional methods, such as the complexity and time-consuming nature of data collection and analysis. Furthermore, finding the optimal treatment for each patient is not easy, highlighting the need for efficient methods to explore the potential of new drug applications.

[0065] 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.

[0066] In this invention, the server includes an information gathering means for collecting and integrating bioscientific information, an information analysis means for extracting biomedical trends by applying machine learning techniques, and a subject selection means for identifying subjects to be studied based on the extracted trends. This enables the efficient collection and analysis of complex biomedical data, leading to the proposal of optimal treatments for patients and the discovery of new drug applications.

[0067] "Life science information" refers to a broad range of information, including biological and medical data such as genetic data, patient statistics, and disease-related information.

[0068] "Information gathering means" refers to methods and systems for efficiently acquiring and centralizing necessary data from various databases and information sources.

[0069] "Machine learning technology" refers to algorithms and techniques that enable computers to automatically learn patterns and insights from data to make predictions and decisions.

[0070] "Information analysis methods" refer to methods and processes for applying machine learning techniques to collected data to extract specific trends or patterns.

[0071] A "subject selection method" is an approach to identify the optimal subjects for an experiment or treatment based on analyzed data.

[0072] A "pharmaceutical group" is a collection of already known drugs and compounds, and is a group of substances for which new applications are being explored.

[0073] "Drug reuse methods" refer to methods for re-evaluating existing drug populations and examining whether they are applicable to new diseases.

[0074] "Medical decision-making support tools" are processes or tools that propose optimal treatment plans and prescriptions based on individual patient information.

[0075] In carrying out this invention, the following methods are appropriate.

[0076] User actions

[0077] Users access the system using a terminal and specify the disease and related life science information they wish to analyze based on their research objectives. Using the terminal's interface, users can select and input the target disease name, genetic information, and other relevant details.

[0078] Server Processing

[0079] The server collects relevant life science information from internal and external databases according to user-specified conditions. This process utilizes data aggregation software and storage systems suitable for handling large datasets, such as widely used database software and cloud services. The collected data is integrated and analyzed using machine learning techniques. This analysis process leverages analytical libraries using Python and R to extract patterns and associations for specific diseases. The server also screens existing drug populations for drug repositioning and explores new applicability. At this stage, data mining techniques are used to generate models that predict the effects of compounds on diseases.

[0080] Device functions

[0081] The terminal is equipped with an input interface for individual patient information, and the server proposes a treatment plan based on the entered information. This information flow occurs through web and mobile applications, and the AI ​​model on the server prioritizes developing an individualized treatment plan. In particular, handling genomic information is required to take into account the patient's genetic background.

[0082] Examples of specific cases and prompt statements

[0083] As a concrete example, this system can be used to analyze data on rare genetic diseases and quickly discover new drugs to treat diseases caused by specific gene mutations. It may also be possible to apply existing antiviral drugs to the treatment of newly discovered cancers. A suitable prompt for the generating AI model would be: "Please propose a method for analyzing the relationship between gene mutations and symptoms to develop new treatments for rare diseases. Also, please tell me about the potential for new disease applications of existing drugs."

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] Users access the system via a terminal and select a dataset to specify the target disease or research subject. This input includes the disease name and associated genetic information, which forms the basis of the data handled by the system. The terminal's function is to accurately transmit the user's input information to the server.

[0087] Step 2:

[0088] The server receives the user-specified background data as input and begins the process of collecting relevant life science information from internal and external databases. Specifically, it retrieves data by calling APIs of existing databases and integrates it. In this process, data in different formats is standardized and combined into a single, unified dataset.

[0089] Step 3:

[0090] Using the collected data, the server applies machine learning techniques and performs data analysis. Input data is supplied to the machine learning algorithms as numerical and text data. In this step, complex data calculations are performed using TENSORFLOW® and PyTorch to extract biomedical trends and patterns of disease mechanisms. The output provides insights related to specific gene mutations and disease progression.

[0091] Step 4:

[0092] When a user plans a clinical trial, the server provides a patient matching function based on the analyzed results. Inputs include an existing patient database and historical patient information. To identify highly similar patient groups, the server compares and calculates this data, outputting optimal candidate subjects. This result is evaluated by the user and forms the basis of the trial design.

[0093] Step 5:

[0094] The server then performs drug repositioning within the existing drug population. It receives compound information as input and processes it to explore whether the compound is applicable to a new disease. Here, data mining techniques are used to build a predictive model of the association between existing drugs and new applicable diseases. The output is a list of potential drug candidates.

[0095] Step 6:

[0096] The terminal provides an interface for suggesting the optimal treatment plan based on information received from the server, once individual patient information is entered. The entered patient information includes genetic background and past treatment history. The server uses a generative AI model to create the most suitable treatment plan, which is then presented to the user through the terminal. The output is a treatment suggestion tailored to the patient.

[0097] (Application Example 1)

[0098] 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."

[0099] The secure handling of biomedical information in healthcare settings and the prevention of unauthorized access to highly confidential information are critical challenges. In particular, accessing information using smart devices requires appropriate authentication processes, but current systems may not provide sufficient security. Furthermore, rapid and secure information processing methods are necessary to efficiently explore new drug applicability and propose optimal treatments.

[0100] 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.

[0101] In this invention, the server includes information gathering means for collecting and integrating biomedical information, information analysis means for applying machine learning algorithms based on the integrated information, and access management means for strengthening the authentication process based on extracted patterns. This enables the secure handling of biomedical information, prevents unauthorized access to confidential information, and further allows for the exploration of new drug applicability and the proposal of optimal treatment methods through the utilization of the information.

[0102] "Biomedical information" is a general term for data related to biology and medicine, including a patient's health status, genetic information, and medical history.

[0103] "Information gathering means" refers to methods and devices for collecting and integrating necessary data from various sources.

[0104] A "machine learning algorithm" is a program that automatically finds patterns and regularities from large amounts of data and uses that knowledge to make predictions and decisions.

[0105] "Information analysis methods" refer to methods and techniques for processing collected data and extracting useful insights.

[0106] An "authentication process" is a set of procedures and technologies used to verify the identity of users and devices accessing an information system and to grant them appropriate permissions.

[0107] "Access control measures" refer to methods and technologies for controlling access to information and preventing its misuse.

[0108] "Repositioning means" refers to methods or processes for applying existing resources or information to new purposes or uses.

[0109] "Decision support tools" are methods and systems that analyze and present data and information to help users make the best choices.

[0110] This invention is a system for ensuring the secure handling and utilization of biomedical information. The server begins by collecting and integrating biomedical information, and then analyzes the information using machine learning algorithms. Based on the extracted biomedical patterns, it strengthens the authentication process and manages unauthorized access to the information.

[0111] Specifically, this system operates on smart devices such as smartphones and smart glasses running iOS or Android®. The software is developed using AI frameworks such as TensorFlow and PyTorch, and securely accesses information by analyzing the user's biometric information and behavioral patterns. If authentication is successful, the user will be able to access the necessary information; otherwise, additional authentication steps will be required.

[0112] As a concrete example, consider a scenario where a medical staff member, as the user, wears smart glasses and accesses the system through voice and facial recognition. This allows for immediate access to confidential information such as patients' electronic medical records, enabling them to perform their duties securely.

[0113] Furthermore, it is possible to analyze diverse information using generative AI models and explore new drug application possibilities. For example, using prompts such as, "Design a prototype application that enables secure access to medical data using AI," can assist in exploring specific implementation methods.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server collects biomedical information from multiple sources and stores it in an integrated database through data collection methods. The input is biomedical data from healthcare and research institutions, and the output is the integrated database containing this information. At this stage, data preprocessing is performed to standardize and ensure consistency of the data format.

[0117] Step 2:

[0118] The server analyzes an integrated database using machine learning algorithms and extracts biomedical patterns. The input is data from the integrated database, and the output is pattern data as a result of the analysis. This process utilizes AI frameworks such as TensorFlow and PyTorch, performing regression analysis and clustering to understand the characteristics of the data.

[0119] Step 3:

[0120] The terminal initiates an authentication process when attempting to access information via the user's smart device. The input is the user's biometric information (e.g., facial image or voice data), and the output is the authentication result. Facial recognition and voice recognition technologies are used to verify the user's identity.

[0121] Step 4:

[0122] The server securely provides information to authenticated users. Input is the requested information of the authenticated user, and output is the requested medical data. The data is appropriately filtered based on access permissions before being provided to the user.

[0123] Step 5:

[0124] The server immediately alerts the administrator upon detecting unauthorized access. Inputs are data from access logs and anomaly detection systems, and output is an alert notification to the administrator. Log analysis and anomaly detection algorithms are used to identify abnormal patterns and implement necessary countermeasures.

[0125] Step 6:

[0126] The server uses a generative AI model to analyze multiple information sources and explore new drug applicability possibilities. Inputs are an integrated database and existing drug information, and outputs are newly proposed treatments and drug application candidates. The exploration results are provided to healthcare professionals through decision support tools, utilizing prompts such as, "Design a prototype application that enables secure access to medical data using AI."

[0127] 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.

[0128] As an embodiment for carrying out the present invention, a drug development support system incorporating an emotion engine will be described. This system includes integration and analysis of biomedical data, patient matching, drug repositioning, and clinical decision support, and further has a function that takes into account the user's emotional state.

[0129] The user first accesses the system and specifies the necessary data according to their purpose and target disease. At that time, an emotion engine is activated on the terminal to estimate the user's emotions from their actions and facial expressions, and to identify the user's stress and fatigue levels.

[0130] The server integrates the specified and collected biomedical data and performs data cleansing. It then analyzes the dataset using machine learning algorithms to discover biomedical patterns.

[0131] The server identifies highly similar patient groups based on discovered patterns and assists users in planning clinical trials. During this process, the interface is adjusted according to the user's emotional state, as assessed by the emotion engine, to ensure the user receives information most effectively.

[0132] In the drug repositioning function, the server screens existing drugs from a compound library and evaluates their potential for new applications. This enables effective approaches to a wide range of diseases.

[0133] The terminal provides a user interface for entering individual patient information, and based on this information, the server proposes the most suitable treatment plan for the patient. This proposal also reflects the user's emotional state, and feedback and the order of suggestions are optimized as needed.

[0134] For example, if a user is searching for treatment for an elderly patient and the emotion engine detects their own fatigue, the server will adjust its presentation to present information in a concise and easy-to-understand format, minimizing the number of steps required. This process reduces the user's burden while maximizing effectiveness.

[0135] By incorporating an emotional engine, this system becomes more human-centered than conventional approaches, enabling more intuitive and effective use. This is expected to lead to the rapid development of treatments for rare and intractable diseases, thereby improving the quality of medical care.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user logs into the system and enters parameters related to the research objectives and target disease into the terminal. Based on this input, the entire system processing begins.

[0139] Step 2:

[0140] The device uses its built-in camera and sensors to analyze facial expressions and voice tone during user interaction, and an emotion engine evaluates the user's emotional state. This information is sent to a server for later interface adjustments.

[0141] Step 3:

[0142] The server automatically collects biomedical data from internal and external databases based on specified conditions. The collected data is centralized and prepared for analysis through a data cleansing process.

[0143] Step 4:

[0144] The server applies machine learning algorithms to the cleansed data to extract disease-related biomedical patterns. The identified patterns are visualized and sent to the terminal for use in research.

[0145] Step 5:

[0146] The server uses the extracted patterns to identify patient groups eligible for clinical trials. It evaluates patient similarity and displays the most suitable candidate group as a list on the terminal.

[0147] Step 6:

[0148] Based on the sentiment evaluation results from the emotion engine, the device adjusts the interface to allow the user to receive information most effectively, and appropriately adjusts the amount and display order of the data presented.

[0149] Step 7:

[0150] The server analyzes the compound library and performs a drug repositioning process to discover new applicability. It then reports newly identified potential applications to the user.

[0151] Step 8:

[0152] The terminal provides a user-friendly interface for entering individual patient data and aggregates the entered data before sending it to the server.

[0153] Step 9:

[0154] The server determines the optimal treatment plan and generates a suggested plan based on the transmitted patient data. During this process, it provides flexible suggestions that incorporate an emotion engine, and sends the results to the terminal.

[0155] Step 10:

[0156] Users review recommended treatments and clinical trial plans and determine the next steps. This entire process accelerates research and prepares the system to apply the best possible treatment approach to patients.

[0157] (Example 2)

[0158] 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".

[0159] Conventional drug development support systems have faced challenges in integrating and analyzing biological information, making it difficult to rapidly identify effective treatment methods in personalized medicine. Furthermore, they have been unable to consider the user's emotions and stress levels during system use, limiting the quality of the user experience.

