system

Abstract

We provide the system. [Solution] A means for collecting medical data and preprocessing that data, A means of receiving information from users in order to obtain individual health information, A means for analyzing the aforementioned medical data and the aforementioned individual health information and executing a generative model for generating optimal medical recommendations, Means for providing the generated medical proposal to the user, A means for collecting user feedback on the aforementioned medical proposal and utilizing it to improve the accuracy of the model, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is not possible to provide optimal medical and lifestyle suggestions for individual patients, and in many cases, uniform treatment according to general medical guidelines is carried out. As a result, the patient's constitution, past medical history, and allergy information cannot be fully considered, not only leaving a risk of medical accidents, but also missing opportunities for health management and lifestyle improvement suitable for individual patients. In addition, the lack of an automated proposal system for reducing the burden on medical staff has become a problem.

Means for Solving the Problems

[0005] This invention provides a system that generates optimal medical recommendations for individual patients by collecting and pre-processing medical data, receiving individual health information from users, and running a generative model to analyze each piece of data. Furthermore, it includes means for providing the generated medical recommendations to users and means for collecting user feedback to improve the accuracy of the model. This system makes it possible to extend the healthy lifespan of patients by considering past medical history and allergy information, preventing medical accidents, and proposing personalized lifestyle improvements.

[0006] "Medical data" refers to various types of information related to healthcare, such as clinical records, drug information, and medical papers.

[0007] A "generative model" refers to an algorithm or framework that uses machine learning or artificial intelligence to perform inferences and make suggestions based on input data.

[0008] "Individual health information" refers to personal data about individual patients, such as their medical history, allergy information, dietary habits, and exercise routines.

[0009] "Medical recommendations" refer to suggesting appropriate treatments and lifestyle improvements based on the user's health information and medical data.

[0010] "Feedback" refers to the process and information involved in users providing results and opinions based on actions taken according to suggestions. [Brief explanation of the drawing]

[0011] [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]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled 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.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] The system of this invention collects medical data, analyzes it based on individual health information, and provides optimal medical recommendations to individual patients. This system consists of the interaction of a server, terminals, and users.

[0033] Server Role

[0034] The server first collects diverse medical data from external sources, including clinical records, clinical data, drug information, and medical papers. It then cleanses and formats the collected data, using it as a foundation for the generative model to learn. The server stores individual health information received from users via their devices in a database and uses this information to perform analysis using the generative model. This analysis generates personalized medical recommendations for each user.

[0035] Terminal role

[0036] The terminal functions as an interface with the user, providing a means for the user to input health information (medical history, allergy information, lifestyle data) and send it to the server. It also displays medical suggestions sent from the server, collects user feedback on those suggestions, and sends it back to the server.

[0037] User roles

[0038] Users participate in the system by entering their health information into a terminal. They receive medical suggestions generated from the server on their terminal, review the content, and implement the suggested treatments and lifestyle improvements. By providing feedback on the results and opinions on the terminal, they contribute to improving the accuracy of the system.

[0039] Specific example

[0040] For example, suppose a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as his past medical history, current diet, and exercise level into his device. The server receives this information and analyzes it using a generative model, comparing it with past hypertension treatment data from a medical database. The server then creates optimal suggestions through the generative model and provides them to the user via the device. These suggestions may include a low-sodium diet plan or a cardiovascular-friendly exercise program. The user then implements the suggestions and provides feedback on the results, allowing the server to continuously improve the model and enable more accurate suggestions in the future.

[0041] Thus, the system of the present invention can prevent medical accidents while meeting individual medical needs, making a significant contribution to patient health management and support for healthcare professionals.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server periodically collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public repositories, and stores it in a database. The collected data is preprocessed and formatted to be suitable for AI models.

[0045] Step 2:

[0046] The server trains a generative model using pre-processed medical data. This model recognizes patterns in the data and builds a foundation for providing personalized medical care and lifestyle suggestions for each patient.

[0047] Step 3:

[0048] Users enter their health information using a device. This information includes medical history, allergy information, daily diet, and exercise habits.

[0049] Step 4:

[0050] The device sends the user's health information to the server. The server records this information in a database and prepares it for analysis.

[0051] Step 5:

[0052] The server analyzes individual user health information and accumulated medical data using a generative model. The model considers various factors to generate optimal suggestions for the user, such as the most suitable treatment or lifestyle improvement measures.

[0053] Step 6:

[0054] The server sends the generated medical suggestions to the terminal, making them available for the user to view. These suggestions include treatment options based on the user's health condition and specific lifestyle improvements.

[0055] Step 7:

[0056] The user reviews the suggestions and takes action based on them. They input the results of their actions and feedback on the suggestions into their device and send it to the server.

[0057] Step 8:

[0058] The server analyzes user feedback and uses it to improve the generative model. Through this iterative process, the model's accuracy improves, aiming to further enhance the quality of future medical recommendations.

[0059] (Example 1)

[0060] 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."

[0061] In modern medicine, providing optimal medical recommendations based on individual health information is crucial, but the diversity and complexity of data present challenges. Accurate collection and analysis of medical data and individual health information are necessary to improve the quality of medical recommendations provided to users, thereby preventing medical errors and enabling more personalized health management.

[0062] 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.

[0063] In this invention, the server includes means for collecting, cleansing, and formatting medical data from external sources; means for receiving individual health information from users and storing it in a database; and means for analyzing the medical data and the individual health information using a generated AI model. This makes it possible to generate and provide medical recommendations optimized for each individual user.

[0064] "Medical data" refers to a variety of information related to healthcare, such as clinical records, clinical information, drug information, and medical papers.

[0065] "Cleaning" refers to the process of detecting and correcting duplicates, missing data, and inconsistencies in the data, and arranging it into a consistent format.

[0066] "Individual health information" refers to information about each user's health status and lifestyle, such as their medical history, allergy information, and lifestyle data.

[0067] A "generative AI model" refers to an artificial intelligence model that generates optimal medical recommendations based on medical data and individual health information.

[0068] "Analyzing" refers to the process of using collected data to identify patterns and relationships in the information, and then drawing conclusions or making recommendations.

[0069] The system of this invention realizes optimal medical recommendations based on individual health information through the interaction of a server, terminal, and user. The server first collects medical data such as clinical records, clinical information, drug information, and medical papers from external sources. The collected data is then cleansed and formatted by removing duplicates and correcting missing values. This formatted data is used as a foundation for analysis by a generative AI model.

[0070] Users input their individual health information, such as medical history, allergy information, and lifestyle data, via a terminal. The terminal transmits this information to the server in an appropriate format. The server uses a generative AI model to analyze the collected medical data and the individual health information from the user, and generates optimized medical recommendations. The generated medical recommendations are provided to the user via the terminal. The user implements the suggested treatments and lifestyle improvements, and provides feedback on the results and opinions to the terminal. This feedback information is used by the server to continuously refine the generative AI model.

[0071] As a concrete example, consider a case where a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as diet and exercise levels into a terminal, and the server uses this information to analyze it with high blood pressure treatment data and a generated AI model. The generated suggestions include low-sodium diet menus and exercise programs. After implementing the suggestions, the user provides feedback on the results obtained, and the system uses this feedback to further improve its accuracy.

[0072] Examples of prompt statements include the following:

[0073] "Please propose an optimal meal plan based on the patient's past hypertension treatment data."

[0074] "Please create an appropriate exercise program, taking into account the health checkup results of a man in his 40s."

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects medical data from external sources, including clinical records, clinical information, drug information, and medical papers. The input is raw medical data provided in various formats, and the output is cleansed data converted to a unified format. Specific operations include removing redundant data, converting data formats, and imputing missing values.

[0078] Step 2:

[0079] Users input their health information into the terminal. This includes medical history, allergy information, and lifestyle data. The input consists of various forms of individual health information provided by the user, and the output is data converted into a format that is easy for the server to process. Specifically, information is entered through interfaces such as input forms and item selection using checkboxes.

[0080] Step 3:

[0081] The terminal transmits individual health information entered by the user to the server. The input is the user's health information, and the output is data that has been properly formatted and sent to the server. Specifically, the data is sent to the server using a secure communication protocol over the internet.

[0082] Step 4:

[0083] The server performs analysis using a generative AI model based on cleansed medical data and individual health information. The input is formatted medical data and individual health information, and the output is an optimal medical recommendation for the user. Specifically, prompt statements are input to the generative AI model, giving instructions such as "Develop the optimal treatment plan for this patient."

[0084] Step 5:

[0085] The server sends the generated medical suggestions to the terminal. The input is the medical suggestions created by the generation AI model, and the output is the specific suggestion content displayed to the user. Specifically, the suggestion content is displayed on the terminal's screen after the data is sent.

[0086] Step 6:

[0087] The terminal displays medical suggestions to the user and collects user feedback. The input is the medical suggestions sent from the server, and the output is the feedback information received from the user. Specifically, after the user reviews the suggestions, a form is provided on the interface for them to enter feedback.

[0088] Step 7:

[0089] The server processes data to improve the generated AI model based on user feedback. The input is user feedback, and the output is an improvement in the accuracy of future suggestions. Specifically, it readjusts model parameters and updates the training dataset through feedback analysis.

[0090] (Application Example 1)

[0091] 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."

[0092] In modern healthcare systems, there is a need to provide appropriate medical recommendations to individual patients. However, there is a challenge in the lack of the technological infrastructure to properly analyze diverse medical data and provide optimal recommendations in real time based on individual health information. Furthermore, there is a lack of responsive product recommendations tailored to the health status of individual users. Therefore, it is necessary to provide advanced systems that prevent medical errors and support lifestyle improvements and optimal product selection.

[0093] 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.

[0094] In this invention, the server includes a device for collecting and preprocessing medical information, a device for receiving information from a user to acquire individual health data, a device for analyzing the medical information and the individual health data and executing a generative model for generating optimal medical suggestions, and a device for providing real-time optimized product recommendations based on the user's on-site health history via a dynamic user interface. This makes it possible to provide individual users with real-time suggestions for medical care and products that are optimal for their individual health conditions, while contributing to the prevention of medical accidents.

[0095] "Medical information" refers to information that includes various medical data (for example, treatment records, clinical data, and drug information), and is used for patient health management and optimal medical recommendations.

[0096] "Individual health data" refers to health information related to each individual user (e.g., medical history, allergy information, lifestyle data), and is the basis for providing personalized medical recommendations.

[0097] A "generative model" is a learning model used to analyze medical information and individual health data to generate optimal medical recommendations, and it has the function of performing data analysis using AI technology.

[0098] A "dynamic user interface" is an interface that provides and adjusts information in real time according to the user's input and environment, enabling product recommendations based on the user's on-site health history.

[0099] "Real-time optimized product recommendations" means that the most suitable products are immediately selected and suggested based on the user's health condition and medical information, accurately introducing the health improvement products and services that the user currently needs.

[0100] The system for implementing this invention consists of a server, a terminal, and user interaction. The server collects a wide variety of medical information from external sources and cleanses and preprocesses it. Specifically, the server uses a Python data analysis library (e.g., pandas) to format the data and prepare it as a learning base. Next, a generative AI model is used to analyze this medical information and individual health data transmitted from the terminal to generate optimal medical recommendations in real time. Machine learning frameworks such as PyTorch and TENSORFLOW® are utilized in this analysis process.

[0101] The device functions as a user interface and collects health data from the user. This data includes medical history, allergy information, and lifestyle data. When this data is sent from the device to the server, the server generates appropriate medical recommendations based on it. The device also receives the generated medical recommendations and product recommendations and displays them to the user. A concrete example is the use of smart glasses to provide health-based product recommendations to customers. For instance, in a health food store, if a user uploads their health data through smart glasses, the most suitable supplements will be suggested accordingly.

[0102] Users participate in this system by entering their health information into their device and receiving medical suggestions from the server. They also provide feedback on their experiences trying out the suggestions, which is then sent to the server. This feedback is used to further improve the accuracy of the generated AI model and provide more appropriate medical suggestions.

[0103] In this way, this invention aims not only to prevent medical accidents but also to provide a highly useful medical suggestion system for users through personalized lifestyle improvement measures and optimized product recommendations.

[0104] Examples of prompt messages are as follows:

[0105] "Based on the health information you enter, we will generate a list of recommended vitamins and supplements. Please select the three that are best for you from this list."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The user enters their health information (medical history, allergy information, lifestyle data, etc.) into the terminal. The terminal then receives the entered data and prepares it for formatting. The input data is checked for field inconsistencies and missing values, and completed as needed.