[0160] 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.

[0161] In this invention, the server includes information acquisition means for acquiring and integrating biological information, information analysis means for applying a machine learning algorithm to the integrated information to extract biological characteristics, and emotion response means for detecting the user's emotional state and adjusting the user interface according to the detected state. This enables rapid and accurate identification of treatment methods based on biological characteristics and the provision of an interface that takes the user's emotions into consideration.

[0162] "Information acquisition means" refers to a component that has the function of acquiring and integrating biological information.

[0163] "Information analysis means" refers to a device or process for applying machine learning algorithms to integrated biological information and extracting biological characteristics.

[0164] "Individual matching means" are components used to identify individuals that are the target of therapeutic research based on extracted biological characteristics.

[0165] A "drug reuse method" is a system configuration for analyzing existing drug databases and exploring new applicability possibilities.

[0166] A "treatment decision support device" is a support system that proposes the optimal treatment method based on individual patient information.

[0167] An "emotional response means" is a component that has the function of detecting the user's emotional state and adjusting the user interface according to the detected state.

[0168] In an embodiment of this invention, the entire system is designed to effectively process biological information and provide an interface that takes into account the user's emotional state. The three main components here are the terminal, the server, and the user.

[0169] The terminal is the primary interface for acquiring biological information input from the user. Equipped with cameras and sensors, the terminal detects the user's emotional state by analyzing their facial expressions and physical reactions. Users also input biological information and information necessary for drug development through the terminal.

[0170] The server integrates biological information based on data transmitted from terminals through information acquisition and analysis methods, and analyzes the information using machine learning algorithms. Specific tools used for data integration and analysis include the Python Pandas library and TensorFlow. As a result of the analysis, biological characteristics are extracted, and based on these, individual matching is performed to identify individuals suitable for treatment. Drug reuse methods are also processed on this server, analyzing existing drug databases and exploring new applicability.

[0171] Based on the results analyzed by the server, the user receives suggestions for the most suitable treatment method. In this process, emotional response mechanisms are used to present information and adjust the interface according to the user's emotional state.

[0172] As a concrete example, consider a scenario where a user is searching for a treatment for a new disease. In this case, if the emotion engine detects the user's stress level, the server will organize the information concisely and present the key points clearly. As a result, the user can obtain the maximum amount of information with the minimum necessary actions.

[0173] An example of a prompt message would be, "Analyze the biological information of the specified disease and propose the optimal clinical trial plan," which would be input to the generating AI model. In this way, rapid and highly accurate medical support is achieved.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The user inputs biological information and information necessary for drug development through the terminal. The terminal temporarily stores the input data and simultaneously uses cameras and sensors to detect the user's facial expressions and movements. This information is also used to evaluate the user's emotional state. The input data includes basic information about the patient and details about the disease.

[0177] Step 2:

[0178] Data sent from the terminal is transferred to the server. The server uses information acquisition methods to integrate biological information from different formats and sources and store it in a database. In this process, the Pandas library in Python is used to combine dataframes and process missing and outlier values ​​to generate a cleaned dataset.

[0179] Step 3:

[0180] The server applies machine learning algorithms to the integrated dataset. Using libraries such as TensorFlow and SciKit-Learn, the server extracts underlying biological characteristics and patterns from the data. The output identifies biomarkers associated with specific diseases, providing important insights for treatment.

[0181] Step 4:

[0182] The server performs individual matching based on extracted biological characteristics. It executes database queries to identify highly similar patient groups and lists this information in a format usable for therapeutic research and clinical trials. This allows users to efficiently plan trials.

[0183] Step 5:

[0184] The server executes drug reuse mechanisms and screens existing drug databases. It searches for similar drugs based on chemical structure and biological properties and evaluates their potential for new applications. This expands treatment options and may lead to the discovery of uncharted treatment methods.

[0185] Step 6:

[0186] The server uses treatment decision support tools to propose the optimal treatment plan based on individual patient information. The proposed treatment plan is displayed on the terminal in an easy-to-understand format. The emotional response tool adjusts the interface according to the user's emotional state and summarizes information concisely as needed.

[0187] Step 7:

[0188] The user decides on a treatment plan based on the information and suggestions presented. The user can input prompts into the AI ​​model to receive further analysis and suggestions. For example, by inputting a prompt such as, "Please suggest the optimal treatment for the specified disease," the system can provide detailed feedback.

[0189] (Application Example 2)

[0190] 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".

[0191] In medical and nursing care settings, the systems used by healthcare professionals are often complex and can cause stress and fatigue. This makes it difficult to provide optimal medical and nursing care services. Furthermore, while rapid and appropriate responses tailored to individual patient conditions are required, conventional technologies struggle to adequately support this. Additionally, the lack of information presentation that considers the emotional state of healthcare professionals can hinder effective work performance.

[0192] 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.

[0193] In this invention, the server includes means for collecting and integrating biomedical data, means for applying machine learning algorithms to the integrated data to extract biomedical patterns, and means for providing an emotion engine that evaluates the user's emotional state and adjusts the interface to optimize information presentation. This enables the presentation of appropriate information according to the user's emotional state, as well as improved work efficiency and the provision of optimal care plans for patients.

[0194] "Biomedical data" refers to data such as test results, genetic information, and patient clinical information obtained in medical and biological research.

[0195] "Data collection methods" refer to devices and technologies for collecting and integrating biomedical data.

[0196] A "machine learning algorithm" is a computational method used in data analysis that automatically learns patterns and insights from data.

[0197] A "biomedicinal pattern" is a consistent characteristic or feature extracted from biomedical data that is associated with a particular disease or condition.

[0198] "Patient matching methods" refer to methods or systems for appropriately selecting patients to participate in clinical trials.

[0199] "Drug repositioning methods" are techniques that explore the possibility of repurposing existing pharmaceuticals for new indications.

[0200] "Clinical decision-making support tools" are support tools that enable healthcare professionals to propose the most suitable treatment method based on individual patient information.

[0201] An "emotion engine" is a technology that evaluates the user's emotional state and optimizes the system's interface and information delivery accordingly.

[0202] "Users" refer to healthcare professionals and care staff who utilize this system.

[0203] To implement this invention, it is necessary to build a system incorporating an emotion engine. The main components of the system include a server that integrates and analyzes data, a terminal that evaluates the user's emotional state, and the users themselves, such as healthcare professionals and care staff.

[0204] The server collects and integrates biomedical data and extracts biomedical patterns using machine learning algorithms. Apache Hadoop is used for data management, and TensorFlow is used for machine learning. Based on the extracted patterns, patient matching is performed, and the optimal treatment method is proposed. Drug repositioning is also performed to explore new indications from the compound library.

[0205] The device is equipped with an emotion engine that evaluates the user's emotional state based on their facial expressions and voice data. Based on this evaluation, the server adjusts how information is displayed, presenting the information the user needs in an easy-to-understand manner. This reduces user stress caused by information overload and improves work efficiency.

[0206] For example, if a caregiver feels fatigued during nighttime rounds, the emotional engine will detect it. Because the information is presented concisely and to the point, caregivers can provide care efficiently.

[0207] An example of a prompt from a generated AI model is, "Please design a smart app for caregivers that analyzes emotions, adjusts the interface accordingly, and allows them to easily check care plans during night shifts." By adjusting the interface in response to emotions in this way, user-centered healthcare delivery can be achieved.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server collects biomedical data. It receives a wide variety of biomedical information from electronic medical record systems and research databases as input. To integrate this information, it uses Apache Hadoop to store the data and perform data cleansing while maintaining consistency. The output is an integrated and refined dataset.

[0211] Step 2:

[0212] The server applies machine learning algorithms to the integrated dataset. The input is the dataset prepared in Step 1. This allows for data analysis using TensorFlow, and biomedical patterns are extracted. The resulting output is patterns associated with specific diseases or patient conditions.

[0213] Step 3:

[0214] The server matches patients for clinical trials based on the extracted patterns. The input consists of the biomedical patterns extracted in step 2 and individual patient information. The server compares this information to identify and list suitable patients. The output is a list of patients suitable for clinical trials and treatment plans.

[0215] Step 4:

[0216] The device evaluates the emotional state of the user (healthcare worker or caregiver). Inputs include the user's facial expressions and voice data acquired through the camera and microphone. An emotion engine analyzes this data to determine the user's level of fatigue and stress. The output is the evaluation result regarding the user's emotional state.

[0217] Step 5:

[0218] The server adjusts the information presentation interface based on the emotional state assessment results. The inputs are the assessment results obtained in step 4 and the medical information requested by the user. The server adjusts the complexity and amount of information in the interface to present the information in the most easily understandable way for the user. This process results in an information presentation screen optimized for user accessibility.

[0219] Step 6:

[0220] Users access optimized information screens using their terminals and perform procedures necessary for treatment planning and patient care. Input consists of finely tuned information provided by the server. Based on this information, users efficiently develop and implement care plans. Output is the optimal treatment or care plan to be implemented.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] As an embodiment for carrying out the present invention, an innovative drug development system utilizing AI will be described. This system aims to efficiently collect, integrate, and analyze biomedical data to accelerate the development of drugs for rare and intractable diseases.

[0238] Users access the system at startup and specify the necessary datasets according to their research objectives and target diseases. The server then collects vast amounts of biomedical data from internal and external databases, forming a centralized data pool.

[0239] The server analyzes the collected data using machine learning algorithms to extract insights related to biomedical patterns and disease mechanisms. For example, it may discover a correlation between specific gene mutations and disease progression.

[0240] Furthermore, when users plan clinical trials, they can utilize the patient matching function provided by the server. This function helps to efficiently conduct trials by matching data with historical data and identifying highly similar patient groups.

[0241] Furthermore, the system includes a drug repositioning function. The server screens existing compound libraries and explores potential applications for new diseases. This approach can, for example, suggest that an antiviral drug may also be effective against certain types of cancer.

[0242] The terminal is equipped with an interface for inputting individual patient information, which allows the server to suggest the optimal treatment plan. For example, it can predict how effective existing treatments will be for patients with a specific genetic background and develop a treatment plan optimized for that patient.

[0243] This system enables users to effectively approach rare and intractable diseases that were difficult to treat with conventional methods. By combining the collection and analysis of vast amounts of data with AI-powered patient matching and drug repositioning functions, a significant increase in the efficiency of drug development is expected.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The user specifies the necessary datasets based on the research objectives and target diseases through the system interface.

[0247] Step 2:

[0248] The server collects biomedical data from internal and external databases based on specified criteria. This data includes patient medical information, genetic information, and research information from public databases.

[0249] Step 3:

[0250] The server integrates the collected data and performs data cleansing. This process corrects missing values ​​and outliers, preparing the data for analysis.

[0251] Step 4:

[0252] The server applies machine learning algorithms to the cleansed data to analyze biomedical patterns, particularly identifying disease-related specific gene mutations and pathological phenomena.

[0253] Step 5:

[0254] Users review the obtained analysis results and use them to formulate research hypotheses and develop experimental plans.

[0255] Step 6:

[0256] The server performs a patient matching process to identify the patient group eligible for clinical trials. It compares current data with past data to extract patients with high similarity.

[0257] Step 7:

[0258] The terminal displays the extracted patient list to the user and assists in its use in clinical trial planning.

[0259] Step 8:

[0260] The server analyzes compound libraries and performs drug repositioning. It identifies newly applicable drugs and predicts their interactions and effects.

[0261] Step 9:

[0262] The terminal provides an interface for entering individual patient data and, based on the information entered by the user, suggests the most suitable treatment plan for the patient.

[0263] Step 10:

[0264] The server generates detailed evaluation results regarding the proposed treatment and presents them to the user via the terminal. This allows the user to obtain the information necessary to determine the optimal treatment plan.

[0265] (Example 1)

[0266] 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."

[0267] In the field of biomedicine, developing treatments for rare and intractable diseases presents challenges with conventional methods, such as the complexity and time-consuming nature of data collection and analysis. Furthermore, finding the optimal treatment for each patient is not easy, highlighting the need for efficient methods to explore the potential of new drug applications.

[0268] 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.

[0269] In this invention, the server includes an information gathering means for collecting and integrating bioscientific information, an information analysis means for extracting biomedical trends by applying machine learning techniques, and a subject selection means for identifying subjects to be studied based on the extracted trends. This enables the efficient collection and analysis of complex biomedical data, leading to the proposal of optimal treatments for patients and the discovery of new drug applications.

[0270] "Life science information" refers to a broad range of information, including biological and medical data such as genetic data, patient statistics, and disease-related information.

[0271] "Information gathering means" refers to methods and systems for efficiently acquiring and centralizing necessary data from various databases and information sources.

[0272] "Machine learning technology" refers to algorithms and techniques that enable computers to automatically learn patterns and insights from data to make predictions and decisions.

[0273] "Information analysis methods" refer to methods and processes for applying machine learning techniques to collected data to extract specific trends or patterns.

[0274] A "subject selection method" is an approach to identify the optimal subjects for an experiment or treatment based on analyzed data.

[0275] A "pharmaceutical group" is a collection of already known drugs and compounds, and is a group of substances for which new applications are being explored.

[0276] "Drug reuse methods" refer to methods for re-evaluating existing drug populations and examining whether they are applicable to new diseases.

[0277] "Medical decision-making support tools" are processes or tools that propose optimal treatment plans and prescriptions based on individual patient information.

[0278] In carrying out this invention, the following methods are appropriate.

[0279] User actions

[0280] Users access the system using a terminal and specify the disease and related life science information they wish to analyze based on their research objectives. Using the terminal's interface, users can select and input the target disease name, genetic information, and other relevant details.

[0281] Server Processing

[0282] The server collects relevant life science information from internal and external databases according to the conditions specified by the user. In this process, software for data aggregation and a storage system suitable for handling, for example, large-scale data are used. Specifically, widely used database software and cloud services are often adopted. The collected data is integrated and analyzed using machine learning techniques. For this analysis process, analysis libraries using Python or R are utilized to extract patterns and correlations of specific diseases. The server also performs drug repositioning screening on existing pharmaceutical groups to explore new applicability. At this stage, data mining techniques are fully utilized to generate models for predicting the effects of compounds and diseases.

[0283] Functions of the terminal

[0284] The terminal has an input interface for individual patient information, and based on the input information, the server proposes a treatment method. This information flow is carried out through web applications or mobile applications, and the AI model on the server formulates an individualized treatment plan as the top priority. In particular, handling of genomic information is required to consider the patient's genetic background.

[0285] Examples of specific cases and prompt sentences

[0286] As a specific example, this system can be used to analyze data on rare genetic diseases and quickly discover new drugs for treating diseases caused by specific gene mutations. There is also a possibility that existing antiviral drugs can be applied to the treatment of newly discovered cancers. As an example of a prompt sentence, a query such as "Please propose a method for analyzing the relationship between gene mutations and symptoms for the development of new treatment methods for rare diseases. Also, please inform me about the possibility of new disease applications for existing drugs." is suitable as an input to the generative AI model.

[0287] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0288] Step 1:

[0289] Users access the system via a terminal and select a dataset to specify the target disease or research subject. This input includes the disease name and associated genetic information, which forms the basis of the data handled by the system. The terminal's function is to accurately transmit the user's input information to the server.

[0290] Step 2:

[0291] The server receives the user-specified background data as input and begins the process of collecting relevant life science information from internal and external databases. Specifically, it retrieves data by calling APIs of existing databases and integrates it. In this process, data in different formats is standardized and combined into a single, unified dataset.

[0292] Step 3:

[0293] Using the collected data, the server applies machine learning techniques and performs data analysis. Input data is supplied to the machine learning algorithm as numerical or text data. In this step, complex data calculations are performed using TensorFlow or PyTorch to extract biomedical trends and patterns of disease mechanisms. The output provides insights related to specific gene mutations and disease progression.

[0294] Step 4:

[0295] When a user plans a clinical trial, the server provides a patient matching function based on the analyzed results. Inputs include an existing patient database and historical patient information. To identify highly similar patient groups, the server compares and calculates this data, outputting optimal candidate subjects. This result is evaluated by the user and forms the basis of the trial design.

[0296] Step 5:

[0297] The server then performs drug repositioning within the existing drug population. It receives compound information as input and processes it to explore whether the compound is applicable to a new disease. Here, data mining techniques are used to build a predictive model of the association between existing drugs and new applicable diseases. The output is a list of potential drug candidates.

[0298] Step 6:

[0299] The terminal provides an interface for suggesting the optimal treatment plan based on information received from the server, once individual patient information is entered. The entered patient information includes genetic background and past treatment history. The server uses a generative AI model to create the most suitable treatment plan, which is then presented to the user through the terminal. The output is a treatment suggestion tailored to the patient.

[0300] (Application Example 1)

[0301] 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 glasses 214 will be referred to as the "terminal."

[0302] The secure handling of biomedical information in healthcare settings and the prevention of unauthorized access to highly confidential information are critical challenges. In particular, accessing information using smart devices requires appropriate authentication processes, but current systems may not provide sufficient security. Furthermore, rapid and secure information processing methods are necessary to efficiently explore new drug applicability and propose optimal treatments.

[0303] 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.

[0304] In this invention, the server includes an information collection means for collecting and integrating biomedical information, an information analysis means for applying a machine learning algorithm based on the integrated information, and an access management means for strengthening the authentication process based on the extracted patterns. Thereby, it realizes the safe handling of biomedical information and the prevention of unauthorized access to confidential information, and further enables the exploration of new drug applicability and the proposal of optimal treatment methods through the utilization of information.

[0305] "Biomedical information" is a general term for data related to biology and medicine, including a patient's health status, genetic information, medical history, etc.

[0306] "Information collection means" refers to a method or device for collecting and integrating necessary data from various sources.

[0307] "Machine learning algorithm" is a program for automatically finding patterns and regularities from a large amount of data and making predictions or decisions based on that knowledge.

[0308] "Information analysis means" refers to a method or technology for processing the collected data and extracting useful insights.

[0309] "Authentication process" is a series of procedures and technologies for verifying the identity of users and devices accessing an information system and granting appropriate permissions.

[0310] "Access management means" refers to a method or technology for controlling access to information and preventing unauthorized use.

[0311] "Repositioning means" is a technique or process for applying existing resources and information to new purposes and uses.

[0312] "Decision-making support means" is a technique or system for analyzing and presenting data and information to assist users in making optimal choices.

[0313] This invention is a system for ensuring the secure handling and utilization of biomedical information. The server begins by collecting and integrating biomedical information, and then analyzes the information using machine learning algorithms. Based on the extracted biomedical patterns, it strengthens the authentication process and manages unauthorized access to the information.

[0314] Specifically, this system operates on smart devices such as smartphones running iOS or Android, and smart glasses. The software is developed using AI frameworks such as TensorFlow and PyTorch, and securely accesses information by analyzing the user's biometric information and behavioral patterns. If authentication is successful, the user will be able to access the necessary information; otherwise, additional authentication steps will be required.

[0315] As a concrete example, consider a scenario where a medical staff member, as the user, wears smart glasses and accesses the system through voice and facial recognition. This allows for immediate access to confidential information such as patients' electronic medical records, enabling them to perform their duties securely.

[0316] Furthermore, it is possible to analyze diverse information using generative AI models and explore new drug application possibilities. For example, using prompts such as, "Design a prototype application that enables secure access to medical data using AI," can assist in exploring specific implementation methods.

[0317] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0318] Step 1:

[0319] The server collects biomedical information from multiple sources and stores it in an integrated database through data collection methods. The input is biomedical data from healthcare and research institutions, and the output is the integrated database containing this information. At this stage, data preprocessing is performed to standardize and ensure consistency of the data format.

[0320] Step 2:

[0321] The server analyzes an integrated database using machine learning algorithms and extracts biomedical patterns. The input is data from the integrated database, and the output is pattern data as a result of the analysis. This process utilizes AI frameworks such as TensorFlow and PyTorch, performing regression analysis and clustering to understand the characteristics of the data.

[0322] Step 3:

[0323] The terminal initiates an authentication process when attempting to access information via the user's smart device. The input is the user's biometric information (e.g., facial image or voice data), and the output is the authentication result. Facial recognition and voice recognition technologies are used to verify the user's identity.

[0324] Step 4:

[0325] The server securely provides information to authenticated users. Input is the requested information of the authenticated user, and output is the requested medical data. The data is appropriately filtered based on access permissions before being provided to the user.

[0326] Step 5:

[0327] The server immediately alerts the administrator upon detecting unauthorized access. Inputs are data from access logs and anomaly detection systems, and output is an alert notification to the administrator. Log analysis and anomaly detection algorithms are used to identify abnormal patterns and implement necessary countermeasures.

[0328] Step 6:

[0329] The server uses a generative AI model to analyze multiple information sources and explore new drug applicability possibilities. Inputs are an integrated database and existing drug information, and outputs are newly proposed treatments and drug application candidates. The exploration results are provided to healthcare professionals through decision support tools, utilizing prompts such as, "Design a prototype application that enables secure access to medical data using AI."

[0330] 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.

[0331] As an embodiment for carrying out the present invention, a drug development support system incorporating an emotion engine will be described. This system includes integration and analysis of biomedical data, patient matching, drug repositioning, and clinical decision support, and further has a function that takes into account the user's emotional state.

[0332] The user first accesses the system and specifies the necessary data according to their purpose and target disease. At that time, an emotion engine is activated on the terminal to estimate the user's emotions from their actions and facial expressions, and to identify the user's stress and fatigue levels.

[0333] The server integrates the specified and collected biomedical data and performs data cleansing. It then analyzes the dataset using machine learning algorithms to discover biomedical patterns.

[0334] The server identifies highly similar patient groups based on discovered patterns and assists users in planning clinical trials. During this process, the interface is adjusted according to the user's emotional state, as assessed by the emotion engine, to ensure the user receives information most effectively.

[0335] In the drug repositioning function, the server screens existing drugs from a compound library and evaluates their potential for new applications. This enables effective approaches to a wide range of diseases.

[0336] The terminal provides a user interface for entering individual patient information, and based on this information, the server proposes the most suitable treatment plan for the patient. This proposal also reflects the user's emotional state, and feedback and the order of suggestions are optimized as needed.

[0337] For example, if a user is searching for treatment for an elderly patient and the emotion engine detects their own fatigue, the server will adjust its presentation to present information in a concise and easy-to-understand format, minimizing the number of steps required. This process reduces the user's burden while maximizing effectiveness.

[0338] By incorporating an emotional engine, this system becomes more human-centered than conventional approaches, enabling more intuitive and effective use. This is expected to lead to the rapid development of treatments for rare and intractable diseases, thereby improving the quality of medical care.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The user logs into the system and enters parameters related to the research objectives and target disease into the terminal. Based on this input, the entire system processing begins.

[0342] Step 2:

[0343] The device uses its built-in camera and sensors to analyze facial expressions and voice tone during user interaction, and an emotion engine evaluates the user's emotional state. This information is sent to a server for later interface adjustments.

[0344] Step 3:

[0345] The server automatically collects biomedical data from internal and external databases based on specified conditions. The collected data is centralized and prepared for analysis through a data cleansing process.

[0346] Step 4:

[0347] The server applies machine learning algorithms to the cleansed data to extract disease-related biomedical patterns. The identified patterns are visualized and sent to the terminal for use in research.

[0348] Step 5:

[0349] The server uses the extracted patterns to identify patient groups eligible for clinical trials. It evaluates patient similarity and displays the most suitable candidate group as a list on the terminal.

[0350] Step 6:

[0351] Based on the sentiment evaluation results from the emotion engine, the device adjusts the interface to allow the user to receive information most effectively, and appropriately adjusts the amount and display order of the data presented.

[0352] Step 7:

[0353] The server analyzes the compound library and performs a drug repositioning process to discover new applicability. It then reports newly identified potential applications to the user.

[0354] Step 8:

[0355] The terminal provides a user-friendly interface for entering individual patient data and aggregates the entered data before sending it to the server.

[0356] Step 9:

[0357] The server determines the optimal treatment plan and generates a suggested plan based on the transmitted patient data. During this process, it provides flexible suggestions that incorporate an emotion engine, and sends the results to the terminal.

[0358] Step 10:

[0359] Users review recommended treatments and clinical trial plans and determine the next steps. This entire process accelerates research and prepares the system to apply the best possible treatment approach to patients.

[0360] (Example 2)

[0361] 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".

[0362] Conventional drug development support systems have faced challenges in integrating and analyzing biological information, making it difficult to rapidly identify effective treatment methods in personalized medicine. Furthermore, they have been unable to consider the user's emotions and stress levels during system use, limiting the quality of the user experience.

[0363] 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.