[0109] Step 2:

[0110] The terminal sends the formatted health information to the server. The server receives this input data and stores it in a database along with the collected medical information. The database creates or updates data records for each user and prepares them for the next analysis step.

[0111] Step 3:

[0112] The server runs a generative AI model using stored health and medical information. The model analyzes the input data and generates optimal medical recommendations for the user. For example, analysis is performed using PyTorch or TensorFlow, health statistics are calculated, and medical recommendations are output based on patterns learned from similar past cases.

[0113] Step 4:

[0114] The generated medical recommendations are sent to the device. The device receives this data and displays the medical recommendations in a user-friendly format. For example, the information may be displayed visualized on smart glasses, allowing the user to review the recommendations.

[0115] Step 5:

[0116] Users actually try the suggested medical treatment or product and input the results as feedback into the device. The device receives this feedback data and sends it back to the server. This information is used as training data to improve the accuracy of the generative AI model.

[0117] Step 6:

[0118] The server receives user feedback and stores it in a database. Furthermore, it updates the generated AI model based on the feedback and retrains the model. During this process, the model's parameters are optimized so that more accurate medical recommendations can be made in the future.

[0119] 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.

[0120] This invention incorporates an emotion engine that recognizes user emotions into a system that collects medical data, links it with individual health information, and provides optimal medical recommendations. The system operates through interaction between a server, a terminal, and the user.

[0121] Server Role

[0122] The server first collects and formats medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and publicly available databases. The generated model learns from the collected data and combines it with the user's individual health information to generate optimal medical recommendations. At this time, it also has a function to prevent medical errors by considering the user's past medical history and allergy information.

[0123] Functions of the Emotion Engine

[0124] The emotion engine recognizes and analyzes health information entered by the user via the device, the feedback received, and the emotional state at the time of receiving suggestions. Based on this information, the server adjusts suggestions according to the user's emotions. For example, if the user is feeling anxious, the emotion engine can soften the communication style and adjust the wording of the suggestions. In this way, the aim is to provide individualized support based on the user's emotional state, making medical suggestions more readily accepted.

[0125] Terminal role

[0126] The terminal functions as a user interface, providing a means for inputting health information and displaying medical suggestions from the server and adjustment suggestions from the emotion engine. User feedback is also collected by the terminal and sent to the server.

[0127] User roles

[0128] Users input their health information through their device and receive medical suggestions from the server. They then take action according to the suggestions and provide feedback on their reactions and opinions through their device.

[0129] Specific example

[0130] For example, if a user has stress-related health problems, they will input information about their past health condition and current symptoms into the terminal. The server, via an emotion engine, analyzes the user's emotional state at the time of input and generates appropriate medical suggestions for stress reduction. These suggestions may include relaxation techniques and psychological support suggestions. If the user's emotions are unstable, the emotion engine adjusts its communication methods to use gentle language and encouraging messages, providing a safe and secure environment.

[0131] This system makes it possible to go beyond conventional, uniform medical recommendations and provide more appropriate and acceptable medical services while taking into account the user's psychological state.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public databases, and stores it in a database. It then preprocesses the collected data to make it easier to analyze.

[0135] Step 2:

[0136] The server trains a generative model using pre-processed medical data. The model learns patterns from the data and builds a foundation for providing medical recommendations based on the user's individual health information.

[0137] Step 3:

[0138] Users input their health information through their device. This information includes medical history, allergy information, and daily eating and exercise habits. Furthermore, their emotional state at the time of input is analyzed by an emotion engine.

[0139] Step 4:

[0140] The terminal sends the entered health information and the user's emotional state to the server. The server records this information in a database and prepares it for analysis.

[0141] Step 5:

[0142] The server uses a generative model to generate optimal medical recommendations based on the user's health information and medical data. The emotion engine takes the user's emotional state into account and adjusts the recommendations accordingly.

[0143] Step 6:

[0144] The server sends the generated medical suggestions to the terminal. The suggestions reflect the results of the emotion engine, and communication methods and expressions are adopted that are tailored to the user's psychological state.

[0145] Step 7:

[0146] Users review the medical suggestions provided on the device and implement the suggested treatments and lifestyle modifications. They then input the results of their implementation and feedback on the suggestions on the device.

[0147] Step 8:

[0148] The device sends user feedback to the server. The server analyzes this feedback and uses it as data to improve the accuracy of the model. Through continuous learning, the overall quality of the system's suggestions improves.

[0149] (Example 2)

[0150] 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".

[0151] In recent years, the rapid increase and complexity of medical data has created a demand for providing optimal medical recommendations to individual patients. However, conventional systems have struggled to effectively integrate collected medical information with individual health information and to provide flexible recommendations that reflect the user's emotional state. As a result, there are situations where the acceptability and effectiveness of medical recommendations cannot be sufficiently enhanced.

[0152] 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.

[0153] In this invention, the server includes means for collecting medical information and preprocessing it; means for receiving information from the user to obtain individual health information; means for executing a generative model to analyze the medical information and individual health information and generate optimal medical recommendations; means for using an emotion analysis engine to analyze the user's emotional state and adjust the content and expression of the recommendations; means for providing medical recommendations to the user; and means for collecting the user's response to the medical recommendations and utilizing it to improve the accuracy of the model. This makes it possible to provide more acceptable medical recommendations that take into account individual health information and the user's emotional state.

[0154] "Medical information" refers to all information related to healthcare, including clinical records, clinical data, drug information, and medical papers.

[0155] "Individualized health information" refers to health-related information specific to each user, such as their health status, past medical history, and allergy information, which is obtained for each individual user.

[0156] A "generative model" refers to a machine learning algorithm that generates optimal medical recommendations based on collected medical information and individual health information.

[0157] A "sentiment analysis engine" refers to a system that includes natural language processing technology used to analyze information entered by a user and recognize their emotional state.

[0158] "Means" refers to a method or technical device for achieving a specific function.

[0159] "Medical proposals" refer to suggestions made to users regarding treatment methods, care plans, and lifestyle improvement measures.

[0160] The embodiment of this invention is a medical recommendation system based on server, terminal, and user interaction. The following describes the specific hardware and software used, as well as their operation.

[0161] Server role:

[0162] The server collects medical information from medical institutions and public databases. This information includes clinical records, clinical data, drug information, and medical papers. The server retrieves data using APIs and scraping techniques. The retrieved data is managed in a database management system such as MySQL (registered trademark) and subjected to processing such as data cleaning and formatting.

[0163] The formatted data is used to train generative AI models using machine learning platforms such as TensorFlow and PyTorch. The models analyze the combination of medical data and individual health information to generate optimal medical recommendations. Once predictions and recommendations with inventory applied are generated, an emotion analysis engine is used to analyze the user's emotional state and adjust the content and presentation of the recommendations to ensure that each user receives appropriate suggestions.

[0164] Terminal role:

[0165] The terminal functions as a user interface, providing a means of receiving health information from the user. Specifically, digital devices such as smartphones and personal computers are used. The data entered by the user is immediately sent to the server and used for analysis.

[0166] The terminal also displays medical suggestions provided by the server to the user. These individually tailored suggestions include reassuring language, allowing the user to make decisions based on them.

[0167] User roles:

[0168] The user's role in this system is to input their health information into the terminal. They are also expected to take recommended actions based on the presented medical suggestions. The user's emotional state is important for improving the acceptability of the suggestions and is analyzed through an emotion analysis engine. For example, by entering a prompt such as "I want to know how to relax," situation-appropriate advice will be provided.

[0169] This system can generate medical recommendations in real time, taking into account the user's specific needs and emotional state, and deliver them directly to the user. This enables the provision of personalized medical services.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The server collects medical information. It receives raw data from medical institutions and public databases as input. Specifically, it performs data retrieval via APIs and web scraping. A database management system stores this information as structured data. The output is a structured medical information dataset.

[0173] Step 2:

[0174] The server formats and preprocesses the collected medical information. It takes the structured data obtained in step 1 as input. Specific operations include data cleaning, normalization, and handling of missing values. It generates formatted data suitable for analysis as output.

[0175] Step 3:

[0176] The server receives individual user health information from the terminal. It receives health data provided by the user via the terminal as input. Specifically, it uses input interfaces such as web forms and mobile apps to send data to the server in real time. The output is the individually collected user health information.

[0177] Step 4:

[0178] The server generates optimal medical recommendations using a generative AI model. It takes formatted medical information and individual health information as input. Specific operations include running machine learning models using tools such as TensorFlow and PyTorch. The output is a customized medical recommendation tailored to the user's condition.

[0179] Step 5:

[0180] The emotion engine analyzes the user's emotions. It uses the user's health information and received feedback data as input. Specifically, it performs emotion analysis using natural language processing techniques. The output is the analysis result regarding the user's emotional state.

[0181] Step 6:

[0182] The server adjusts the suggested content based on the sentiment analysis results and sends it to the terminal. The input includes AI-generated medical suggestions and sentiment analysis results. Specific actions include adjusting the suggested wording and changing it to gentler language. The output is an adjusted medical suggestion that is gentle and effectively communicated to the user.

[0183] Step 7:

[0184] The terminal displays tailored medical suggestions to the user. It receives medical suggestions sent from the server as input. Its specific operation is to display the suggestions through a user-friendly interface. The output is the feedback data responded to by the user.

[0185] Step 8:

[0186] The user takes action based on the medical suggestions they receive. The input is the medical suggestions displayed on the device. Specific actions include implementing the suggested health management plan. The output is feedback on their health status and opinions based on their actions.

[0187] Step 9:

[0188] The server receives user feedback and uses it to improve the model's accuracy. It collects feedback sent from the terminal as input. Specific actions include retraining the model and analyzing data to improve the accuracy of suggestions. The output is a highly accurate trained model that enables improved medical recommendations.

[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] Conventional health management systems often make uniform suggestions without considering the emotional state of individual users, leading to difficulties in users accepting these suggestions. Furthermore, because they cannot adjust responses based on emotional states, they fail to adequately alleviate users' anxiety and stress, thus hindering the maximization of the effectiveness of medical care and health management.

[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 a device for collecting medical-related data and preprocessing the information, a device for receiving information from a user to obtain individual health information, and a device for analyzing the medical-related data and the individual health information and executing a generation algorithm to generate optimal health management suggestions. This makes it possible to recognize and adjust suggestions based on the user's emotions, and to provide suggestions that are easily accepted by the user.

[0194] "Medical-related data" refers to information such as clinical records, drug information, and medical papers obtained from medical institutions and publicly available databases.

[0195] "Individual health information" refers to health information specific to an individual, such as past health status, medical history, allergy information, and lifestyle habits, obtained from the user.

[0196] A "generative algorithm" is a computational procedure or method for generating optimal health management suggestions by analyzing medical-related data and individual health information.

[0197] An "device" refers to a mechanical or electronic instrument or system used to perform a specific function.

[0198] "Emotionally conscious and adjusted suggestions" are suggestions that analyze the user's emotional state, optimize the content and expression of the suggestions based on the results, and make them more acceptable to the user.

[0199] One embodiment of this invention is the construction of a health management system equipped with emotion recognition capabilities. The server first collects medical-related data from an external source, preprocesses that data, and stores it. Specifically, it employs a database management system to handle medical records, clinical information, and information on pharmaceuticals. Furthermore, it integrates and analyzes the collected medical data based on the individual health information of the received user. During this analysis process, a generation algorithm is used to generate optimal health management suggestions.

[0200] The server also uses emotion recognition APIs running on cloud platforms such as Azure® to analyze the user's emotional state. This allows it to understand in real time how the user receives health management suggestions and adjust the suggestions based on that feedback.

[0201] The terminal functions as a user interface. Users can input health information using a smartphone or head-mounted display and receive suggestions from the server. The terminal also plays a role in enhancing acceptance by displaying suggestions tailored to the user's emotional state.

[0202] For example, when a user receives stress management suggestions through a head-mounted display, the system evaluates the user's stress level based on their heart rate and facial expression data, and uses a generative AI model to present suggestions in a gentle tone, such as, "This supplement will help you relax."

[0203] An example of a prompt for a generative AI model would be, "Generate a communication message appropriate for when the user is feeling anxious." This allows for a more intuitive and meaningful health management experience for the user.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects medical-related data from external databases. This collection process includes clinical records, clinical data, and drug information. Input is raw data from various databases, and output is integrated medical data that has been formatted for preprocessing. This data is stored in the database management system.

[0207] Step 2:

[0208] Users input individual health information using a terminal. This data includes past health status, medical history, and allergy information. The terminal receives this data and sends it to the server. The input is health information provided by the user themselves, while the output is detailed health information used for analysis on the server side.