[0364] In this invention, the server includes information acquisition means for acquiring and integrating biological information, information analysis means for applying a machine learning algorithm to the integrated information to extract biological characteristics, and emotion response means for detecting the user's emotional state and adjusting the user interface according to the detected state. This enables rapid and accurate identification of treatment methods based on biological characteristics and the provision of an interface that takes the user's emotions into consideration.

[0365] "Information acquisition means" refers to a component that has the function of acquiring and integrating biological information.

[0366] "Information analysis means" refers to a device or process for applying machine learning algorithms to integrated biological information and extracting biological characteristics.

[0367] "Individual matching means" are components used to identify individuals that are the target of therapeutic research based on extracted biological characteristics.

[0368] A "drug reuse method" is a system configuration for analyzing existing drug databases and exploring new applicability possibilities.

[0369] A "treatment decision support device" is a support system that proposes the optimal treatment method based on individual patient information.

[0370] An "emotional response means" is a component that has the function of detecting the user's emotional state and adjusting the user interface according to the detected state.

[0371] In an embodiment of this invention, the entire system is designed to effectively process biological information and provide an interface that takes into account the user's emotional state. The three main components here are the terminal, the server, and the user.

[0372] The terminal is the primary interface for acquiring biological information input from the user. Equipped with cameras and sensors, the terminal detects the user's emotional state by analyzing their facial expressions and physical reactions. Users also input biological information and information necessary for drug development through the terminal.

[0373] The server integrates biological information based on data transmitted from terminals through information acquisition and analysis methods, and analyzes the information using machine learning algorithms. Specific tools used for data integration and analysis include the Python Pandas library and TensorFlow. As a result of the analysis, biological characteristics are extracted, and based on these, individual matching is performed to identify individuals suitable for treatment. Drug reuse methods are also processed on this server, analyzing existing drug databases and exploring new applicability.

[0374] Based on the results analyzed by the server, the user receives suggestions for the most suitable treatment method. In this process, emotional response mechanisms are used to present information and adjust the interface according to the user's emotional state.

[0375] As a concrete example, consider a scenario where a user is searching for a treatment for a new disease. In this case, if the emotion engine detects the user's stress level, the server will organize the information concisely and present the key points clearly. As a result, the user can obtain the maximum amount of information with the minimum necessary actions.

[0376] An example of a prompt message would be, "Analyze the biological information of the specified disease and propose the optimal clinical trial plan," which would be input to the generating AI model. In this way, rapid and highly accurate medical support is achieved.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The user inputs biological information and information necessary for drug development through the terminal. The terminal temporarily stores the input data and simultaneously uses cameras and sensors to detect the user's facial expressions and movements. This information is also used to evaluate the user's emotional state. The input data includes basic information about the patient and details about the disease.

[0380] Step 2:

[0381] Data sent from the terminal is transferred to the server. The server uses information acquisition methods to integrate biological information from different formats and sources and store it in a database. In this process, the Pandas library in Python is used to combine dataframes and process missing and outlier values ​​to generate a cleaned dataset.

[0382] Step 3:

[0383] The server applies machine learning algorithms to the integrated dataset. Using libraries such as TensorFlow and SciKit-Learn, the server extracts underlying biological characteristics and patterns from the data. The output identifies biomarkers associated with specific diseases, providing important insights for treatment.

[0384] Step 4:

[0385] The server performs individual matching based on extracted biological characteristics. It executes database queries to identify highly similar patient groups and lists this information in a format usable for therapeutic research and clinical trials. This allows users to efficiently plan trials.

[0386] Step 5:

[0387] The server executes drug reuse mechanisms and screens existing drug databases. It searches for similar drugs based on chemical structure and biological properties and evaluates their potential for new applications. This expands treatment options and may lead to the discovery of uncharted treatment methods.

[0388] Step 6:

[0389] The server uses treatment decision support tools to propose the optimal treatment plan based on individual patient information. The proposed treatment plan is displayed on the terminal in an easy-to-understand format. The emotional response tool adjusts the interface according to the user's emotional state and summarizes information concisely as needed.

[0390] Step 7:

[0391] The user decides on a treatment plan based on the information and suggestions presented. The user can input prompts into the AI ​​model to receive further analysis and suggestions. For example, by inputting a prompt such as, "Please suggest the optimal treatment for the specified disease," the system can provide detailed feedback.

[0392] (Application Example 2)

[0393] 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 will be referred to as the "terminal."

[0394] In medical and nursing care settings, the systems used by healthcare professionals are often complex and can cause stress and fatigue. This makes it difficult to provide optimal medical and nursing care services. Furthermore, while rapid and appropriate responses tailored to individual patient conditions are required, conventional technologies struggle to adequately support this. Additionally, the lack of information presentation that considers the emotional state of healthcare professionals can hinder effective work performance.

[0395] 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.

[0396] In this invention, the server includes means for collecting and integrating biomedical data, means for applying machine learning algorithms to the integrated data to extract biomedical patterns, and means for providing an emotion engine that evaluates the user's emotional state and adjusts the interface to optimize information presentation. This enables the presentation of appropriate information according to the user's emotional state, as well as improved work efficiency and the provision of optimal care plans for patients.

[0397] "Biomedical data" refers to data such as test results, genetic information, and patient clinical information obtained in medical and biological research.

[0398] "Data collection methods" refer to devices and technologies for collecting and integrating biomedical data.

[0399] A "machine learning algorithm" is a computational method used in data analysis that automatically learns patterns and insights from data.

[0400] A "biomedicinal pattern" is a consistent characteristic or feature extracted from biomedical data that is associated with a particular disease or condition.

[0401] "Patient matching methods" refer to methods or systems for appropriately selecting patients to participate in clinical trials.

[0402] "Drug repositioning methods" are techniques that explore the possibility of repurposing existing pharmaceuticals for new indications.

[0403] "Clinical decision-making support tools" are support tools that enable healthcare professionals to propose the most suitable treatment method based on individual patient information.

[0404] An "emotion engine" is a technology that evaluates the user's emotional state and optimizes the system's interface and information delivery accordingly.

[0405] "Users" refer to healthcare professionals and care staff who utilize this system.

[0406] To implement this invention, it is necessary to build a system incorporating an emotion engine. The main components of the system include a server that integrates and analyzes data, a terminal that evaluates the user's emotional state, and the users themselves, such as healthcare professionals and care staff.

[0407] The server collects and integrates biomedical data and extracts biomedical patterns using machine learning algorithms. Apache Hadoop is used for data management, and TensorFlow for machine learning. Based on the extracted patterns, patient matching is performed, and the optimal treatment is proposed. Drug repositioning is also performed to explore new indications from the compound library.

[0408] The device is equipped with an emotion engine that evaluates the user's emotional state based on their facial expressions and voice data. Based on this evaluation, the server adjusts how information is displayed, presenting the information the user needs in an easy-to-understand manner. This reduces user stress caused by information overload and improves work efficiency.

[0409] For example, if a caregiver feels fatigued during nighttime rounds, the emotional engine will detect it. Because the information is presented concisely and to the point, caregivers can provide care efficiently.

[0410] An example of a prompt from a generated AI model is, "Please design a smart app for caregivers that analyzes emotions, adjusts the interface accordingly, and allows them to easily check care plans during night shifts." By adjusting the interface in response to emotions in this way, user-centered healthcare delivery can be achieved.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] The server collects biomedical data. It receives a wide variety of biomedical information from electronic medical record systems and research databases as input. To integrate this information, it uses Apache Hadoop to store the data and perform data cleansing while maintaining consistency. The output is an integrated and refined dataset.

[0414] Step 2:

[0415] The server applies machine learning algorithms to the integrated dataset. The input is the dataset prepared in Step 1. This allows for data analysis using TensorFlow, and biomedical patterns are extracted. The resulting output is patterns associated with specific diseases or patient conditions.

[0416] Step 3:

[0417] The server matches patients for clinical trials based on the extracted patterns. The input consists of the biomedical patterns extracted in step 2 and individual patient information. The server compares this information to identify and list suitable patients. The output is a list of patients suitable for clinical trials and treatment plans.

[0418] Step 4:

[0419] The device evaluates the emotional state of the user (healthcare worker or caregiver). Inputs include the user's facial expressions and voice data acquired through the camera and microphone. An emotion engine analyzes this data to determine the user's level of fatigue and stress. The output is the evaluation result regarding the user's emotional state.

[0420] Step 5:

[0421] The server adjusts the information presentation interface based on the emotional state assessment results. The inputs are the assessment results obtained in step 4 and the medical information requested by the user. The server adjusts the complexity and amount of information in the interface to present the information in the most easily understandable way for the user. This process results in an information presentation screen optimized for user accessibility.

[0422] Step 6:

[0423] Users access optimized information screens using their terminals and perform procedures necessary for treatment planning and patient care. Input consists of finely tuned information provided by the server. Based on this information, users efficiently develop and implement care plans. Output is the optimal treatment or care plan to be implemented.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] As an embodiment for carrying out the present invention, an innovative drug development system utilizing AI will be described. This system aims to efficiently collect, integrate, and analyze biomedical data to accelerate the development of drugs for rare and intractable diseases.

[0441] Users access the system at startup and specify the necessary datasets according to their research objectives and target diseases. The server then collects vast amounts of biomedical data from internal and external databases, forming a centralized data pool.

[0442] The server analyzes the collected data using machine learning algorithms to extract insights related to biomedical patterns and disease mechanisms. For example, it may discover a correlation between specific gene mutations and disease progression.

[0443] Furthermore, when users plan clinical trials, they can utilize the patient matching function provided by the server. This function helps to efficiently conduct trials by matching data with historical data and identifying highly similar patient groups.

[0444] Furthermore, the system includes a drug repositioning function. The server screens existing compound libraries and explores potential applications for new diseases. This approach can, for example, suggest that an antiviral drug may also be effective against certain types of cancer.

[0445] The terminal is equipped with an interface for inputting individual patient information, which allows the server to suggest the optimal treatment plan. For example, it can predict how effective existing treatments will be for patients with a specific genetic background and develop a treatment plan optimized for that patient.

[0446] This system enables users to effectively approach rare and intractable diseases that were difficult to treat with conventional methods. By combining the collection and analysis of vast amounts of data with AI-powered patient matching and drug repositioning functions, a significant increase in the efficiency of drug development is expected.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] The user specifies the necessary datasets based on the research objectives and target diseases through the system interface.

[0450] Step 2:

[0451] The server collects biomedical data from internal and external databases based on specified criteria. This data includes patient medical information, genetic information, and research information from public databases.

[0452] Step 3:

[0453] The server integrates the collected data and performs data cleansing. This process corrects missing values ​​and outliers, preparing the data for analysis.

[0454] Step 4:

[0455] The server applies machine learning algorithms to the cleansed data to analyze biomedical patterns, particularly identifying disease-related specific gene mutations and pathological phenomena.

[0456] Step 5:

[0457] Users review the obtained analysis results and use them to formulate research hypotheses and develop experimental plans.

[0458] Step 6:

[0459] The server performs a patient matching process to identify the patient group eligible for clinical trials. It compares current data with past data to extract patients with high similarity.

[0460] Step 7:

[0461] The terminal displays the extracted patient list to the user and assists in its use in clinical trial planning.

[0462] Step 8:

[0463] The server analyzes compound libraries and performs drug repositioning. It identifies newly applicable drugs and predicts their interactions and effects.

[0464] Step 9:

[0465] The terminal provides an interface for entering individual patient data and, based on the information entered by the user, suggests the most suitable treatment plan for the patient.

[0466] Step 10:

[0467] The server generates detailed evaluation results regarding the proposed treatment and presents them to the user via the terminal. This allows the user to obtain the information necessary to determine the optimal treatment plan.

[0468] (Example 1)

[0469] 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."

[0470] In the field of biomedicine, developing treatments for rare and intractable diseases presents challenges with conventional methods, such as the complexity and time-consuming nature of data collection and analysis. Furthermore, finding the optimal treatment for each patient is not easy, highlighting the need for efficient methods to explore the potential of new drug applications.

[0471] 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.

[0472] In this invention, the server includes an information gathering means for collecting and integrating bioscientific information, an information analysis means for extracting biomedical trends by applying machine learning techniques, and a subject selection means for identifying subjects to be studied based on the extracted trends. This enables the efficient collection and analysis of complex biomedical data, leading to the proposal of optimal treatments for patients and the discovery of new drug applications.

[0473] "Life science information" refers to a broad range of information, including biological and medical data such as genetic data, patient statistics, and disease-related information.

[0474] "Information gathering means" refers to methods and systems for efficiently acquiring and centralizing necessary data from various databases and information sources.

[0475] "Machine learning technology" refers to algorithms and techniques that enable computers to automatically learn patterns and insights from data to make predictions and decisions.

[0476] "Information analysis methods" refer to methods and processes for applying machine learning techniques to collected data to extract specific trends or patterns.

[0477] A "subject selection method" is an approach to identify the optimal subjects for an experiment or treatment based on analyzed data.

[0478] A "pharmaceutical group" is a collection of already known drugs and compounds, and is a group of substances for which new applications are being explored.

[0479] "Drug reuse methods" refer to methods for re-evaluating existing drug populations and examining whether they are applicable to new diseases.

[0480] "Medical decision-making support tools" are processes or tools that propose optimal treatment plans and prescriptions based on individual patient information.

[0481] In carrying out this invention, the following methods are appropriate.

[0482] User actions

[0483] Users access the system using a terminal and specify the disease and related life science information they wish to analyze based on their research objectives. Using the terminal's interface, users can select and input the target disease name, genetic information, and other relevant details.

[0484] Server Processing

[0485] The server collects relevant life science information from internal and external databases according to user-specified conditions. This process utilizes data aggregation software and storage systems suitable for handling large datasets, such as widely used database software and cloud services. The collected data is integrated and analyzed using machine learning techniques. This analysis process leverages analytical libraries using Python and R to extract patterns and associations for specific diseases. The server also screens existing drug populations for drug repositioning and explores new applicability. At this stage, data mining techniques are used to generate models that predict the effects of compounds on diseases.

[0486] Device functions

[0487] The terminal is equipped with an input interface for individual patient information, and the server proposes a treatment plan based on the entered information. This information flow occurs through web and mobile applications, and the AI ​​model on the server prioritizes developing an individualized treatment plan. In particular, handling genomic information is required to take into account the patient's genetic background.

[0488] Examples of specific cases and prompt statements

[0489] As a concrete example, this system can be used to analyze data on rare genetic diseases and quickly discover new drugs to treat diseases caused by specific gene mutations. It may also be possible to apply existing antiviral drugs to the treatment of newly discovered cancers. A suitable prompt for the generating AI model would be: "Please propose a method for analyzing the relationship between gene mutations and symptoms to develop new treatments for rare diseases. Also, please tell me about the potential for new disease applications of existing drugs."

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1:

[0492] Users access the system via a terminal and select a dataset to specify the target disease or research subject. This input includes the disease name and associated genetic information, which forms the basis of the data handled by the system. The terminal's function is to accurately transmit the user's input information to the server.

[0493] Step 2:

[0494] The server receives the user-specified background data as input and begins the process of collecting relevant life science information from internal and external databases. Specifically, it retrieves data by calling APIs of existing databases and integrates it. In this process, data in different formats is standardized and combined into a single, unified dataset.

[0495] Step 3:

[0496] Using the collected data, the server applies machine learning techniques and performs data analysis. Input data is supplied to the machine learning algorithm as numerical or text data. In this step, complex data calculations are performed using TensorFlow or PyTorch to extract biomedical trends and patterns of disease mechanisms. The output provides insights related to specific gene mutations and disease progression.

[0497] Step 4:

[0498] When a user plans a clinical trial, the server provides a patient matching function based on the analyzed results. Inputs include an existing patient database and historical patient information. To identify highly similar patient groups, the server compares and calculates this data, outputting optimal candidate subjects. This result is evaluated by the user and forms the basis of the trial design.

[0499] Step 5:

[0500] The server then performs drug repositioning within the existing drug population. It receives compound information as input and processes it to explore whether the compound is applicable to a new disease. Here, data mining techniques are used to build a predictive model of the association between existing drugs and new applicable diseases. The output is a list of potential drug candidates.

[0501] Step 6:

[0502] The terminal provides an interface for suggesting the optimal treatment plan based on information received from the server, once individual patient information is entered. The entered patient information includes genetic background and past treatment history. The server uses a generative AI model to create the most suitable treatment plan, which is then presented to the user through the terminal. The output is a treatment suggestion tailored to the patient.

[0503] (Application Example 1)

[0504] 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."

[0505] The secure handling of biomedical information in healthcare settings and the prevention of unauthorized access to highly confidential information are critical challenges. In particular, accessing information using smart devices requires appropriate authentication processes, but current systems may not provide sufficient security. Furthermore, rapid and secure information processing methods are necessary to efficiently explore new drug applicability and propose optimal treatments.

[0506] 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.

[0507] In this invention, the server includes information gathering means for collecting and integrating biomedical information, information analysis means for applying machine learning algorithms based on the integrated information, and access management means for strengthening the authentication process based on extracted patterns. This enables the secure handling of biomedical information, prevents unauthorized access to confidential information, and further allows for the exploration of new drug applicability and the proposal of optimal treatment methods through the utilization of the information.

[0508] "Biomedical information" is a general term for data related to biology and medicine, including a patient's health status, genetic information, and medical history.

[0509] "Information gathering means" refers to methods and devices for collecting and integrating necessary data from various sources.

[0510] A "machine learning algorithm" is a program that automatically finds patterns and regularities from large amounts of data and uses that knowledge to make predictions and decisions.

[0511] "Information analysis methods" refer to methods and techniques for processing collected data and extracting useful insights.

[0512] An "authentication process" is a set of procedures and technologies used to verify the identity of users and devices accessing an information system and to grant them appropriate permissions.

[0513] "Access control measures" refer to methods and technologies for controlling access to information and preventing its misuse.

[0514] "Repositioning means" refers to methods or processes for applying existing resources or information to new purposes or uses.

[0515] "Decision support tools" are methods and systems that analyze and present data and information to help users make the best choices.

[0516] This invention is a system for ensuring the secure handling and utilization of biomedical information. The server begins by collecting and integrating biomedical information, and then analyzes the information using machine learning algorithms. Based on the extracted biomedical patterns, it strengthens the authentication process and manages unauthorized access to the information.

[0517] Specifically, this system operates on smart devices such as smartphones running iOS or Android, and smart glasses. The software is developed using AI frameworks such as TensorFlow and PyTorch, and securely accesses information by analyzing the user's biometric information and behavioral patterns. If authentication is successful, the user will be able to access the necessary information; otherwise, additional authentication steps will be required.

[0518] As a concrete example, consider a scenario where a medical staff member, as the user, wears smart glasses and accesses the system through voice and facial recognition. This allows for immediate access to confidential information such as patients' electronic medical records, enabling them to perform their duties securely.

[0519] Furthermore, it is possible to analyze diverse information using generative AI models and explore new drug application possibilities. For example, using prompts such as, "Design a prototype application that enables secure access to medical data using AI," can assist in exploring specific implementation methods.

[0520] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0521] Step 1:

[0522] The server collects biomedical information from multiple sources and stores it in an integrated database through data collection methods. The input is biomedical data from healthcare and research institutions, and the output is the integrated database containing this information. At this stage, data preprocessing is performed to standardize and ensure consistency of the data format.

[0523] Step 2:

[0524] The server analyzes an integrated database using machine learning algorithms and extracts biomedical patterns. The input is data from the integrated database, and the output is pattern data as a result of the analysis. This process utilizes AI frameworks such as TensorFlow and PyTorch, performing regression analysis and clustering to understand the characteristics of the data.

[0525] Step 3:

[0526] The terminal initiates an authentication process when attempting to access information via the user's smart device. The input is the user's biometric information (e.g., facial image or voice data), and the output is the authentication result. Facial recognition and voice recognition technologies are used to verify the user's identity.

[0527] Step 4:

[0528] The server securely provides information to authenticated users. Input is the requested information of the authenticated user, and output is the requested medical data. The data is appropriately filtered based on access permissions before being provided to the user.

[0529] Step 5:

[0530] The server immediately alerts the administrator upon detecting unauthorized access. Inputs are data from access logs and anomaly detection systems, and output is an alert notification to the administrator. Log analysis and anomaly detection algorithms are used to identify abnormal patterns and implement necessary countermeasures.

[0531] Step 6:

[0532] The server uses a generative AI model to analyze multiple information sources and explore new drug applicability possibilities. Inputs are an integrated database and existing drug information, and outputs are newly proposed treatments and drug application candidates. The exploration results are provided to healthcare professionals through decision support tools, utilizing prompts such as, "Design a prototype application that enables secure access to medical data using AI."

[0533] 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.

[0534] As an embodiment for carrying out the present invention, a drug development support system incorporating an emotion engine will be described. This system includes integration and analysis of biomedical data, patient matching, drug repositioning, and clinical decision support, and further has a function that takes into account the user's emotional state.

[0535] The user first accesses the system and specifies the necessary data according to their purpose and target disease. At that time, an emotion engine is activated on the terminal to estimate the user's emotions from their actions and facial expressions, and to identify the user's stress and fatigue levels.

[0536] The server integrates the specified and collected biomedical data and performs data cleansing. It then analyzes the dataset using machine learning algorithms to discover biomedical patterns.

[0537] The server identifies highly similar patient groups based on discovered patterns and assists users in planning clinical trials. During this process, the interface is adjusted according to the user's emotional state, as assessed by the emotion engine, to ensure the user receives information most effectively.

[0538] In the drug repositioning function, the server screens existing drugs from a compound library and evaluates their potential for new applications. This enables effective approaches to a wide range of diseases.

[0539] The terminal provides a user interface for entering individual patient information, and based on this information, the server proposes the most suitable treatment plan for the patient. This proposal also reflects the user's emotional state, and feedback and the order of suggestions are optimized as needed.

[0540] For example, if a user is searching for treatment for an elderly patient and the emotion engine detects their own fatigue, the server will adjust its presentation to present information in a concise and easy-to-understand format, minimizing the number of steps required. This process reduces the user's burden while maximizing effectiveness.

[0541] By incorporating an emotional engine, this system becomes more human-centered than conventional approaches, enabling more intuitive and effective use. This is expected to lead to the rapid development of treatments for rare and intractable diseases, thereby improving the quality of medical care.

[0542] The following describes the processing flow.

[0543] Step 1:

[0544] The user logs into the system and enters parameters related to the research objectives and target disease into the terminal. Based on this input, the entire system processing begins.

[0545] Step 2:

[0546] The device uses its built-in camera and sensors to analyze facial expressions and voice tone during user interaction, and an emotion engine evaluates the user's emotional state. This information is sent to a server for later interface adjustments.

[0547] Step 3:

[0548] The server automatically collects biomedical data from internal and external databases based on specified conditions. The collected data is centralized and prepared for analysis through a data cleansing process.

[0549] Step 4:

[0550] The server applies machine learning algorithms to the cleansed data to extract disease-related biomedical patterns. The identified patterns are visualized and sent to the terminal for use in research.

[0551] Step 5:

[0552] The server uses the extracted patterns to identify patient groups eligible for clinical trials. It evaluates patient similarity and displays the most suitable candidate group as a list on the terminal.

[0553] Step 6:

[0554] Based on the sentiment evaluation results from the emotion engine, the device adjusts the interface to allow the user to receive information most effectively, and appropriately adjusts the amount and display order of the data presented.

[0555] Step 7:

[0556] The server analyzes the compound library and performs a drug repositioning process to discover new applicability. It then reports newly identified potential applications to the user.

[0557] Step 8:

[0558] The terminal provides a user-friendly interface for entering individual patient data and aggregates the entered data before sending it to the server.

[0559] Step 9:

[0560] The server determines the optimal treatment plan and generates a suggested plan based on the transmitted patient data. During this process, it provides flexible suggestions that incorporate an emotion engine, and sends the results to the terminal.

[0561] Step 10:

[0562] Users review recommended treatments and clinical trial plans and determine the next steps. This entire process accelerates research and prepares the system to apply the best possible treatment approach to patients.

[0563] (Example 2)

[0564] 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."

[0565] Conventional drug development support systems have faced challenges in integrating and analyzing biological information, making it difficult to rapidly identify effective treatment methods in personalized medicine. Furthermore, they have been unable to consider the user's emotions and stress levels during system use, limiting the quality of the user experience.

[0566] 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.

[0567] In this invention, the server includes information acquisition means for acquiring and integrating biological information, information analysis means for applying a machine learning algorithm to the integrated information to extract biological characteristics, and emotion response means for detecting the user's emotional state and adjusting the user interface according to the detected state. This enables rapid and accurate identification of treatment methods based on biological characteristics and the provision of an interface that takes the user's emotions into consideration.

[0568] "Information acquisition means" refers to a component that has the function of acquiring and integrating biological information.

[0569] "Information analysis means" refers to a device or process for applying machine learning algorithms to integrated biological information and extracting biological characteristics.