[0209] Step 3:

[0210] The server integrates medical data and individual health information and performs analysis using a generation algorithm. The input is the integrated data and detailed health information recorded in the previous step, and the output is optimal health management suggestions provided to the user. Specifically, the server constructs suggestions from this information using a generation AI model.

[0211] Step 4:

[0212] The server uses a cloud-based emotion recognition API to evaluate the user's emotional state. This process uses the user's biometric information (such as heart rate and facial expression data) as input. The output is an index indicating the user's emotional state. This prepares the server to adjust the content and expression of suggestions according to the user's emotions.

[0213] Step 5:

[0214] The device displays health management suggestions tailored to the user's emotions. The input is the tailored suggestions sent from the server, and the output is the information displayed on the user's screen. Specifically, the suggestions are delivered in a tone that aligns with the user's emotions.

[0215] Step 6:

[0216] After accepting health management suggestions, users input their feedback into a terminal. The input consists of the user's reactions and evaluations, while the output is data sent to the server for readjustment. This feedback is used to improve the accuracy of the generated AI model and serves as foundational data for making even more appropriate suggestions.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] The system of this invention collects medical data, analyzes it based on individual health information, and provides optimal medical recommendations to individual patients. This system consists of the interaction of a server, terminals, and users.

[0234] Server Role

[0235] The server first collects diverse medical data from external sources, including clinical records, clinical data, drug information, and medical papers. It then cleanses and formats the collected data, using it as a foundation for the generative model to learn. The server stores individual health information received from users via their devices in a database and uses this information to perform analysis using the generative model. This analysis generates personalized medical recommendations for each user.

[0236] Terminal role

[0237] The terminal functions as an interface with the user, providing a means for the user to input health information (medical history, allergy information, lifestyle data) and send it to the server. It also displays medical suggestions sent from the server, collects user feedback on those suggestions, and sends it back to the server.

[0238] User roles

[0239] Users participate in the system by entering their health information into a terminal. They receive medical suggestions generated from the server on their terminal, review the content, and implement the suggested treatments and lifestyle improvements. By providing feedback on the results and opinions on the terminal, they contribute to improving the accuracy of the system.

[0240] Specific example

[0241] For example, suppose a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as his past medical history, current diet, and exercise level into his device. The server receives this information and analyzes it using a generative model, comparing it with past hypertension treatment data from a medical database. The server then creates optimal suggestions through the generative model and provides them to the user via the device. These suggestions may include a low-sodium diet plan or a cardiovascular-friendly exercise program. The user then implements the suggestions and provides feedback on the results, allowing the server to continuously improve the model and enable more accurate suggestions in the future.

[0242] Thus, the system of the present invention can prevent medical accidents while meeting individual medical needs, making a significant contribution to patient health management and support for healthcare professionals.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server periodically collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public repositories, and stores it in a database. The collected data is preprocessed and formatted to be suitable for AI models.

[0246] Step 2:

[0247] The server trains a generative model using pre-processed medical data. This model recognizes patterns in the data and builds a foundation for providing personalized medical care and lifestyle suggestions for each patient.

[0248] Step 3:

[0249] Users enter their health information using a device. This information includes medical history, allergy information, daily diet, and exercise habits.

[0250] Step 4:

[0251] The device sends the user's health information to the server. The server records this information in a database and prepares it for analysis.

[0252] Step 5:

[0253] The server analyzes individual user health information and accumulated medical data using a generative model. The model considers various factors to generate optimal suggestions for the user, such as the most suitable treatment or lifestyle improvement measures.

[0254] Step 6:

[0255] The server sends the generated medical suggestions to the terminal, making them available for the user to view. These suggestions include treatment options based on the user's health condition and specific lifestyle improvements.

[0256] Step 7:

[0257] The user reviews the suggestions and takes action based on them. They input the results of their actions and feedback on the suggestions into their device and send it to the server.

[0258] Step 8:

[0259] The server analyzes user feedback and uses it to improve the generative model. Through this iterative process, the model's accuracy improves, aiming to further enhance the quality of future medical recommendations.

[0260] (Example 1)

[0261] 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."

[0262] In modern medicine, providing optimal medical recommendations based on individual health information is crucial, but the diversity and complexity of data present challenges. Accurate collection and analysis of medical data and individual health information are necessary to improve the quality of medical recommendations provided to users, thereby preventing medical errors and enabling more personalized health management.

[0263] 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.

[0264] In this invention, the server includes means for collecting, cleansing, and formatting medical data from external sources; means for receiving individual health information from users and storing it in a database; and means for analyzing the medical data and the individual health information using a generated AI model. This makes it possible to generate and provide medical recommendations optimized for each individual user.

[0265] "Medical data" refers to a variety of information related to healthcare, such as clinical records, clinical information, drug information, and medical papers.

[0266] "Cleaning" refers to the process of detecting and correcting duplicates, missing data, and inconsistencies in the data, and arranging it into a consistent format.

[0267] "Individual health information" refers to information about each user's health status and lifestyle, such as their medical history, allergy information, and lifestyle data.

[0268] A "generative AI model" refers to an artificial intelligence model that generates optimal medical recommendations based on medical data and individual health information.

[0269] "Analyzing" refers to the process of using collected data to identify patterns and relationships in the information, and then drawing conclusions or making recommendations.

[0270] The system of this invention realizes optimal medical recommendations based on individual health information through the interaction of a server, terminal, and user. The server first collects medical data such as clinical records, clinical information, drug information, and medical papers from external sources. The collected data is then cleansed and formatted by removing duplicates and correcting missing values. This formatted data is used as a foundation for analysis by a generative AI model.

[0271] Users input their individual health information, such as medical history, allergy information, and lifestyle data, via a terminal. The terminal transmits this information to the server in an appropriate format. The server uses a generative AI model to analyze the collected medical data and the individual health information from the user, and generates optimized medical recommendations. The generated medical recommendations are provided to the user via the terminal. The user implements the suggested treatments and lifestyle improvements, and provides feedback on the results and opinions to the terminal. This feedback information is used by the server to continuously refine the generative AI model.

[0272] As a concrete example, consider a case where a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as diet and exercise levels into a terminal, and the server uses this information to analyze it with high blood pressure treatment data and a generated AI model. The generated suggestions include low-sodium diet menus and exercise programs. After implementing the suggestions, the user provides feedback on the results obtained, and the system uses this feedback to further improve its accuracy.

[0273] Examples of prompt statements include the following:

[0274] "Please propose an optimal meal plan based on the patient's past hypertension treatment data."

[0275] "Please create an appropriate exercise program, taking into account the health checkup results of a man in his 40s."

[0276] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0277] Step 1:

[0278] The server collects medical data from external information sources. This includes medical records, clinical information, pharmaceutical information, medical papers, etc. The input is raw medical data provided in various formats, and the output is cleansed data converted into a unified format. Specific operations include deleting redundant data, converting data formats, and filling in missing values.

[0279] Step 2:

[0280] The user inputs their own health information into the terminal. This includes medical histories, allergy information, lifestyle data, etc. The input is individual health information in various formats provided by the user, and the output is data converted into a format that is easy for the server to process. Specifically, the information is input through interfaces such as using input forms and selecting items using checkboxes.

[0281] Step 3:

[0282] The terminal sends the individual health information input by the user to the server. The input is the user's health information, and the output is data properly formatted and sent to the server. As a specific operation, the data is sent to the server using a secure communication protocol via the Internet.

[0283] Step 4:

[0284] The server executes analysis using an AI model generated based on the cleansed medical data and individual health information. The input is the formatted medical data and individual health information, and the output is the optimal medical proposal for the user. As a specific operation, a prompt sentence is input into the AI model, giving an instruction such as "Devise the optimal treatment plan for this patient."

[0285] Step 5:

[0286] The server sends the generated medical proposal to the terminal. The input is the medical proposal created by the generation AI model, and the output is the specific proposal content displayed to the user. Specifically, after the data is sent, the proposal content is displayed on the terminal's display.

[0287] Step 6:

[0288] The terminal displays the medical proposal to the user and collects the user's feedback. The input is the medical proposal sent from the server, and the output is the feedback information obtained from the user. As a specific operation, after the user checks the proposal, a form for inputting feedback is provided on the interface.

[0289] Step 7:

[0290] The server performs data processing to improve the generation AI model based on the user's feedback. The input is the user's feedback, and the output is the improvement in the accuracy of the proposals provided in subsequent times. As a specific operation, the model parameters are readjusted through feedback analysis, and the training dataset is updated.

[0291] (Application Example 1)

[0292] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0293] In modern medical systems, it is required to provide appropriate medical proposals for individual patients. However, there is a problem that the technical foundation for appropriately analyzing various medical data and providing optimal proposals in real time based on individual health information is lacking. Also, regarding product recommendations for customers, there is a lack of immediate proposals according to the health status of individual users. Therefore, it is necessary to provide an advanced system that prevents medical accidents and supports the improvement of lifestyle and optimal product selection.

[0294] 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.

[0295] In this invention, the server includes a device for collecting and preprocessing medical information, a device for receiving information from a user to acquire individual health data, a device for analyzing the medical information and the individual health data and executing a generative model for generating optimal medical suggestions, and a device for providing real-time optimized product recommendations based on the user's on-site health history via a dynamic user interface. This makes it possible to provide individual users with real-time suggestions for medical care and products that are optimal for their individual health conditions, while contributing to the prevention of medical accidents.

[0296] "Medical information" refers to information that includes various medical data (for example, treatment records, clinical data, and drug information), and is used for patient health management and optimal medical recommendations.

[0297] "Individual health data" refers to health information related to each individual user (e.g., medical history, allergy information, lifestyle data), and is the basis for providing personalized medical recommendations.

[0298] A "generative model" is a learning model used to analyze medical information and individual health data to generate optimal medical recommendations, and it has the function of performing data analysis using AI technology.

[0299] A "dynamic user interface" is an interface that provides and adjusts information in real time according to the user's input and environment, enabling product recommendations based on the user's on-site health history.

[0300] "Real-time optimized product recommendations" means that the most suitable products are immediately selected and suggested based on the user's health condition and medical information, accurately introducing the health improvement products and services that the user currently needs.

[0301] The system for implementing this invention consists of a server, a terminal, and user interaction. The server collects a wide variety of medical information from external sources and cleanses and preprocesses it. Specifically, the server uses a Python data analysis library (e.g., pandas) to format the data and prepare it as a basis for learning. Next, a generative AI model is used to analyze this medical information and individual health data transmitted from the terminal to generate optimal medical recommendations in real time. Machine learning frameworks such as PyTorch and TensorFlow are utilized in this analysis process.

[0302] The device functions as a user interface and collects health data from the user. This data includes medical history, allergy information, and lifestyle data. When this data is sent from the device to the server, the server generates appropriate medical recommendations based on it. The device also receives the generated medical recommendations and product recommendations and displays them to the user. A concrete example is the use of smart glasses to provide health-based product recommendations to customers. For instance, in a health food store, if a user uploads their health data through smart glasses, the most suitable supplements will be suggested accordingly.

[0303] Users participate in this system by entering their health information into their device and receiving medical suggestions from the server. They also provide feedback on their experiences trying out the suggestions, which is then sent to the server. This feedback is used to further improve the accuracy of the generated AI model and provide more appropriate medical suggestions.

[0304] In this way, this invention aims not only to prevent medical accidents but also to provide a highly useful medical suggestion system for users through personalized lifestyle improvement measures and optimized product recommendations.

[0305] Examples of prompt messages are as follows:

[0306] "Based on the health information entered by the user, generate a recommended list of vitamins and supplements, and please select the top three optimal ones from it."

[0307] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The user inputs their health information (medical history, allergy information, lifestyle data, etc.) into the terminal. As a result, the terminal receives the input data and prepares it for data shaping. The input data is checked for field inconsistencies and missing values, and is supplemented if necessary.

[0310] Step 2:

[0311] The terminal transmits the shaped health information to the server. The server receives this input data and stores it in the database together with the collected medical information. The database creates or updates a data record for each user and prepares for the next analysis step.

[0312] Step 3:

[0313] The server executes the generated AI model using the stored health information and medical information. It analyzes the input data, and the model generates an optimal medical proposal for the user. For example, the analysis is performed using PyTorch or TensorFlow, calculates statistical values of the health information, and outputs a medical proposal based on patterns learned from past similar cases.

[0314] Step 4:

[0315] The generated medical proposal is transmitted to the terminal. The terminal receives this data and displays the medical proposal in a user-friendly format. Here, for example, information visualized on smart glasses is displayed, and the user can check the content of the proposal.

[0316] Step 5:

[0317] Users actually try the suggested medical treatment or product and input the results as feedback into the device. The device receives this feedback data and sends it back to the server. This information is used as training data to improve the accuracy of the generative AI model.

[0318] Step 6:

[0319] The server receives user feedback and stores it in a database. Furthermore, it updates the generated AI model based on the feedback and retrains the model. During this process, the model's parameters are optimized so that more accurate medical recommendations can be made in the future.

[0320] 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.

[0321] This invention incorporates an emotion engine that recognizes user emotions into a system that collects medical data, links it with individual health information, and provides optimal medical recommendations. The system operates through interaction between a server, a terminal, and the user.

[0322] Server Role

[0323] The server first collects and formats medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and publicly available databases. The generated model learns from the collected data and combines it with the user's individual health information to generate optimal medical recommendations. At this time, it also has a function to prevent medical errors by considering the user's past medical history and allergy information.

[0324] Functions of the Emotion Engine

[0325] The emotion engine recognizes and analyzes health information entered by the user via the device, the feedback received, and the emotional state at the time of receiving suggestions. Based on this information, the server adjusts suggestions according to the user's emotions. For example, if the user is feeling anxious, the emotion engine can soften the communication style and adjust the wording of the suggestions. In this way, the aim is to provide individualized support based on the user's emotional state, making medical suggestions more readily accepted.

[0326] Terminal role

[0327] The terminal functions as a user interface, providing a means for inputting health information and displaying medical suggestions from the server and adjustment suggestions from the emotion engine. User feedback is also collected by the terminal and sent to the server.

[0328] User roles

[0329] Users input their health information through their device and receive medical suggestions from the server. They then take action according to the suggestions and provide feedback on their reactions and opinions through their device.

[0330] Specific example

[0331] For example, if a user has stress-related health problems, they will input information about their past health condition and current symptoms into the terminal. The server, via an emotion engine, analyzes the user's emotional state at the time of input and generates appropriate medical suggestions for stress reduction. These suggestions may include relaxation techniques and psychological support suggestions. If the user's emotions are unstable, the emotion engine adjusts its communication methods to use gentle language and encouraging messages, providing a safe and secure environment.

[0332] This system makes it possible to go beyond conventional, uniform medical recommendations and provide more appropriate and acceptable medical services while taking into account the user's psychological state.

[0333] The following describes the processing flow.

[0334] Step 1:

[0335] The server collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public databases, and stores it in a database. It then preprocesses the collected data to make it easier to analyze.

[0336] Step 2:

[0337] The server trains a generative model using pre-processed medical data. The model learns patterns from the data and builds a foundation for providing medical recommendations based on the user's individual health information.

[0338] Step 3:

[0339] Users input their health information through their device. This information includes medical history, allergy information, and daily eating and exercise habits. Furthermore, their emotional state at the time of input is analyzed by an emotion engine.

[0340] Step 4:

[0341] The terminal sends the entered health information and the user's emotional state to the server. The server records this information in a database and prepares it for analysis.

[0342] Step 5:

[0343] The server uses a generative model to generate optimal medical recommendations based on the user's health information and medical data. The emotion engine takes the user's emotional state into account and adjusts the recommendations accordingly.

[0344] Step 6:

[0345] The server sends the generated medical suggestions to the terminal. The suggestions reflect the results of the emotion engine, and communication methods and expressions are adopted that are tailored to the user's psychological state.

[0346] Step 7:

[0347] Users review the medical suggestions provided on the device and implement the suggested treatments and lifestyle modifications. They then input the results of their implementation and feedback on the suggestions on the device.

[0348] Step 8:

[0349] The device sends user feedback to the server. The server analyzes this feedback and uses it as data to improve the accuracy of the model. Through continuous learning, the overall quality of the system's suggestions improves.

[0350] (Example 2)

[0351] 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".

[0352] In recent years, the rapid increase and complexity of medical data has created a demand for providing optimal medical recommendations to individual patients. However, conventional systems have struggled to effectively integrate collected medical information with individual health information and to provide flexible recommendations that reflect the user's emotional state. As a result, there are situations where the acceptability and effectiveness of medical recommendations cannot be sufficiently enhanced.

[0353] 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.

[0354] In this invention, the server includes means for collecting medical information and preprocessing it; means for receiving information from the user to obtain individual health information; means for executing a generative model to analyze the medical information and individual health information and generate optimal medical recommendations; means for using an emotion analysis engine to analyze the user's emotional state and adjust the content and expression of the recommendations; means for providing medical recommendations to the user; and means for collecting the user's response to the medical recommendations and utilizing it to improve the accuracy of the model. This makes it possible to provide more acceptable medical recommendations that take into account individual health information and the user's emotional state.

[0355] "Medical information" refers to all information related to healthcare, including clinical records, clinical data, drug information, and medical papers.

[0356] "Individualized health information" refers to health-related information specific to each user, such as their health status, past medical history, and allergy information, which is obtained for each individual user.

[0357] A "generative model" refers to a machine learning algorithm that generates optimal medical recommendations based on collected medical information and individual health information.

[0358] A "sentiment analysis engine" refers to a system that includes natural language processing technology used to analyze information entered by a user and recognize their emotional state.

[0359] "Means" refers to a method or technical device for achieving a specific function.

[0360] "Medical proposals" refer to suggestions made to users regarding treatment methods, care plans, and lifestyle improvement measures.

[0361] The embodiment of this invention is a medical recommendation system based on server, terminal, and user interaction. The following describes the specific hardware and software used, as well as their operation.

[0362] Server role:

[0363] The server collects medical information from medical institutions and public databases. This information includes clinical records, clinical data, drug information, and medical papers. The server retrieves data using APIs and scraping techniques. The retrieved data is managed in a database management system such as MySQL, where it undergoes processing such as data cleaning and formatting.

[0364] The formatted data is used to train generative AI models using machine learning platforms such as TensorFlow and PyTorch. The models analyze the combination of medical data and individual health information to generate optimal medical recommendations. Once predictions and recommendations with inventory applied are generated, an emotion analysis engine is used to analyze the user's emotional state and adjust the content and presentation of the recommendations to ensure that each user receives appropriate suggestions.

[0365] Terminal role:

[0366] The terminal functions as a user interface, providing a means of receiving health information from the user. Specifically, digital devices such as smartphones and personal computers are used. The data entered by the user is immediately sent to the server and used for analysis.

[0367] The terminal also displays medical suggestions provided by the server to the user. These individually tailored suggestions include reassuring language, allowing the user to make decisions based on them.

[0368] User roles:

[0369] The user's role in this system is to input their health information into the terminal. They are also expected to take recommended actions based on the presented medical suggestions. The user's emotional state is important for improving the acceptability of the suggestions and is analyzed through an emotion analysis engine. For example, by entering a prompt such as "I want to know how to relax," situation-appropriate advice will be provided.

[0370] This system can generate medical recommendations in real time, taking into account the user's specific needs and emotional state, and deliver them directly to the user. This enables the provision of personalized medical services.

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1:

[0373] The server collects medical information. It receives raw data from medical institutions and public databases as input. Specifically, it performs data retrieval via APIs and web scraping. A database management system stores this information as structured data. The output is a structured medical information dataset.

[0374] Step 2:

[0375] The server formats and preprocesses the collected medical information. It takes the structured data obtained in step 1 as input. Specific operations include data cleaning, normalization, and handling of missing values. It generates formatted data suitable for analysis as output.

[0376] Step 3:

[0377] The server receives individual user health information from the terminal. It receives health data provided by the user via the terminal as input. Specifically, it uses input interfaces such as web forms and mobile apps to send data to the server in real time. The output is the individually collected user health information.

[0378] Step 4:

[0379] The server generates optimal medical recommendations using a generative AI model. It takes formatted medical information and individual health information as input. Specific operations include running machine learning models using tools such as TensorFlow and PyTorch. The output is a customized medical recommendation tailored to the user's condition.

[0380] Step 5:

[0381] The emotion engine analyzes the user's emotions. It uses the user's health information and received feedback data as input. Specifically, it performs emotion analysis using natural language processing techniques. The output is the analysis result regarding the user's emotional state.

[0382] Step 6:

[0383] The server adjusts the suggested content based on the sentiment analysis results and sends it to the terminal. The input includes AI-generated medical suggestions and sentiment analysis results. Specific actions include adjusting the suggested wording and changing it to gentler language. The output is an adjusted medical suggestion that is gentle and effectively communicated to the user.

[0384] Step 7:

[0385] The terminal displays tailored medical suggestions to the user. It receives medical suggestions sent from the server as input. Its specific operation is to display the suggestions through a user-friendly interface. The output is the feedback data responded to by the user.

[0386] Step 8:

[0387] The user takes action based on the medical suggestions they receive. The input is the medical suggestions displayed on the device. Specific actions include implementing the suggested health management plan. The output is feedback on their health status and opinions based on their actions.

[0388] Step 9:

[0389] The server receives user feedback and uses it to improve the model's accuracy. It collects feedback sent from the terminal as input. Specific actions include retraining the model and analyzing data to improve the accuracy of suggestions. The output is a highly accurate trained model that enables improved medical recommendations.

[0390] (Application Example 2)

[0391] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0392] Conventional health management systems often make uniform suggestions without considering the emotional state of individual users, leading to difficulties in users accepting these suggestions. Furthermore, because they cannot adjust responses based on emotional states, they fail to adequately alleviate users' anxiety and stress, thus hindering the maximization of the effectiveness of medical care and health management.

[0393] 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.

[0394] In this invention, the server includes a device for collecting medical-related data and preprocessing the information, a device for receiving information from a user to obtain individual health information, and a device for analyzing the medical-related data and the individual health information and executing a generation algorithm to generate optimal health management suggestions. This makes it possible to recognize and adjust suggestions based on the user's emotions, and to provide suggestions that are easily accepted by the user.

[0395] "Medical-related data" refers to information such as clinical records, drug information, and medical papers obtained from medical institutions and publicly available databases.

[0396] "Individual health information" refers to health information specific to an individual, such as past health status, medical history, allergy information, and lifestyle habits, obtained from the user.

[0397] A "generative algorithm" is a computational procedure or method for generating optimal health management suggestions by analyzing medical-related data and individual health information.

[0398] An "device" refers to a mechanical or electronic instrument or system used to perform a specific function.

[0399] "Emotionally conscious and adjusted suggestions" are suggestions that analyze the user's emotional state, optimize the content and expression of the suggestions based on the results, and make them more acceptable to the user.

[0400] One embodiment of this invention is the construction of a health management system equipped with emotion recognition capabilities. The server first collects medical-related data from an external source, preprocesses that data, and stores it. Specifically, it employs a database management system to handle medical records, clinical information, and information on pharmaceuticals. Furthermore, it integrates and analyzes the collected medical data based on the individual health information of the received user. During this analysis process, a generation algorithm is used to generate optimal health management suggestions.

[0401] The server also uses emotion recognition APIs running on cloud platforms such as Azure to analyze the user's emotional state. This allows it to understand in real time how users perceive health management suggestions and adjust the suggestions based on that feedback.

[0402] The terminal functions as a user interface. Users can input health information using a smartphone or head-mounted display and receive suggestions from the server. The terminal also plays a role in enhancing acceptance by displaying suggestions tailored to the user's emotional state.

[0403] For example, when a user receives stress management suggestions through a head-mounted display, the system evaluates the user's stress level based on their heart rate and facial expression data, and uses a generative AI model to present suggestions in a gentle tone, such as, "This supplement will help you relax."

[0404] An example of a prompt for a generative AI model would be, "Generate a communication message appropriate for when the user is feeling anxious." This allows for a more intuitive and meaningful health management experience for the user.

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The server collects medical-related data from external databases. This collection process includes clinical records, clinical data, and drug information. Input is raw data from various databases, and output is integrated medical data that has been formatted for preprocessing. This data is stored in the database management system.

[0408] Step 2:

[0409] Users input individual health information using a terminal. This data includes past health status, medical history, and allergy information. The terminal receives this data and sends it to the server. The input is health information provided by the user themselves, while the output is detailed health information used for analysis on the server side.

[0410] Step 3:

[0411] The server integrates medical data and individual health information and performs analysis using a generation algorithm. The input is the integrated data and detailed health information recorded in the previous step, and the output is optimal health management suggestions provided to the user. Specifically, the server constructs suggestions from this information using a generation AI model.