[0570] "Individual matching means" are components used to identify individuals that are the target of therapeutic research based on extracted biological characteristics.

[0571] A "drug reuse method" is a system configuration for analyzing existing drug databases and exploring new applicability possibilities.

[0572] A "treatment decision support device" is a support system that proposes the optimal treatment method based on individual patient information.

[0573] An "emotional response means" is a component that has the function of detecting the user's emotional state and adjusting the user interface according to the detected state.

[0574] In an embodiment of this invention, the entire system is designed to effectively process biological information and provide an interface that takes into account the user's emotional state. The three main components here are the terminal, the server, and the user.

[0575] The terminal is the primary interface for acquiring biological information input from the user. Equipped with cameras and sensors, the terminal detects the user's emotional state by analyzing their facial expressions and physical reactions. Users also input biological information and information necessary for drug development through the terminal.

[0576] The server integrates biological information based on data transmitted from terminals through information acquisition and analysis methods, and analyzes the information using machine learning algorithms. Specific tools used for data integration and analysis include the Python Pandas library and TensorFlow. As a result of the analysis, biological characteristics are extracted, and based on these, individual matching is performed to identify individuals suitable for treatment. Drug reuse methods are also processed on this server, analyzing existing drug databases and exploring new applicability.

[0577] Based on the results analyzed by the server, the user receives suggestions for the most suitable treatment method. In this process, emotional response mechanisms are used to present information and adjust the interface according to the user's emotional state.

[0578] As a concrete example, consider a scenario where a user is searching for a treatment for a new disease. In this case, if the emotion engine detects the user's stress level, the server will organize the information concisely and present the key points clearly. As a result, the user can obtain the maximum amount of information with the minimum necessary actions.

[0579] An example of a prompt message would be, "Analyze the biological information of the specified disease and propose the optimal clinical trial plan," which would be input to the generating AI model. In this way, rapid and highly accurate medical support is achieved.

[0580] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0581] Step 1:

[0582] The user inputs biological information and information necessary for drug development through the terminal. The terminal temporarily stores the input data and simultaneously uses cameras and sensors to detect the user's facial expressions and movements. This information is also used to evaluate the user's emotional state. The input data includes basic information about the patient and details about the disease.

[0583] Step 2:

[0584] Data sent from the terminal is transferred to the server. The server uses information acquisition methods to integrate biological information from different formats and sources and store it in a database. In this process, the Pandas library in Python is used to combine dataframes and process missing and outlier values ​​to generate a cleaned dataset.

[0585] Step 3:

[0586] The server applies machine learning algorithms to the integrated dataset. Using libraries such as TensorFlow and SciKit-Learn, the server extracts underlying biological characteristics and patterns from the data. The output identifies biomarkers associated with specific diseases, providing important insights for treatment.

[0587] Step 4:

[0588] The server performs individual matching based on extracted biological characteristics. It executes database queries to identify highly similar patient groups and lists this information in a format usable for therapeutic research and clinical trials. This allows users to efficiently plan trials.

[0589] Step 5:

[0590] The server executes drug reuse mechanisms and screens existing drug databases. It searches for similar drugs based on chemical structure and biological properties and evaluates their potential for new applications. This expands treatment options and may lead to the discovery of uncharted treatment methods.

[0591] Step 6:

[0592] The server uses treatment decision support tools to propose the optimal treatment plan based on individual patient information. The proposed treatment plan is displayed on the terminal in an easy-to-understand format. The emotional response tool adjusts the interface according to the user's emotional state and summarizes information concisely as needed.

[0593] Step 7:

[0594] The user decides on a treatment plan based on the information and suggestions presented. The user can input prompts into the AI ​​model to receive further analysis and suggestions. For example, by inputting a prompt such as, "Please suggest the optimal treatment for the specified disease," the system can provide detailed feedback.

[0595] (Application Example 2)

[0596] 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."

[0597] In medical and nursing care settings, the systems used by healthcare professionals are often complex and can cause stress and fatigue. This makes it difficult to provide optimal medical and nursing care services. Furthermore, while rapid and appropriate responses tailored to individual patient conditions are required, conventional technologies struggle to adequately support this. Additionally, the lack of information presentation that considers the emotional state of healthcare professionals can hinder effective work performance.

[0598] 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.

[0599] In this invention, the server includes means for collecting and integrating biomedical data, means for applying machine learning algorithms to the integrated data to extract biomedical patterns, and means for providing an emotion engine that evaluates the user's emotional state and adjusts the interface to optimize information presentation. This enables the presentation of appropriate information according to the user's emotional state, as well as improved work efficiency and the provision of optimal care plans for patients.

[0600] "Biomedical data" refers to data such as test results, genetic information, and patient clinical information obtained in medical and biological research.

[0601] "Data collection methods" refer to devices and technologies for collecting and integrating biomedical data.

[0602] A "machine learning algorithm" is a computational method used in data analysis that automatically learns patterns and insights from data.

[0603] A "biomedicinal pattern" is a consistent characteristic or feature extracted from biomedical data that is associated with a particular disease or condition.

[0604] "Patient matching methods" refer to methods or systems for appropriately selecting patients to participate in clinical trials.

[0605] "Drug repositioning methods" are techniques that explore the possibility of repurposing existing pharmaceuticals for new indications.

[0606] "Clinical decision-making support tools" are support tools that enable healthcare professionals to propose the most suitable treatment method based on individual patient information.

[0607] An "emotion engine" is a technology that evaluates the user's emotional state and optimizes the system's interface and information delivery accordingly.

[0608] "Users" refer to healthcare professionals and care staff who utilize this system.

[0609] To implement this invention, it is necessary to build a system incorporating an emotion engine. The main components of the system include a server that integrates and analyzes data, a terminal that evaluates the user's emotional state, and the users themselves, such as healthcare professionals and care staff.

[0610] The server collects and integrates biomedical data and extracts biomedical patterns using machine learning algorithms. Apache Hadoop is used for data management, and TensorFlow for machine learning. Based on the extracted patterns, patient matching is performed, and the optimal treatment is proposed. Drug repositioning is also performed to explore new indications from the compound library.

[0611] The device is equipped with an emotion engine that evaluates the user's emotional state based on their facial expressions and voice data. Based on this evaluation, the server adjusts how information is displayed, presenting the information the user needs in an easy-to-understand manner. This reduces user stress caused by information overload and improves work efficiency.

[0612] For example, if a caregiver feels fatigued during nighttime rounds, the emotional engine will detect it. Because the information is presented concisely and to the point, caregivers can provide care efficiently.

[0613] An example of a prompt from a generated AI model is, "Please design a smart app for caregivers that analyzes emotions, adjusts the interface accordingly, and allows them to easily check care plans during night shifts." By adjusting the interface in response to emotions in this way, user-centered healthcare delivery can be achieved.

[0614] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0615] Step 1:

[0616] The server collects biomedical data. It receives a wide variety of biomedical information from electronic medical record systems and research databases as input. To integrate this information, it uses Apache Hadoop to store the data and perform data cleansing while maintaining consistency. The output is an integrated and refined dataset.

[0617] Step 2:

[0618] The server applies machine learning algorithms to the integrated dataset. The input is the dataset prepared in Step 1. This allows for data analysis using TensorFlow, and biomedical patterns are extracted. The resulting output is patterns associated with specific diseases or patient conditions.

[0619] Step 3:

[0620] The server matches patients for clinical trials based on the extracted patterns. The input consists of the biomedical patterns extracted in step 2 and individual patient information. The server compares this information to identify and list suitable patients. The output is a list of patients suitable for clinical trials and treatment plans.

[0621] Step 4:

[0622] The device evaluates the emotional state of the user (healthcare worker or caregiver). Inputs include the user's facial expressions and voice data acquired through the camera and microphone. An emotion engine analyzes this data to determine the user's level of fatigue and stress. The output is the evaluation result regarding the user's emotional state.

[0623] Step 5:

[0624] The server adjusts the information presentation interface based on the emotional state assessment results. The inputs are the assessment results obtained in step 4 and the medical information requested by the user. The server adjusts the complexity and amount of information in the interface to present the information in the most easily understandable way for the user. This process results in an information presentation screen optimized for user accessibility.

[0625] Step 6:

[0626] Users access optimized information screens using their terminals and perform procedures necessary for treatment planning and patient care. Input consists of finely tuned information provided by the server. Based on this information, users efficiently develop and implement care plans. Output is the optimal treatment or care plan to be implemented.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] [Fourth Embodiment]

[0631] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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".

[0644] As an embodiment for carrying out the present invention, an innovative drug development system utilizing AI will be described. This system aims to efficiently collect, integrate, and analyze biomedical data to accelerate the development of drugs for rare and intractable diseases.

[0645] Users access the system at startup and specify the necessary datasets according to their research objectives and target diseases. The server then collects vast amounts of biomedical data from internal and external databases, forming a centralized data pool.

[0646] The server analyzes the collected data using machine learning algorithms to extract insights related to biomedical patterns and disease mechanisms. For example, it may discover a correlation between specific gene mutations and disease progression.

[0647] Furthermore, when users plan clinical trials, they can utilize the patient matching function provided by the server. This function helps to efficiently conduct trials by matching data with historical data and identifying highly similar patient groups.

[0648] Furthermore, the system includes a drug repositioning function. The server screens existing compound libraries and explores potential applications for new diseases. This approach can, for example, suggest that an antiviral drug may also be effective against certain types of cancer.

[0649] The terminal is equipped with an interface for inputting individual patient information, which allows the server to suggest the optimal treatment plan. For example, it can predict how effective existing treatments will be for patients with a specific genetic background and develop a treatment plan optimized for that patient.

[0650] This system enables users to effectively approach rare and intractable diseases that were difficult to treat with conventional methods. By combining the collection and analysis of vast amounts of data with AI-powered patient matching and drug repositioning functions, a significant increase in the efficiency of drug development is expected.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The user specifies the necessary datasets based on the research objectives and target diseases through the system interface.

[0654] Step 2:

[0655] The server collects biomedical data from internal and external databases based on specified criteria. This data includes patient medical information, genetic information, and research information from public databases.

[0656] Step 3:

[0657] The server integrates the collected data and performs data cleansing. This process corrects missing values ​​and outliers, preparing the data for analysis.

[0658] Step 4:

[0659] The server applies machine learning algorithms to the cleansed data to analyze biomedical patterns, particularly identifying disease-related specific gene mutations and pathological phenomena.

[0660] Step 5:

[0661] Users review the obtained analysis results and use them to formulate research hypotheses and develop experimental plans.

[0662] Step 6:

[0663] The server performs a patient matching process to identify the patient group eligible for clinical trials. It compares current data with past data to extract patients with high similarity.

[0664] Step 7:

[0665] The terminal displays the extracted patient list to the user and assists in its use in clinical trial planning.

[0666] Step 8:

[0667] The server analyzes compound libraries and performs drug repositioning. It identifies newly applicable drugs and predicts their interactions and effects.

[0668] Step 9:

[0669] The terminal provides an interface for entering individual patient data and, based on the information entered by the user, suggests the most suitable treatment plan for the patient.

[0670] Step 10:

[0671] The server generates detailed evaluation results regarding the proposed treatment and presents them to the user via the terminal. This allows the user to obtain the information necessary to determine the optimal treatment plan.

[0672] (Example 1)

[0673] 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".

[0674] In the field of biomedicine, developing treatments for rare and intractable diseases presents challenges with conventional methods, such as the complexity and time-consuming nature of data collection and analysis. Furthermore, finding the optimal treatment for each patient is not easy, highlighting the need for efficient methods to explore the potential of new drug applications.

[0675] 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.

[0676] In this invention, the server includes an information gathering means for collecting and integrating bioscientific information, an information analysis means for extracting biomedical trends by applying machine learning techniques, and a subject selection means for identifying subjects to be studied based on the extracted trends. This enables the efficient collection and analysis of complex biomedical data, leading to the proposal of optimal treatments for patients and the discovery of new drug applications.

[0677] "Life science information" refers to a broad range of information, including biological and medical data such as genetic data, patient statistics, and disease-related information.

[0678] "Information gathering means" refers to methods and systems for efficiently acquiring and centralizing necessary data from various databases and information sources.

[0679] "Machine learning technology" refers to algorithms and techniques that enable computers to automatically learn patterns and insights from data to make predictions and decisions.

[0680] "Information analysis methods" refer to methods and processes for applying machine learning techniques to collected data to extract specific trends or patterns.

[0681] A "subject selection method" is an approach to identify the optimal subjects for an experiment or treatment based on analyzed data.