[0412] Step 4:

[0413] The server uses a cloud-based emotion recognition API to evaluate the user's emotional state. This process uses the user's biometric information (such as heart rate and facial expression data) as input. The output is an index indicating the user's emotional state. This prepares the server to adjust the content and expression of suggestions according to the user's emotions.

[0414] Step 5:

[0415] The device displays health management suggestions tailored to the user's emotions. The input is the tailored suggestions sent from the server, and the output is the information displayed on the user's screen. Specifically, the suggestions are delivered in a tone that aligns with the user's emotions.

[0416] Step 6:

[0417] After accepting health management suggestions, users input their feedback into a terminal. The input consists of the user's reactions and evaluations, while the output is data sent to the server for readjustment. This feedback is used to improve the accuracy of the generated AI model and serves as foundational data for making even more appropriate suggestions.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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".

[0434] The system of this invention collects medical data, analyzes it based on individual health information, and provides optimal medical recommendations to individual patients. This system consists of the interaction of a server, terminals, and users.

[0435] Server Role

[0436] The server first collects diverse medical data from external sources, including clinical records, clinical data, drug information, and medical papers. It then cleanses and formats the collected data, using it as a foundation for the generative model to learn. The server stores individual health information received from users via their devices in a database and uses this information to perform analysis using the generative model. This analysis generates personalized medical recommendations for each user.

[0437] Terminal role

[0438] The terminal functions as an interface with the user, providing a means for the user to input health information (medical history, allergy information, lifestyle data) and send it to the server. It also displays medical suggestions sent from the server, collects user feedback on those suggestions, and sends it back to the server.

[0439] User roles

[0440] Users participate in the system by entering their health information into a terminal. They receive medical suggestions generated from the server on their terminal, review the content, and implement the suggested treatments and lifestyle improvements. By providing feedback on the results and opinions on the terminal, they contribute to improving the accuracy of the system.

[0441] Specific example

[0442] For example, suppose a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as his past medical history, current diet, and exercise level into his device. The server receives this information and analyzes it using a generative model, comparing it with past hypertension treatment data from a medical database. The server then creates optimal suggestions through the generative model and provides them to the user via the device. These suggestions may include a low-sodium diet plan or a cardiovascular-friendly exercise program. The user then implements the suggestions and provides feedback on the results, allowing the server to continuously improve the model and enable more accurate suggestions in the future.

[0443] Thus, the system of the present invention can prevent medical accidents while meeting individual medical needs, making a significant contribution to patient health management and support for healthcare professionals.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The server periodically collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public repositories, and stores it in a database. The collected data is preprocessed and formatted to be suitable for AI models.

[0447] Step 2:

[0448] The server trains a generative model using pre-processed medical data. This model recognizes patterns in the data and builds a foundation for providing personalized medical care and lifestyle suggestions for each patient.

[0449] Step 3:

[0450] Users enter their health information using a device. This information includes medical history, allergy information, daily diet, and exercise habits.

[0451] Step 4:

[0452] The device sends the user's health information to the server. The server records this information in a database and prepares it for analysis.

[0453] Step 5:

[0454] The server analyzes individual user health information and accumulated medical data using a generative model. The model considers various factors to generate optimal suggestions for the user, such as the most suitable treatment or lifestyle improvement measures.

[0455] Step 6:

[0456] The server sends the generated medical suggestions to the terminal, making them available for the user to view. These suggestions include treatment options based on the user's health condition and specific lifestyle improvements.

[0457] Step 7:

[0458] The user reviews the suggestions and takes action based on them. They input the results of their actions and feedback on the suggestions into their device and send it to the server.

[0459] Step 8:

[0460] The server analyzes user feedback and uses it to improve the generative model. Through this iterative process, the model's accuracy improves, aiming to further enhance the quality of future medical recommendations.

[0461] (Example 1)

[0462] 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."

[0463] In modern medicine, providing optimal medical recommendations based on individual health information is crucial, but the diversity and complexity of data present challenges. Accurate collection and analysis of medical data and individual health information are necessary to improve the quality of medical recommendations provided to users, thereby preventing medical errors and enabling more personalized health management.

[0464] 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.

[0465] In this invention, the server includes means for collecting, cleansing, and formatting medical data from external sources; means for receiving individual health information from users and storing it in a database; and means for analyzing the medical data and the individual health information using a generated AI model. This makes it possible to generate and provide medical recommendations optimized for each individual user.

[0466] "Medical data" refers to a variety of information related to healthcare, such as clinical records, clinical information, drug information, and medical papers.

[0467] "Cleaning" refers to the process of detecting and correcting duplicates, missing data, and inconsistencies in the data, and arranging it into a consistent format.

[0468] "Individual health information" refers to information about each user's health status and lifestyle, such as their medical history, allergy information, and lifestyle data.

[0469] A "generative AI model" refers to an artificial intelligence model that generates optimal medical recommendations based on medical data and individual health information.

[0470] "Analyzing" refers to the process of using collected data to identify patterns and relationships in the information, and then drawing conclusions or making recommendations.

[0471] The system of this invention realizes optimal medical recommendations based on individual health information through the interaction of a server, terminal, and user. The server first collects medical data such as clinical records, clinical information, drug information, and medical papers from external sources. The collected data is then cleansed and formatted by removing duplicates and correcting missing values. This formatted data is used as a foundation for analysis by a generative AI model.

[0472] Users input their individual health information, such as medical history, allergy information, and lifestyle data, via a terminal. The terminal transmits this information to the server in an appropriate format. The server uses a generative AI model to analyze the collected medical data and the individual health information from the user, and generates optimized medical recommendations. The generated medical recommendations are provided to the user via the terminal. The user implements the suggested treatments and lifestyle improvements, and provides feedback on the results and opinions to the terminal. This feedback information is used by the server to continuously refine the generative AI model.

[0473] As a concrete example, consider a case where a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as diet and exercise levels into a terminal, and the server uses this information to analyze it with high blood pressure treatment data and a generated AI model. The generated suggestions include low-sodium diet menus and exercise programs. After implementing the suggestions, the user provides feedback on the results obtained, and the system uses this feedback to further improve its accuracy.

[0474] Examples of prompt statements include the following:

[0475] "Please propose an optimal meal plan based on the patient's past hypertension treatment data."

[0476] "Please create an appropriate exercise program, taking into account the health checkup results of a man in his 40s."

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The server collects medical data from external sources, including clinical records, clinical information, drug information, and medical papers. The input is raw medical data provided in various formats, and the output is cleansed data converted to a unified format. Specific operations include removing redundant data, converting data formats, and imputing missing values.

[0480] Step 2:

[0481] Users input their health information into the terminal. This includes medical history, allergy information, and lifestyle data. The input consists of various forms of individual health information provided by the user, and the output is data converted into a format that is easy for the server to process. Specifically, information is entered through interfaces such as input forms and item selection using checkboxes.

[0482] Step 3:

[0483] The terminal transmits individual health information entered by the user to the server. The input is the user's health information, and the output is data that has been properly formatted and sent to the server. Specifically, the data is sent to the server using a secure communication protocol over the internet.

[0484] Step 4:

[0485] The server performs analysis using a generative AI model based on cleansed medical data and individual health information. The input is formatted medical data and individual health information, and the output is an optimal medical recommendation for the user. Specifically, prompt statements are input to the generative AI model, giving instructions such as "Develop the optimal treatment plan for this patient."

[0486] Step 5:

[0487] The server sends the generated medical suggestions to the terminal. The input is the medical suggestions created by the generation AI model, and the output is the specific suggestion content displayed to the user. Specifically, the suggestion content is displayed on the terminal's screen after the data is sent.

[0488] Step 6:

[0489] The terminal displays medical suggestions to the user and collects user feedback. The input is the medical suggestions sent from the server, and the output is the feedback information received from the user. Specifically, after the user reviews the suggestions, a form is provided on the interface for them to enter feedback.

[0490] Step 7:

[0491] The server processes data to improve the generated AI model based on user feedback. The input is user feedback, and the output is an improvement in the accuracy of future suggestions. Specifically, it readjusts model parameters and updates the training dataset through feedback analysis.

[0492] (Application Example 1)

[0493] 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."

[0494] In modern healthcare systems, there is a need to provide appropriate medical recommendations to individual patients. However, there is a challenge in the lack of the technological infrastructure to properly analyze diverse medical data and provide optimal recommendations in real time based on individual health information. Furthermore, there is a lack of responsive product recommendations tailored to the health status of individual users. Therefore, it is necessary to provide advanced systems that prevent medical errors and support lifestyle improvements and optimal product selection.

[0495] 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.

[0496] In this invention, the server includes a device for collecting and preprocessing medical information, a device for receiving information from a user to acquire individual health data, a device for analyzing the medical information and the individual health data and executing a generative model for generating optimal medical suggestions, and a device for providing real-time optimized product recommendations based on the user's on-site health history via a dynamic user interface. This makes it possible to provide individual users with real-time suggestions for medical care and products that are optimal for their individual health conditions, while contributing to the prevention of medical accidents.

[0497] "Medical information" refers to information that includes various medical data (for example, treatment records, clinical data, and drug information), and is used for patient health management and optimal medical recommendations.

[0498] "Individual health data" refers to health information related to each individual user (e.g., medical history, allergy information, lifestyle data), and is the basis for providing personalized medical recommendations.

[0499] A "generative model" is a learning model used to analyze medical information and individual health data to generate optimal medical recommendations, and it has the function of performing data analysis using AI technology.

[0500] A "dynamic user interface" is an interface that provides and adjusts information in real time according to the user's input and environment, enabling product recommendations based on the user's on-site health history.

[0501] "Real-time optimized product recommendations" means that the most suitable products are immediately selected and suggested based on the user's health condition and medical information, accurately introducing the health improvement products and services that the user currently needs.

[0502] The system for implementing this invention consists of a server, a terminal, and user interaction. The server collects a wide variety of medical information from external sources and cleanses and preprocesses it. Specifically, the server uses a Python data analysis library (e.g., pandas) to format the data and prepare it as a basis for learning. Next, a generative AI model is used to analyze this medical information and individual health data transmitted from the terminal to generate optimal medical recommendations in real time. Machine learning frameworks such as PyTorch and TensorFlow are utilized in this analysis process.

[0503] The device functions as a user interface and collects health data from the user. This data includes medical history, allergy information, and lifestyle data. When this data is sent from the device to the server, the server generates appropriate medical recommendations based on it. The device also receives the generated medical recommendations and product recommendations and displays them to the user. A concrete example is the use of smart glasses to provide health-based product recommendations to customers. For instance, in a health food store, if a user uploads their health data through smart glasses, the most suitable supplements will be suggested accordingly.

[0504] Users participate in this system by entering their health information into their device and receiving medical suggestions from the server. They also provide feedback on their experiences trying out the suggestions, which is then sent to the server. This feedback is used to further improve the accuracy of the generated AI model and provide more appropriate medical suggestions.

[0505] In this way, this invention aims not only to prevent medical accidents but also to provide a highly useful medical suggestion system for users through personalized lifestyle improvement measures and optimized product recommendations.

[0506] Examples of prompt messages are as follows:

[0507] "Based on the health information you enter, we will generate a list of recommended vitamins and supplements. Please select the three that are best for you from this list."

[0508] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0509] Step 1:

[0510] The user enters their health information (medical history, allergy information, lifestyle data, etc.) into the terminal. The terminal then receives the entered data and prepares it for formatting. The input data is checked for field inconsistencies and missing values, and completed as needed.

[0511] Step 2:

[0512] The terminal sends the formatted health information to the server. The server receives this input data and stores it in a database along with the collected medical information. The database creates or updates data records for each user and prepares them for the next analysis step.

[0513] Step 3:

[0514] The server runs a generative AI model using stored health and medical information. The model analyzes the input data and generates optimal medical recommendations for the user. For example, analysis is performed using PyTorch or TensorFlow, health statistics are calculated, and medical recommendations are output based on patterns learned from similar past cases.

[0515] Step 4:

[0516] The generated medical recommendations are sent to the device. The device receives this data and displays the medical recommendations in a user-friendly format. For example, the information may be displayed visualized on smart glasses, allowing the user to review the recommendations.

[0517] Step 5:

[0518] Users actually try the suggested medical treatment or product and input the results as feedback into the device. The device receives this feedback data and sends it back to the server. This information is used as training data to improve the accuracy of the generative AI model.

[0519] Step 6:

[0520] The server receives user feedback and stores it in a database. Furthermore, it updates the generated AI model based on the feedback and retrains the model. During this process, the model's parameters are optimized so that more accurate medical recommendations can be made in the future.

[0521] 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.

[0522] This invention incorporates an emotion engine that recognizes user emotions into a system that collects medical data, links it with individual health information, and provides optimal medical recommendations. The system operates through interaction between a server, a terminal, and the user.

[0523] Server Role

[0524] The server first collects and formats medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and publicly available databases. The generated model learns from the collected data and combines it with the user's individual health information to generate optimal medical recommendations. At this time, it also has a function to prevent medical errors by considering the user's past medical history and allergy information.

[0525] Functions of the Emotion Engine

[0526] The emotion engine recognizes and analyzes health information entered by the user via the device, the feedback received, and the emotional state at the time of receiving suggestions. Based on this information, the server adjusts suggestions according to the user's emotions. For example, if the user is feeling anxious, the emotion engine can soften the communication style and adjust the wording of the suggestions. In this way, the aim is to provide individualized support based on the user's emotional state, making medical suggestions more readily accepted.

[0527] Terminal role

[0528] The terminal functions as a user interface, providing a means for inputting health information and displaying medical suggestions from the server and adjustment suggestions from the emotion engine. User feedback is also collected by the terminal and sent to the server.

[0529] User roles

[0530] Users input their health information through their device and receive medical suggestions from the server. They then take action according to the suggestions and provide feedback on their reactions and opinions through their device.

[0531] Specific example

[0532] For example, if a user has stress-related health problems, they will input information about their past health condition and current symptoms into the terminal. The server, via an emotion engine, analyzes the user's emotional state at the time of input and generates appropriate medical suggestions for stress reduction. These suggestions may include relaxation techniques and psychological support suggestions. If the user's emotions are unstable, the emotion engine adjusts its communication methods to use gentle language and encouraging messages, providing a safe and secure environment.

[0533] This system makes it possible to go beyond conventional, uniform medical recommendations and provide more appropriate and acceptable medical services while taking into account the user's psychological state.

[0534] The following describes the processing flow.

[0535] Step 1:

[0536] The server collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public databases, and stores it in a database. It then preprocesses the collected data to make it easier to analyze.

[0537] Step 2:

[0538] The server trains a generative model using pre-processed medical data. The model learns patterns from the data and builds a foundation for providing medical recommendations based on the user's individual health information.

[0539] Step 3:

[0540] Users input their health information through their device. This information includes medical history, allergy information, and daily eating and exercise habits. Furthermore, their emotional state at the time of input is analyzed by an emotion engine.

[0541] Step 4:

[0542] The terminal sends the entered health information and the user's emotional state to the server. The server records this information in a database and prepares it for analysis.

[0543] Step 5:

[0544] The server uses a generative model to generate optimal medical recommendations based on the user's health information and medical data. The emotion engine takes the user's emotional state into account and adjusts the recommendations accordingly.

[0545] Step 6:

[0546] The server sends the generated medical suggestions to the terminal. The suggestions reflect the results of the emotion engine, and communication methods and expressions are adopted that are tailored to the user's psychological state.

[0547] Step 7:

[0548] Users review the medical suggestions provided on the device and implement the suggested treatments and lifestyle modifications. They then input the results of their implementation and feedback on the suggestions on the device.

[0549] Step 8:

[0550] The device sends user feedback to the server. The server analyzes this feedback and uses it as data to improve the accuracy of the model. Through continuous learning, the overall quality of the system's suggestions improves.

[0551] (Example 2)

[0552] 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."

[0553] In recent years, the rapid increase and complexity of medical data has created a demand for providing optimal medical recommendations to individual patients. However, conventional systems have struggled to effectively integrate collected medical information with individual health information and to provide flexible recommendations that reflect the user's emotional state. As a result, there are situations where the acceptability and effectiveness of medical recommendations cannot be sufficiently enhanced.

[0554] 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.

[0555] In this invention, the server includes means for collecting medical information and preprocessing it; means for receiving information from the user to obtain individual health information; means for executing a generative model to analyze the medical information and individual health information and generate optimal medical recommendations; means for using an emotion analysis engine to analyze the user's emotional state and adjust the content and expression of the recommendations; means for providing medical recommendations to the user; and means for collecting the user's response to the medical recommendations and utilizing it to improve the accuracy of the model. This makes it possible to provide more acceptable medical recommendations that take into account individual health information and the user's emotional state.

[0556] "Medical information" refers to all information related to healthcare, including clinical records, clinical data, drug information, and medical papers.

[0557] "Individualized health information" refers to health-related information specific to each user, such as their health status, past medical history, and allergy information, which is obtained for each individual user.

[0558] A "generative model" refers to a machine learning algorithm that generates optimal medical recommendations based on collected medical information and individual health information.

[0559] A "sentiment analysis engine" refers to a system that includes natural language processing technology used to analyze information entered by a user and recognize their emotional state.

[0560] "Means" refers to a method or technical device for achieving a specific function.

[0561] "Medical proposals" refer to suggestions made to users regarding treatment methods, care plans, and lifestyle improvement measures.

[0562] The embodiment of this invention is a medical recommendation system based on server, terminal, and user interaction. The following describes the specific hardware and software used, as well as their operation.

[0563] Server role:

[0564] The server collects medical information from medical institutions and public databases. This information includes clinical records, clinical data, drug information, and medical papers. The server retrieves data using APIs and scraping techniques. The retrieved data is managed in a database management system such as MySQL, where it undergoes processing such as data cleaning and formatting.

[0565] The formatted data is used to train generative AI models using machine learning platforms such as TensorFlow and PyTorch. The models analyze the combination of medical data and individual health information to generate optimal medical recommendations. Once predictions and recommendations with inventory applied are generated, an emotion analysis engine is used to analyze the user's emotional state and adjust the content and presentation of the recommendations to ensure that each user receives appropriate suggestions.

[0566] Terminal role:

[0567] The terminal functions as a user interface, providing a means of receiving health information from the user. Specifically, digital devices such as smartphones and personal computers are used. The data entered by the user is immediately sent to the server and used for analysis.

[0568] The terminal also displays medical suggestions provided by the server to the user. These individually tailored suggestions include reassuring language, allowing the user to make decisions based on them.

[0569] User roles:

[0570] The user's role in this system is to input their health information into the terminal. They are also expected to take recommended actions based on the presented medical suggestions. The user's emotional state is important for improving the acceptability of the suggestions and is analyzed through an emotion analysis engine. For example, by entering a prompt such as "I want to know how to relax," situation-appropriate advice will be provided.

[0571] This system can generate medical recommendations in real time, taking into account the user's specific needs and emotional state, and deliver them directly to the user. This enables the provision of personalized medical services.

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] The server collects medical information. It receives raw data from medical institutions and public databases as input. Specifically, it performs data retrieval via APIs and web scraping. A database management system stores this information as structured data. The output is a structured medical information dataset.

[0575] Step 2:

[0576] The server formats and preprocesses the collected medical information. It takes the structured data obtained in step 1 as input. Specific operations include data cleaning, normalization, and handling of missing values. It generates formatted data suitable for analysis as output.

[0577] Step 3:

[0578] The server receives individual user health information from the terminal. It receives health data provided by the user via the terminal as input. Specifically, it uses input interfaces such as web forms and mobile apps to send data to the server in real time. The output is the individually collected user health information.

[0579] Step 4:

[0580] The server generates optimal medical recommendations using a generative AI model. It takes formatted medical information and individual health information as input. Specific operations include running machine learning models using tools such as TensorFlow and PyTorch. The output is a customized medical recommendation tailored to the user's condition.

[0581] Step 5:

[0582] The emotion engine analyzes the user's emotions. It uses the user's health information and received feedback data as input. Specifically, it performs emotion analysis using natural language processing techniques. The output is the analysis result regarding the user's emotional state.

[0583] Step 6:

[0584] The server adjusts the suggested content based on the sentiment analysis results and sends it to the terminal. The input includes AI-generated medical suggestions and sentiment analysis results. Specific actions include adjusting the suggested wording and changing it to gentler language. The output is an adjusted medical suggestion that is gentle and effectively communicated to the user.

[0585] Step 7:

[0586] The terminal displays tailored medical suggestions to the user. It receives medical suggestions sent from the server as input. Its specific operation is to display the suggestions through a user-friendly interface. The output is the feedback data responded to by the user.

[0587] Step 8:

[0588] The user takes action based on the medical suggestions they receive. The input is the medical suggestions displayed on the device. Specific actions include implementing the suggested health management plan. The output is feedback on their health status and opinions based on their actions.

[0589] Step 9:

[0590] The server receives user feedback and uses it to improve the model's accuracy. It collects feedback sent from the terminal as input. Specific actions include retraining the model and analyzing data to improve the accuracy of suggestions. The output is a highly accurate trained model that enables improved medical recommendations.

[0591] (Application Example 2)

[0592] 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."

[0593] Conventional health management systems often make uniform suggestions without considering the emotional state of individual users, leading to difficulties in users accepting these suggestions. Furthermore, because they cannot adjust responses based on emotional states, they fail to adequately alleviate users' anxiety and stress, thus hindering the maximization of the effectiveness of medical care and health management.

[0594] 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.

[0595] In this invention, the server includes a device for collecting medical-related data and preprocessing the information, a device for receiving information from a user to obtain individual health information, and a device for analyzing the medical-related data and the individual health information and executing a generation algorithm to generate optimal health management suggestions. This makes it possible to recognize and adjust suggestions based on the user's emotions, and to provide suggestions that are easily accepted by the user.

[0596] "Medical-related data" refers to information such as clinical records, drug information, and medical papers obtained from medical institutions and publicly available databases.

[0597] "Individual health information" refers to health information specific to an individual, such as past health status, medical history, allergy information, and lifestyle habits, obtained from the user.

[0598] A "generative algorithm" is a computational procedure or method for generating optimal health management suggestions by analyzing medical-related data and individual health information.

[0599] An "device" refers to a mechanical or electronic instrument or system used to perform a specific function.

[0600] "Emotionally conscious and adjusted suggestions" are suggestions that analyze the user's emotional state, optimize the content and expression of the suggestions based on the results, and make them more acceptable to the user.

[0601] One embodiment of this invention is the construction of a health management system equipped with emotion recognition capabilities. The server first collects medical-related data from an external source, preprocesses that data, and stores it. Specifically, it employs a database management system to handle medical records, clinical information, and information on pharmaceuticals. Furthermore, it integrates and analyzes the collected medical data based on the individual health information of the received user. During this analysis process, a generation algorithm is used to generate optimal health management suggestions.

[0602] The server also uses emotion recognition APIs running on cloud platforms such as Azure to analyze the user's emotional state. This allows it to understand in real time how users perceive health management suggestions and adjust the suggestions based on that feedback.

[0603] The terminal functions as a user interface. Users can input health information using a smartphone or head-mounted display and receive suggestions from the server. The terminal also plays a role in enhancing acceptance by displaying suggestions tailored to the user's emotional state.

[0604] For example, when a user receives stress management suggestions through a head-mounted display, the system evaluates the user's stress level based on their heart rate and facial expression data, and uses a generative AI model to present suggestions in a gentle tone, such as, "This supplement will help you relax."

[0605] An example of a prompt for a generative AI model would be, "Generate a communication message appropriate for when the user is feeling anxious." This allows for a more intuitive and meaningful health management experience for the user.

[0606] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0607] Step 1:

[0608] The server collects medical-related data from external databases. This collection process includes clinical records, clinical data, and drug information. Input is raw data from various databases, and output is integrated medical data that has been formatted for preprocessing. This data is stored in the database management system.

[0609] Step 2:

[0610] Users input individual health information using a terminal. This data includes past health status, medical history, and allergy information. The terminal receives this data and sends it to the server. The input is health information provided by the user themselves, while the output is detailed health information used for analysis on the server side.

[0611] Step 3:

[0612] The server integrates medical data and individual health information and performs analysis using a generation algorithm. The input is the integrated data and detailed health information recorded in the previous step, and the output is optimal health management suggestions provided to the user. Specifically, the server constructs suggestions from this information using a generation AI model.

[0613] Step 4:

[0614] The server uses a cloud-based emotion recognition API to evaluate the user's emotional state. This process uses the user's biometric information (such as heart rate and facial expression data) as input. The output is an index indicating the user's emotional state. This prepares the server to adjust the content and expression of suggestions according to the user's emotions.

[0615] Step 5:

[0616] The device displays health management suggestions tailored to the user's emotions. The input is the tailored suggestions sent from the server, and the output is the information displayed on the user's screen. Specifically, the suggestions are delivered in a tone that aligns with the user's emotions.