[0682] A "pharmaceutical group" is a collection of already known drugs and compounds, and is a group of substances for which new applications are being explored.

[0683] "Drug reuse methods" refer to methods for re-evaluating existing drug populations and examining whether they are applicable to new diseases.

[0684] "Medical decision-making support tools" are processes or tools that propose optimal treatment plans and prescriptions based on individual patient information.

[0685] In carrying out this invention, the following methods are appropriate.

[0686] User actions

[0687] Users access the system using a terminal and specify the disease and related life science information they wish to analyze based on their research objectives. Using the terminal's interface, users can select and input the target disease name, genetic information, and other relevant details.

[0688] Server Processing

[0689] The server collects relevant life science information from internal and external databases according to user-specified conditions. This process utilizes data aggregation software and storage systems suitable for handling large datasets, such as widely used database software and cloud services. The collected data is integrated and analyzed using machine learning techniques. This analysis process leverages analytical libraries using Python and R to extract patterns and associations for specific diseases. The server also screens existing drug populations for drug repositioning and explores new applicability. At this stage, data mining techniques are used to generate models that predict the effects of compounds on diseases.

[0690] Device functions

[0691] The terminal is equipped with an input interface for individual patient information, and the server proposes a treatment plan based on the entered information. This information flow occurs through web and mobile applications, and the AI ​​model on the server prioritizes developing an individualized treatment plan. In particular, handling genomic information is required to take into account the patient's genetic background.

[0692] Examples of specific cases and prompt statements

[0693] As a concrete example, this system can be used to analyze data on rare genetic diseases and quickly discover new drugs to treat diseases caused by specific gene mutations. It may also be possible to apply existing antiviral drugs to the treatment of newly discovered cancers. A suitable prompt for the generating AI model would be: "Please propose a method for analyzing the relationship between gene mutations and symptoms to develop new treatments for rare diseases. Also, please tell me about the potential for new disease applications of existing drugs."

[0694] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0695] Step 1:

[0696] Users access the system via a terminal and select a dataset to specify the target disease or research subject. This input includes the disease name and associated genetic information, which forms the basis of the data handled by the system. The terminal's function is to accurately transmit the user's input information to the server.

[0697] Step 2:

[0698] The server receives the user-specified background data as input and begins the process of collecting relevant life science information from internal and external databases. Specifically, it retrieves data by calling APIs of existing databases and integrates it. In this process, data in different formats is standardized and combined into a single, unified dataset.

[0699] Step 3:

[0700] Using the collected data, the server applies machine learning techniques and performs data analysis. Input data is supplied to the machine learning algorithm as numerical or text data. In this step, complex data calculations are performed using TensorFlow or PyTorch to extract biomedical trends and patterns of disease mechanisms. The output provides insights related to specific gene mutations and disease progression.

[0701] Step 4:

[0702] When a user plans a clinical trial, the server provides a patient matching function based on the analyzed results. Inputs include an existing patient database and historical patient information. To identify highly similar patient groups, the server compares and calculates this data, outputting optimal candidate subjects. This result is evaluated by the user and forms the basis of the trial design.

[0703] Step 5:

[0704] The server then performs drug repositioning within the existing drug population. It receives compound information as input and processes it to explore whether the compound is applicable to a new disease. Here, data mining techniques are used to build a predictive model of the association between existing drugs and new applicable diseases. The output is a list of potential drug candidates.

[0705] Step 6:

[0706] The terminal provides an interface for suggesting the optimal treatment plan based on information received from the server, once individual patient information is entered. The entered patient information includes genetic background and past treatment history. The server uses a generative AI model to create the most suitable treatment plan, which is then presented to the user through the terminal. The output is a treatment suggestion tailored to the patient.

[0707] (Application Example 1)

[0708] 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".

[0709] The secure handling of biomedical information in healthcare settings and the prevention of unauthorized access to highly confidential information are critical challenges. In particular, accessing information using smart devices requires appropriate authentication processes, but current systems may not provide sufficient security. Furthermore, rapid and secure information processing methods are necessary to efficiently explore new drug applicability and propose optimal treatments.

[0710] 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.

[0711] In this invention, the server includes information gathering means for collecting and integrating biomedical information, information analysis means for applying machine learning algorithms based on the integrated information, and access management means for strengthening the authentication process based on extracted patterns. This enables the secure handling of biomedical information, prevents unauthorized access to confidential information, and further allows for the exploration of new drug applicability and the proposal of optimal treatment methods through the utilization of the information.

[0712] "Biomedical information" is a general term for data related to biology and medicine, including a patient's health status, genetic information, and medical history.

[0713] "Information gathering means" refers to methods and devices for collecting and integrating necessary data from various sources.

[0714] A "machine learning algorithm" is a program that automatically finds patterns and regularities from large amounts of data and uses that knowledge to make predictions and decisions.

[0715] "Information analysis methods" refer to methods and techniques for processing collected data and extracting useful insights.

[0716] An "authentication process" is a set of procedures and technologies used to verify the identity of users and devices accessing an information system and to grant them appropriate permissions.

[0717] "Access control measures" refer to methods and technologies for controlling access to information and preventing its misuse.

[0718] "Repositioning means" refers to methods or processes for applying existing resources or information to new purposes or uses.

[0719] "Decision support tools" are methods and systems that analyze and present data and information to help users make the best choices.

[0720] This invention is a system for ensuring the secure handling and utilization of biomedical information. The server begins by collecting and integrating biomedical information, and then analyzes the information using machine learning algorithms. Based on the extracted biomedical patterns, it strengthens the authentication process and manages unauthorized access to the information.

[0721] Specifically, this system operates on smart devices such as smartphones running iOS or Android, and smart glasses. The software is developed using AI frameworks such as TensorFlow and PyTorch, and securely accesses information by analyzing the user's biometric information and behavioral patterns. If authentication is successful, the user will be able to access the necessary information; otherwise, additional authentication steps will be required.

[0722] As a concrete example, consider a scenario where a medical staff member, as the user, wears smart glasses and accesses the system through voice and facial recognition. This allows for immediate access to confidential information such as patients' electronic medical records, enabling them to perform their duties securely.

[0723] Furthermore, it is possible to analyze diverse information using generative AI models and explore new drug application possibilities. For example, using prompts such as, "Design a prototype application that enables secure access to medical data using AI," can assist in exploring specific implementation methods.

[0724] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0725] Step 1:

[0726] The server collects biomedical information from multiple sources and stores it in an integrated database through data collection methods. The input is biomedical data from healthcare and research institutions, and the output is the integrated database containing this information. At this stage, data preprocessing is performed to standardize and ensure consistency of the data format.

[0727] Step 2:

[0728] The server analyzes an integrated database using machine learning algorithms and extracts biomedical patterns. The input is data from the integrated database, and the output is pattern data as a result of the analysis. This process utilizes AI frameworks such as TensorFlow and PyTorch, performing regression analysis and clustering to understand the characteristics of the data.

[0729] Step 3:

[0730] The terminal initiates an authentication process when attempting to access information via the user's smart device. The input is the user's biometric information (e.g., facial image or voice data), and the output is the authentication result. Facial recognition and voice recognition technologies are used to verify the user's identity.

[0731] Step 4:

[0732] The server securely provides information to authenticated users. Input is the requested information of the authenticated user, and output is the requested medical data. The data is appropriately filtered based on access permissions before being provided to the user.

[0733] Step 5:

[0734] The server immediately alerts the administrator upon detecting unauthorized access. Inputs are data from access logs and anomaly detection systems, and output is an alert notification to the administrator. Log analysis and anomaly detection algorithms are used to identify abnormal patterns and implement necessary countermeasures.

[0735] Step 6:

[0736] The server uses a generative AI model to analyze multiple information sources and explore new drug applicability possibilities. Inputs are an integrated database and existing drug information, and outputs are newly proposed treatments and drug application candidates. The exploration results are provided to healthcare professionals through decision support tools, utilizing prompts such as, "Design a prototype application that enables secure access to medical data using AI."

[0737] 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.

[0738] As an embodiment for carrying out the present invention, a drug development support system incorporating an emotion engine will be described. This system includes integration and analysis of biomedical data, patient matching, drug repositioning, and clinical decision support, and further has a function that takes into account the user's emotional state.

[0739] The user first accesses the system and specifies the necessary data according to their purpose and target disease. At that time, an emotion engine is activated on the terminal to estimate the user's emotions from their actions and facial expressions, and to identify the user's stress and fatigue levels.

[0740] The server integrates the specified and collected biomedical data and performs data cleansing. It then analyzes the dataset using machine learning algorithms to discover biomedical patterns.

[0741] The server identifies highly similar patient groups based on discovered patterns and assists users in planning clinical trials. During this process, the interface is adjusted according to the user's emotional state, as assessed by the emotion engine, to ensure the user receives information most effectively.

[0742] In the drug repositioning function, the server screens existing drugs from a compound library and evaluates their potential for new applications. This enables effective approaches to a wide range of diseases.

[0743] The terminal provides a user interface for entering individual patient information, and based on this information, the server proposes the most suitable treatment plan for the patient. This proposal also reflects the user's emotional state, and feedback and the order of suggestions are optimized as needed.

[0744] For example, if a user is searching for treatment for an elderly patient and the emotion engine detects their own fatigue, the server will adjust its presentation to present information in a concise and easy-to-understand format, minimizing the number of steps required. This process reduces the user's burden while maximizing effectiveness.

[0745] By incorporating an emotional engine, this system becomes more human-centered than conventional approaches, enabling more intuitive and effective use. This is expected to lead to the rapid development of treatments for rare and intractable diseases, thereby improving the quality of medical care.

[0746] The following describes the processing flow.

[0747] Step 1:

[0748] The user logs into the system and enters parameters related to the research objectives and target disease into the terminal. Based on this input, the entire system processing begins.

[0749] Step 2:

[0750] The device uses its built-in camera and sensors to analyze facial expressions and voice tone during user interaction, and an emotion engine evaluates the user's emotional state. This information is sent to a server for later interface adjustments.

[0751] Step 3:

[0752] The server automatically collects biomedical data from internal and external databases based on specified conditions. The collected data is centralized and prepared for analysis through a data cleansing process.

[0753] Step 4:

[0754] The server applies machine learning algorithms to the cleansed data to extract disease-related biomedical patterns. The identified patterns are visualized and sent to the terminal for use in research.

[0755] Step 5:

[0756] The server uses the extracted patterns to identify patient groups eligible for clinical trials. It evaluates patient similarity and displays the most suitable candidate group as a list on the terminal.

[0757] Step 6:

[0758] Based on the sentiment evaluation results from the emotion engine, the device adjusts the interface to allow the user to receive information most effectively, and appropriately adjusts the amount and display order of the data presented.

[0759] Step 7:

[0760] The server analyzes the compound library and performs a drug repositioning process to discover new applicability. It then reports newly identified potential applications to the user.

[0761] Step 8:

[0762] The terminal provides a user-friendly interface for entering individual patient data and aggregates the entered data before sending it to the server.

[0763] Step 9:

[0764] The server determines the optimal treatment plan and generates a suggested plan based on the transmitted patient data. During this process, it provides flexible suggestions that incorporate an emotion engine, and sends the results to the terminal.

[0765] Step 10:

[0766] Users review recommended treatments and clinical trial plans and determine the next steps. This entire process accelerates research and prepares the system to apply the best possible treatment approach to patients.

[0767] (Example 2)

[0768] 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".

[0769] Conventional drug development support systems have faced challenges in integrating and analyzing biological information, making it difficult to rapidly identify effective treatment methods in personalized medicine. Furthermore, they have been unable to consider the user's emotions and stress levels during system use, limiting the quality of the user experience.

[0770] 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.

[0771] In this invention, the server includes information acquisition means for acquiring and integrating biological information, information analysis means for applying a machine learning algorithm to the integrated information to extract biological characteristics, and emotion response means for detecting the user's emotional state and adjusting the user interface according to the detected state. This enables rapid and accurate identification of treatment methods based on biological characteristics and the provision of an interface that takes the user's emotions into consideration.

[0772] "Information acquisition means" refers to a component that has the function of acquiring and integrating biological information.

[0773] "Information analysis means" refers to a device or process for applying machine learning algorithms to integrated biological information and extracting biological characteristics.

[0774] "Individual matching means" are components used to identify individuals that are the target of therapeutic research based on extracted biological characteristics.

[0775] A "drug reuse method" is a system configuration for analyzing existing drug databases and exploring new applicability possibilities.

[0776] A "treatment decision support device" is a support system that proposes the optimal treatment method based on individual patient information.