[0617] Step 6:

[0618] After accepting health management suggestions, users input their feedback into a terminal. The input consists of the user's reactions and evaluations, while the output is data sent to the server for readjustment. This feedback is used to improve the accuracy of the generated AI model and serves as foundational data for making even more appropriate suggestions.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] [Fourth Embodiment]

[0623] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0624] 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.

[0625] 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).

[0626] 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.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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".

[0636] The system of this invention collects medical data, analyzes it based on individual health information, and provides optimal medical recommendations to individual patients. This system consists of the interaction of a server, terminals, and users.

[0637] Server Role

[0638] The server first collects diverse medical data from external sources, including clinical records, clinical data, drug information, and medical papers. It then cleanses and formats the collected data, using it as a foundation for the generative model to learn. The server stores individual health information received from users via their devices in a database and uses this information to perform analysis using the generative model. This analysis generates personalized medical recommendations for each user.

[0639] Terminal role

[0640] The terminal functions as an interface with the user, providing a means for the user to input health information (medical history, allergy information, lifestyle data) and send it to the server. It also displays medical suggestions sent from the server, collects user feedback on those suggestions, and sends it back to the server.

[0641] User roles

[0642] Users participate in the system by entering their health information into a terminal. They receive medical suggestions generated from the server on their terminal, review the content, and implement the suggested treatments and lifestyle improvements. By providing feedback on the results and opinions on the terminal, they contribute to improving the accuracy of the system.

[0643] Specific example

[0644] For example, suppose a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as his past medical history, current diet, and exercise level into his device. The server receives this information and analyzes it using a generative model, comparing it with past hypertension treatment data from a medical database. The server then creates optimal suggestions through the generative model and provides them to the user via the device. These suggestions may include a low-sodium diet plan or a cardiovascular-friendly exercise program. The user then implements the suggestions and provides feedback on the results, allowing the server to continuously improve the model and enable more accurate suggestions in the future.

[0645] Thus, the system of the present invention can prevent medical accidents while meeting individual medical needs, making a significant contribution to patient health management and support for healthcare professionals.

[0646] The following describes the processing flow.

[0647] Step 1:

[0648] The server periodically collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public repositories, and stores it in a database. The collected data is preprocessed and formatted to be suitable for AI models.

[0649] Step 2:

[0650] The server trains a generative model using pre-processed medical data. This model recognizes patterns in the data and builds a foundation for providing personalized medical care and lifestyle suggestions for each patient.

[0651] Step 3:

[0652] Users enter their health information using a device. This information includes medical history, allergy information, daily diet, and exercise habits.

[0653] Step 4:

[0654] The device sends the user's health information to the server. The server records this information in a database and prepares it for analysis.

[0655] Step 5:

[0656] The server analyzes individual user health information and accumulated medical data using a generative model. The model considers various factors to generate optimal suggestions for the user, such as the most suitable treatment or lifestyle improvement measures.

[0657] Step 6:

[0658] The server sends the generated medical suggestions to the terminal, making them available for the user to view. These suggestions include treatment options based on the user's health condition and specific lifestyle improvements.

[0659] Step 7:

[0660] The user reviews the suggestions and takes action based on them. They input the results of their actions and feedback on the suggestions into their device and send it to the server.

[0661] Step 8:

[0662] The server analyzes user feedback and uses it to improve the generative model. Through this iterative process, the model's accuracy improves, aiming to further enhance the quality of future medical recommendations.

[0663] (Example 1)

[0664] 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".

[0665] In modern medicine, providing optimal medical recommendations based on individual health information is crucial, but the diversity and complexity of data present challenges. Accurate collection and analysis of medical data and individual health information are necessary to improve the quality of medical recommendations provided to users, thereby preventing medical errors and enabling more personalized health management.

[0666] 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.

[0667] In this invention, the server includes means for collecting, cleansing, and formatting medical data from external sources; means for receiving individual health information from users and storing it in a database; and means for analyzing the medical data and the individual health information using a generated AI model. This makes it possible to generate and provide medical recommendations optimized for each individual user.

[0668] "Medical data" refers to a variety of information related to healthcare, such as clinical records, clinical information, drug information, and medical papers.

[0669] "Cleaning" refers to the process of detecting and correcting duplicates, missing data, and inconsistencies in the data, and arranging it into a consistent format.

[0670] "Individual health information" refers to information about each user's health status and lifestyle, such as their medical history, allergy information, and lifestyle data.

[0671] A "generative AI model" refers to an artificial intelligence model that generates optimal medical recommendations based on medical data and individual health information.

[0672] "Analyzing" refers to the process of using collected data to identify patterns and relationships in the information, and then drawing conclusions or making recommendations.

[0673] The system of this invention realizes optimal medical recommendations based on individual health information through the interaction of a server, terminal, and user. The server first collects medical data such as clinical records, clinical information, drug information, and medical papers from external sources. The collected data is then cleansed and formatted by removing duplicates and correcting missing values. This formatted data is used as a foundation for analysis by a generative AI model.

[0674] Users input their individual health information, such as medical history, allergy information, and lifestyle data, via a terminal. The terminal transmits this information to the server in an appropriate format. The server uses a generative AI model to analyze the collected medical data and the individual health information from the user, and generates optimized medical recommendations. The generated medical recommendations are provided to the user via the terminal. The user implements the suggested treatments and lifestyle improvements, and provides feedback on the results and opinions to the terminal. This feedback information is used by the server to continuously refine the generative AI model.

[0675] As a concrete example, consider a case where a male user in his 40s requests advice on managing high blood pressure based on his health checkup results. This user inputs health information such as diet and exercise levels into a terminal, and the server uses this information to analyze it with high blood pressure treatment data and a generated AI model. The generated suggestions include low-sodium diet menus and exercise programs. After implementing the suggestions, the user provides feedback on the results obtained, and the system uses this feedback to further improve its accuracy.

[0676] Examples of prompt statements include the following:

[0677] "Please propose an optimal meal plan based on the patient's past hypertension treatment data."

[0678] "Please create an appropriate exercise program, taking into account the health checkup results of a man in his 40s."

[0679] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0680] Step 1:

[0681] The server collects medical data from external sources, including clinical records, clinical information, drug information, and medical papers. The input is raw medical data provided in various formats, and the output is cleansed data converted to a unified format. Specific operations include removing redundant data, converting data formats, and imputing missing values.

[0682] Step 2:

[0683] Users input their health information into the terminal. This includes medical history, allergy information, and lifestyle data. The input consists of various forms of individual health information provided by the user, and the output is data converted into a format that is easy for the server to process. Specifically, information is entered through interfaces such as input forms and item selection using checkboxes.

[0684] Step 3:

[0685] The terminal transmits individual health information entered by the user to the server. The input is the user's health information, and the output is data that has been properly formatted and sent to the server. Specifically, the data is sent to the server using a secure communication protocol over the internet.

[0686] Step 4:

[0687] The server performs analysis using a generative AI model based on cleansed medical data and individual health information. The input is formatted medical data and individual health information, and the output is an optimal medical recommendation for the user. Specifically, prompt statements are input to the generative AI model, giving instructions such as "Develop the optimal treatment plan for this patient."

[0688] Step 5:

[0689] The server sends the generated medical suggestions to the terminal. The input is the medical suggestions created by the generation AI model, and the output is the specific suggestion content displayed to the user. Specifically, the suggestion content is displayed on the terminal's screen after the data is sent.

[0690] Step 6:

[0691] The terminal displays medical suggestions to the user and collects user feedback. The input is the medical suggestions sent from the server, and the output is the feedback information received from the user. Specifically, after the user reviews the suggestions, a form is provided on the interface for them to enter feedback.

[0692] Step 7:

[0693] The server processes data to improve the generated AI model based on user feedback. The input is user feedback, and the output is an improvement in the accuracy of future suggestions. Specifically, it readjusts model parameters and updates the training dataset through feedback analysis.

[0694] (Application Example 1)

[0695] 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".

[0696] In modern healthcare systems, there is a need to provide appropriate medical recommendations to individual patients. However, there is a challenge in the lack of the technological infrastructure to properly analyze diverse medical data and provide optimal recommendations in real time based on individual health information. Furthermore, there is a lack of responsive product recommendations tailored to the health status of individual users. Therefore, it is necessary to provide advanced systems that prevent medical errors and support lifestyle improvements and optimal product selection.

[0697] 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.

[0698] In this invention, the server includes a device for collecting and preprocessing medical information, a device for receiving information from a user to acquire individual health data, a device for analyzing the medical information and the individual health data and executing a generative model for generating optimal medical suggestions, and a device for providing real-time optimized product recommendations based on the user's on-site health history via a dynamic user interface. This makes it possible to provide individual users with real-time suggestions for medical care and products that are optimal for their individual health conditions, while contributing to the prevention of medical accidents.

[0699] "Medical information" refers to information that includes various medical data (for example, treatment records, clinical data, and drug information), and is used for patient health management and optimal medical recommendations.

[0700] "Individual health data" refers to health information related to each individual user (e.g., medical history, allergy information, lifestyle data), and is the basis for providing personalized medical recommendations.

[0701] A "generative model" is a learning model used to analyze medical information and individual health data to generate optimal medical recommendations, and it has the function of performing data analysis using AI technology.

[0702] A "dynamic user interface" is an interface that provides and adjusts information in real time according to the user's input and environment, enabling product recommendations based on the user's on-site health history.

[0703] "Real-time optimized product recommendations" means that the most suitable products are immediately selected and suggested based on the user's health condition and medical information, accurately introducing the health improvement products and services that the user currently needs.

[0704] The system for implementing this invention consists of a server, a terminal, and user interaction. The server collects a wide variety of medical information from external sources and cleanses and preprocesses it. Specifically, the server uses a Python data analysis library (e.g., pandas) to format the data and prepare it as a basis for learning. Next, a generative AI model is used to analyze this medical information and individual health data transmitted from the terminal to generate optimal medical recommendations in real time. Machine learning frameworks such as PyTorch and TensorFlow are utilized in this analysis process.

[0705] The device functions as a user interface and collects health data from the user. This data includes medical history, allergy information, and lifestyle data. When this data is sent from the device to the server, the server generates appropriate medical recommendations based on it. The device also receives the generated medical recommendations and product recommendations and displays them to the user. A concrete example is the use of smart glasses to provide health-based product recommendations to customers. For instance, in a health food store, if a user uploads their health data through smart glasses, the most suitable supplements will be suggested accordingly.

[0706] Users participate in this system by entering their health information into their device and receiving medical suggestions from the server. They also provide feedback on their experiences trying out the suggestions, which is then sent to the server. This feedback is used to further improve the accuracy of the generated AI model and provide more appropriate medical suggestions.

[0707] In this way, this invention aims not only to prevent medical accidents but also to provide a highly useful medical suggestion system for users through personalized lifestyle improvement measures and optimized product recommendations.

[0708] Examples of prompt messages are as follows:

[0709] "Based on the health information you enter, we will generate a list of recommended vitamins and supplements. Please select the three that are best for you from this list."

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The user enters their health information (medical history, allergy information, lifestyle data, etc.) into the terminal. The terminal then receives the entered data and prepares it for formatting. The input data is checked for field inconsistencies and missing values, and completed as needed.

[0713] Step 2:

[0714] The terminal sends the formatted health information to the server. The server receives this input data and stores it in a database along with the collected medical information. The database creates or updates data records for each user and prepares them for the next analysis step.

[0715] Step 3:

[0716] The server runs a generative AI model using stored health and medical information. The model analyzes the input data and generates optimal medical recommendations for the user. For example, analysis is performed using PyTorch or TensorFlow, health statistics are calculated, and medical recommendations are output based on patterns learned from similar past cases.

[0717] Step 4:

[0718] The generated medical recommendations are sent to the device. The device receives this data and displays the medical recommendations in a user-friendly format. For example, the information may be displayed visualized on smart glasses, allowing the user to review the recommendations.

[0719] Step 5:

[0720] Users actually try the suggested medical treatment or product and input the results as feedback into the device. The device receives this feedback data and sends it back to the server. This information is used as training data to improve the accuracy of the generative AI model.

[0721] Step 6:

[0722] The server receives user feedback and stores it in a database. Furthermore, it updates the generated AI model based on the feedback and retrains the model. During this process, the model's parameters are optimized so that more accurate medical recommendations can be made in the future.

[0723] 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.