[0777] An "emotional response means" is a component that has the function of detecting the user's emotional state and adjusting the user interface according to the detected state.

[0778] In an embodiment of this invention, the entire system is designed to effectively process biological information and provide an interface that takes into account the user's emotional state. The three main components here are the terminal, the server, and the user.

[0779] The terminal is the primary interface for acquiring biological information input from the user. Equipped with cameras and sensors, the terminal detects the user's emotional state by analyzing their facial expressions and physical reactions. Users also input biological information and information necessary for drug development through the terminal.

[0780] The server integrates biological information based on data transmitted from terminals through information acquisition and analysis methods, and analyzes the information using machine learning algorithms. Specific tools used for data integration and analysis include the Python Pandas library and TensorFlow. As a result of the analysis, biological characteristics are extracted, and based on these, individual matching is performed to identify individuals suitable for treatment. Drug reuse methods are also processed on this server, analyzing existing drug databases and exploring new applicability.

[0781] Based on the results analyzed by the server, the user receives suggestions for the most suitable treatment method. In this process, emotional response mechanisms are used to present information and adjust the interface according to the user's emotional state.

[0782] As a concrete example, consider a scenario where a user is searching for a treatment for a new disease. In this case, if the emotion engine detects the user's stress level, the server will organize the information concisely and present the key points clearly. As a result, the user can obtain the maximum amount of information with the minimum necessary actions.

[0783] An example of a prompt message would be, "Analyze the biological information of the specified disease and propose the optimal clinical trial plan," which would be input to the generating AI model. In this way, rapid and highly accurate medical support is achieved.

[0784] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0785] Step 1:

[0786] The user inputs biological information and information necessary for drug development through the terminal. The terminal temporarily stores the input data and simultaneously uses cameras and sensors to detect the user's facial expressions and movements. This information is also used to evaluate the user's emotional state. The input data includes basic information about the patient and details about the disease.

[0787] Step 2:

[0788] Data sent from the terminal is transferred to the server. The server uses information acquisition methods to integrate biological information from different formats and sources and store it in a database. In this process, the Pandas library in Python is used to combine dataframes and process missing and outlier values ​​to generate a cleaned dataset.

[0789] Step 3:

[0790] The server applies machine learning algorithms to the integrated dataset. Using libraries such as TensorFlow and SciKit-Learn, the server extracts underlying biological characteristics and patterns from the data. The output identifies biomarkers associated with specific diseases, providing important insights for treatment.

[0791] Step 4:

[0792] The server performs individual matching based on extracted biological characteristics. It executes database queries to identify highly similar patient groups and lists this information in a format usable for therapeutic research and clinical trials. This allows users to efficiently plan trials.

[0793] Step 5:

[0794] The server executes drug reuse mechanisms and screens existing drug databases. It searches for similar drugs based on chemical structure and biological properties and evaluates their potential for new applications. This expands treatment options and may lead to the discovery of uncharted treatment methods.

[0795] Step 6:

[0796] The server uses treatment decision support tools to propose the optimal treatment plan based on individual patient information. The proposed treatment plan is displayed on the terminal in an easy-to-understand format. The emotional response tool adjusts the interface according to the user's emotional state and summarizes information concisely as needed.

[0797] Step 7:

[0798] The user decides on a treatment plan based on the information and suggestions presented. The user can input prompts into the AI ​​model to receive further analysis and suggestions. For example, by inputting a prompt such as, "Please suggest the optimal treatment for the specified disease," the system can provide detailed feedback.

[0799] (Application Example 2)

[0800] 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".

[0801] In medical and nursing care settings, the systems used by healthcare professionals are often complex and can cause stress and fatigue. This makes it difficult to provide optimal medical and nursing care services. Furthermore, while rapid and appropriate responses tailored to individual patient conditions are required, conventional technologies struggle to adequately support this. Additionally, the lack of information presentation that considers the emotional state of healthcare professionals can hinder effective work performance.

[0802] 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.

[0803] In this invention, the server includes means for collecting and integrating biomedical data, means for applying machine learning algorithms to the integrated data to extract biomedical patterns, and means for providing an emotion engine that evaluates the user's emotional state and adjusts the interface to optimize information presentation. This enables the presentation of appropriate information according to the user's emotional state, as well as improved work efficiency and the provision of optimal care plans for patients.

[0804] "Biomedical data" refers to data such as test results, genetic information, and patient clinical information obtained in medical and biological research.

[0805] "Data collection methods" refer to devices and technologies for collecting and integrating biomedical data.

[0806] A "machine learning algorithm" is a computational method used in data analysis that automatically learns patterns and insights from data.

[0807] A "biomedicinal pattern" is a consistent characteristic or feature extracted from biomedical data that is associated with a particular disease or condition.

[0808] "Patient matching methods" refer to methods or systems for appropriately selecting patients to participate in clinical trials.

[0809] "Drug repositioning methods" are techniques that explore the possibility of repurposing existing pharmaceuticals for new indications.

[0810] "Clinical decision-making support tools" are support tools that enable healthcare professionals to propose the most suitable treatment method based on individual patient information.

[0811] An "emotion engine" is a technology that evaluates the user's emotional state and optimizes the system's interface and information delivery accordingly.

[0812] "Users" refer to healthcare professionals and care staff who utilize this system.

[0813] To implement this invention, it is necessary to build a system incorporating an emotion engine. The main components of the system include a server that integrates and analyzes data, a terminal that evaluates the user's emotional state, and the users themselves, such as healthcare professionals and care staff.

[0814] The server collects and integrates biomedical data and extracts biomedical patterns using machine learning algorithms. Apache Hadoop is used for data management, and TensorFlow for machine learning. Based on the extracted patterns, patient matching is performed, and the optimal treatment is proposed. Drug repositioning is also performed to explore new indications from the compound library.

[0815] The device is equipped with an emotion engine that evaluates the user's emotional state based on their facial expressions and voice data. Based on this evaluation, the server adjusts how information is displayed, presenting the information the user needs in an easy-to-understand manner. This reduces user stress caused by information overload and improves work efficiency.

[0816] For example, if a caregiver feels fatigued during nighttime rounds, the emotional engine will detect it. Because the information is presented concisely and to the point, caregivers can provide care efficiently.

[0817] An example of a prompt from a generated AI model is, "Please design a smart app for caregivers that analyzes emotions, adjusts the interface accordingly, and allows them to easily check care plans during night shifts." By adjusting the interface in response to emotions in this way, user-centered healthcare delivery can be achieved.

[0818] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0819] Step 1:

[0820] The server collects biomedical data. It receives a wide variety of biomedical information from electronic medical record systems and research databases as input. To integrate this information, it uses Apache Hadoop to store the data and perform data cleansing while maintaining consistency. The output is an integrated and refined dataset.

[0821] Step 2:

[0822] The server applies machine learning algorithms to the integrated dataset. The input is the dataset prepared in Step 1. This allows for data analysis using TensorFlow, and biomedical patterns are extracted. The resulting output is patterns associated with specific diseases or patient conditions.

[0823] Step 3:

[0824] The server matches patients for clinical trials based on the extracted patterns. The input consists of the biomedical patterns extracted in step 2 and individual patient information. The server compares this information to identify and list suitable patients. The output is a list of patients suitable for clinical trials and treatment plans.

[0825] Step 4:

[0826] The device evaluates the emotional state of the user (healthcare worker or caregiver). Inputs include the user's facial expressions and voice data acquired through the camera and microphone. An emotion engine analyzes this data to determine the user's level of fatigue and stress. The output is the evaluation result regarding the user's emotional state.

[0827] Step 5:

[0828] The server adjusts the information presentation interface based on the emotional state assessment results. The inputs are the assessment results obtained in step 4 and the medical information requested by the user. The server adjusts the complexity and amount of information in the interface to present the information in the most easily understandable way for the user. This process results in an information presentation screen optimized for user accessibility.

[0829] Step 6:

[0830] Users access optimized information screens using their terminals and perform procedures necessary for treatment planning and patient care. Input consists of finely tuned information provided by the server. Based on this information, users efficiently develop and implement care plans. Output is the optimal treatment or care plan to be implemented.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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."

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] The following is further disclosed regarding the embodiments described above.

[0853] (Claim 1)

[0854] A data collection means for collecting biomedical data and integrating said data,

[0855] A data analysis means for extracting biomedical patterns by applying a machine learning algorithm to the integrated data,

[0856] A patient matching means for identifying patients to be targeted for clinical trials based on the extracted patterns,

[0857] A drug repositioning method that analyzes existing drug libraries and explores new applicability,

[0858] A clinical decision-making support tool that proposes the optimal treatment method based on individual patient information,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, further comprising means for identifying highly similar patient groups from past data to assist in planning clinical trials.

[0862] (Claim 3)

[0863] The system according to claim 1, further comprising means for automatically screening suitable compounds from a compound library and identifying candidate substances.

[0864] "Example 1"

[0865] (Claim 1)

[0866] Information gathering means for collecting and integrating life science information,

[0867] An information analysis means for extracting biomedical trends by applying machine learning techniques to the integrated information,

[0868] A subject selection means for identifying subjects to be included in the experiment based on the extracted trends,

[0869] Drug reuse methods that analyze existing drug populations and explore new applicability,

[0870] A medical decision-making support tool that proposes the optimal treatment method based on individual patient information,

[0871] An information analysis method that analyzes disease-related characteristics from collected information and discovers new therapeutic targets,

[0872] A correlation discovery method that aims to predict the relationship between compounds and diseases based on past and present information,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, further comprising means for identifying highly similar subject groups from past information and assisting in the planning of experiments.

[0876] (Claim 3)

[0877] The system according to claim 1, further comprising means for automatically selecting suitable substances from a group of pharmaceuticals and identifying candidate substances.

[0878] "Application Example 1"

[0879] (Claim 1)

[0880] Information gathering means for collecting and integrating biomedical information,

[0881] An information analysis means for extracting biomedical patterns by applying a machine learning algorithm to the integrated information,

[0882] Access management means to enhance the authentication process based on the extracted pattern,

[0883] A repositioning method that explores applicability from multiple information resources,

[0884] A decision-making support tool that proposes the optimal treatment method based on individual subject information,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, further comprising means for performing biometric authentication in real time information access.

[0888] (Claim 3)

[0889] The system according to claim 1, further comprising means for detecting abnormal access and issuing a warning when accessing information.

[0890] "Example 2 of combining an emotion engine"

[0891] (Claim 1)

[0892] Information acquisition means for acquiring biological information and integrating said information,

[0893] Information analysis means for extracting biological characteristics by applying a machine learning algorithm to the integrated information,

[0894] An individual matching means for identifying individuals to be the subject of treatment research based on the extracted characteristics,

[0895] A drug reuse method that analyzes existing drug databases and explores new applicability,

[0896] A treatment decision support tool that proposes the optimal treatment method based on individual patient information,

[0897] An emotional response means for detecting the user's emotional state and adjusting the user interface according to the detected state,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, further comprising means for identifying highly similar populations from past information in order to support the planning of therapeutic research.

[0901] (Claim 3)

[0902] The system according to claim 1, further comprising means for automatically screening suitable compounds from a compound database and identifying potentially applicable substances.

[0903] "Application example 2 when combining with an emotional engine"

[0904] (Claim 1)

[0905] A data collection means for collecting biomedical data and integrating said data,

[0906] A data analysis means for extracting biomedical patterns by applying a machine learning algorithm to the integrated data,

[0907] A patient matching means for identifying patients to be targeted for clinical trials based on the extracted patterns,

[0908] A drug repositioning method that analyzes existing drug libraries and explores new applicability,

[0909] A clinical decision-making support tool that proposes the optimal treatment method based on individual patient information,

[0910] A means comprising an emotion engine that optimizes information presentation by evaluating the user's emotional state and adjusting the interface,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, further comprising means for identifying highly similar patient groups from past data to assist in planning clinical trials.

[0914] (Claim 3)

[0915] The system according to claim 1, further comprising means for automatically screening suitable compounds from a compound library and identifying candidate substances. [Explanation of Symbols]

[0916] 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. Information gathering means for collecting and integrating biomedical information, An information analysis means for extracting biomedical patterns by applying a machine learning algorithm to the integrated information, Access management means to enhance the authentication process based on the extracted pattern, A repositioning method that explores applicability from multiple information resources, A decision-making support tool that proposes the optimal treatment method based on individual subject information, A system that includes this.

2. The system according to claim 1, further comprising means for performing biometric authentication in real time information access.

3. The system according to claim 1, further comprising means for detecting abnormal access and issuing a warning when accessing information.

Images