[0724] This invention incorporates an emotion engine that recognizes user emotions into a system that collects medical data, links it with individual health information, and provides optimal medical recommendations. The system operates through interaction between a server, a terminal, and the user.

[0725] Server Role

[0726] The server first collects and formats medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and publicly available databases. The generated model learns from the collected data and combines it with the user's individual health information to generate optimal medical recommendations. At this time, it also has a function to prevent medical errors by considering the user's past medical history and allergy information.

[0727] Functions of the Emotion Engine

[0728] The emotion engine recognizes and analyzes health information entered by the user via the device, the feedback received, and the emotional state at the time of receiving suggestions. Based on this information, the server adjusts suggestions according to the user's emotions. For example, if the user is feeling anxious, the emotion engine can soften the communication style and adjust the wording of the suggestions. In this way, the aim is to provide individualized support based on the user's emotional state, making medical suggestions more readily accepted.

[0729] Terminal role

[0730] The terminal functions as a user interface, providing a means for inputting health information and displaying medical suggestions from the server and adjustment suggestions from the emotion engine. User feedback is also collected by the terminal and sent to the server.

[0731] User roles

[0732] Users input their health information through their device and receive medical suggestions from the server. They then take action according to the suggestions and provide feedback on their reactions and opinions through their device.

[0733] Specific example

[0734] For example, if a user has stress-related health problems, they will input information about their past health condition and current symptoms into the terminal. The server, via an emotion engine, analyzes the user's emotional state at the time of input and generates appropriate medical suggestions for stress reduction. These suggestions may include relaxation techniques and psychological support suggestions. If the user's emotions are unstable, the emotion engine adjusts its communication methods to use gentle language and encouraging messages, providing a safe and secure environment.

[0735] This system makes it possible to go beyond conventional, uniform medical recommendations and provide more appropriate and acceptable medical services while taking into account the user's psychological state.

[0736] The following describes the processing flow.

[0737] Step 1:

[0738] The server collects medical data such as treatment records, clinical data, drug information, and medical papers from medical institutions and public databases, and stores it in a database. It then preprocesses the collected data to make it easier to analyze.

[0739] Step 2:

[0740] The server trains a generative model using pre-processed medical data. The model learns patterns from the data and builds a foundation for providing medical recommendations based on the user's individual health information.

[0741] Step 3:

[0742] Users input their health information through their device. This information includes medical history, allergy information, and daily eating and exercise habits. Furthermore, their emotional state at the time of input is analyzed by an emotion engine.

[0743] Step 4:

[0744] The terminal sends the entered health information and the user's emotional state to the server. The server records this information in a database and prepares it for analysis.

[0745] Step 5:

[0746] The server uses a generative model to generate optimal medical recommendations based on the user's health information and medical data. The emotion engine takes the user's emotional state into account and adjusts the recommendations accordingly.

[0747] Step 6:

[0748] The server sends the generated medical suggestions to the terminal. The suggestions reflect the results of the emotion engine, and communication methods and expressions are adopted that are tailored to the user's psychological state.

[0749] Step 7:

[0750] Users review the medical suggestions provided on the device and implement the suggested treatments and lifestyle modifications. They then input the results of their implementation and feedback on the suggestions on the device.

[0751] Step 8:

[0752] The device sends user feedback to the server. The server analyzes this feedback and uses it as data to improve the accuracy of the model. Through continuous learning, the overall quality of the system's suggestions improves.

[0753] (Example 2)

[0754] 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".

[0755] In recent years, the rapid increase and complexity of medical data has created a demand for providing optimal medical recommendations to individual patients. However, conventional systems have struggled to effectively integrate collected medical information with individual health information and to provide flexible recommendations that reflect the user's emotional state. As a result, there are situations where the acceptability and effectiveness of medical recommendations cannot be sufficiently enhanced.

[0756] 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.

[0757] In this invention, the server includes means for collecting medical information and preprocessing it; means for receiving information from the user to obtain individual health information; means for executing a generative model to analyze the medical information and individual health information and generate optimal medical recommendations; means for using an emotion analysis engine to analyze the user's emotional state and adjust the content and expression of the recommendations; means for providing medical recommendations to the user; and means for collecting the user's response to the medical recommendations and utilizing it to improve the accuracy of the model. This makes it possible to provide more acceptable medical recommendations that take into account individual health information and the user's emotional state.

[0758] "Medical information" refers to all information related to healthcare, including clinical records, clinical data, drug information, and medical papers.

[0759] "Individualized health information" refers to health-related information specific to each user, such as their health status, past medical history, and allergy information, which is obtained for each individual user.

[0760] A "generative model" refers to a machine learning algorithm that generates optimal medical recommendations based on collected medical information and individual health information.

[0761] A "sentiment analysis engine" refers to a system that includes natural language processing technology used to analyze information entered by a user and recognize their emotional state.

[0762] "Means" refers to a method or technical device for achieving a specific function.

[0763] "Medical proposals" refer to suggestions made to users regarding treatment methods, care plans, and lifestyle improvement measures.

[0764] The embodiment of this invention is a medical recommendation system based on server, terminal, and user interaction. The following describes the specific hardware and software used, as well as their operation.

[0765] Server role:

[0766] The server collects medical information from medical institutions and public databases. This information includes clinical records, clinical data, drug information, and medical papers. The server retrieves data using APIs and scraping techniques. The retrieved data is managed in a database management system such as MySQL, where it undergoes processing such as data cleaning and formatting.

[0767] The formatted data is used to train generative AI models using machine learning platforms such as TensorFlow and PyTorch. The models analyze the combination of medical data and individual health information to generate optimal medical recommendations. Once predictions and recommendations with inventory applied are generated, an emotion analysis engine is used to analyze the user's emotional state and adjust the content and presentation of the recommendations to ensure that each user receives appropriate suggestions.

[0768] Terminal role:

[0769] The terminal functions as a user interface, providing a means of receiving health information from the user. Specifically, digital devices such as smartphones and personal computers are used. The data entered by the user is immediately sent to the server and used for analysis.

[0770] The terminal also displays medical suggestions provided by the server to the user. These individually tailored suggestions include reassuring language, allowing the user to make decisions based on them.

[0771] User roles:

[0772] The user's role in this system is to input their health information into the terminal. They are also expected to take recommended actions based on the presented medical suggestions. The user's emotional state is important for improving the acceptability of the suggestions and is analyzed through an emotion analysis engine. For example, by entering a prompt such as "I want to know how to relax," situation-appropriate advice will be provided.

[0773] This system can generate medical recommendations in real time, taking into account the user's specific needs and emotional state, and deliver them directly to the user. This enables the provision of personalized medical services.

[0774] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0775] Step 1:

[0776] The server collects medical information. It receives raw data from medical institutions and public databases as input. Specifically, it performs data retrieval via APIs and web scraping. A database management system stores this information as structured data. The output is a structured medical information dataset.

[0777] Step 2:

[0778] The server formats and preprocesses the collected medical information. It takes the structured data obtained in step 1 as input. Specific operations include data cleaning, normalization, and handling of missing values. It generates formatted data suitable for analysis as output.

[0779] Step 3:

[0780] The server receives individual user health information from the terminal. It receives health data provided by the user via the terminal as input. Specifically, it uses input interfaces such as web forms and mobile apps to send data to the server in real time. The output is the individually collected user health information.

[0781] Step 4:

[0782] The server generates optimal medical recommendations using a generative AI model. It takes formatted medical information and individual health information as input. Specific operations include running machine learning models using tools such as TensorFlow and PyTorch. The output is a customized medical recommendation tailored to the user's condition.

[0783] Step 5:

[0784] The emotion engine analyzes the user's emotions. It uses the user's health information and received feedback data as input. Specifically, it performs emotion analysis using natural language processing techniques. The output is the analysis result regarding the user's emotional state.

[0785] Step 6:

[0786] The server adjusts the suggested content based on the sentiment analysis results and sends it to the terminal. The input includes AI-generated medical suggestions and sentiment analysis results. Specific actions include adjusting the suggested wording and changing it to gentler language. The output is an adjusted medical suggestion that is gentle and effectively communicated to the user.

[0787] Step 7:

[0788] The terminal displays tailored medical suggestions to the user. It receives medical suggestions sent from the server as input. Its specific operation is to display the suggestions through a user-friendly interface. The output is the feedback data responded to by the user.

[0789] Step 8:

[0790] The user takes action based on the medical suggestions they receive. The input is the medical suggestions displayed on the device. Specific actions include implementing the suggested health management plan. The output is feedback on their health status and opinions based on their actions.

[0791] Step 9:

[0792] The server receives user feedback and uses it to improve the model's accuracy. It collects feedback sent from the terminal as input. Specific actions include retraining the model and analyzing data to improve the accuracy of suggestions. The output is a highly accurate trained model that enables improved medical recommendations.

[0793] (Application Example 2)

[0794] 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".

[0795] Conventional health management systems often make uniform suggestions without considering the emotional state of individual users, leading to difficulties in users accepting these suggestions. Furthermore, because they cannot adjust responses based on emotional states, they fail to adequately alleviate users' anxiety and stress, thus hindering the maximization of the effectiveness of medical care and health management.

[0796] 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.

[0797] In this invention, the server includes a device for collecting medical-related data and preprocessing the information, a device for receiving information from a user to obtain individual health information, and a device for analyzing the medical-related data and the individual health information and executing a generation algorithm to generate optimal health management suggestions. This makes it possible to recognize and adjust suggestions based on the user's emotions, and to provide suggestions that are easily accepted by the user.

[0798] "Medical-related data" refers to information such as clinical records, drug information, and medical papers obtained from medical institutions and publicly available databases.

[0799] "Individual health information" refers to health information specific to an individual, such as past health status, medical history, allergy information, and lifestyle habits, obtained from the user.

[0800] A "generative algorithm" is a computational procedure or method for generating optimal health management suggestions by analyzing medical-related data and individual health information.

[0801] An "device" refers to a mechanical or electronic instrument or system used to perform a specific function.

[0802] "Emotionally conscious and adjusted suggestions" are suggestions that analyze the user's emotional state, optimize the content and expression of the suggestions based on the results, and make them more acceptable to the user.

[0803] One embodiment of this invention is the construction of a health management system equipped with emotion recognition capabilities. The server first collects medical-related data from an external source, preprocesses that data, and stores it. Specifically, it employs a database management system to handle medical records, clinical information, and information on pharmaceuticals. Furthermore, it integrates and analyzes the collected medical data based on the individual health information of the received user. During this analysis process, a generation algorithm is used to generate optimal health management suggestions.

[0804] The server also uses emotion recognition APIs running on cloud platforms such as Azure to analyze the user's emotional state. This allows it to understand in real time how users perceive health management suggestions and adjust the suggestions based on that feedback.

[0805] The terminal functions as a user interface. Users can input health information using a smartphone or head-mounted display and receive suggestions from the server. The terminal also plays a role in enhancing acceptance by displaying suggestions tailored to the user's emotional state.

[0806] For example, when a user receives stress management suggestions through a head-mounted display, the system evaluates the user's stress level based on their heart rate and facial expression data, and uses a generative AI model to present suggestions in a gentle tone, such as, "This supplement will help you relax."

[0807] An example of a prompt for a generative AI model would be, "Generate a communication message appropriate for when the user is feeling anxious." This allows for a more intuitive and meaningful health management experience for the user.

[0808] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0809] Step 1:

[0810] The server collects medical-related data from external databases. This collection process includes clinical records, clinical data, and drug information. Input is raw data from various databases, and output is integrated medical data that has been formatted for preprocessing. This data is stored in the database management system.

[0811] Step 2:

[0812] Users input individual health information using a terminal. This data includes past health status, medical history, and allergy information. The terminal receives this data and sends it to the server. The input is health information provided by the user themselves, while the output is detailed health information used for analysis on the server side.

[0813] Step 3:

[0814] The server integrates medical data and individual health information and performs analysis using a generation algorithm. The input is the integrated data and detailed health information recorded in the previous step, and the output is optimal health management suggestions provided to the user. Specifically, the server constructs suggestions from this information using a generation AI model.

[0815] Step 4:

[0816] The server uses a cloud-based emotion recognition API to evaluate the user's emotional state. This process uses the user's biometric information (such as heart rate and facial expression data) as input. The output is an index indicating the user's emotional state. This prepares the server to adjust the content and expression of suggestions according to the user's emotions.

[0817] Step 5:

[0818] The device displays health management suggestions tailored to the user's emotions. The input is the tailored suggestions sent from the server, and the output is the information displayed on the user's screen. Specifically, the suggestions are delivered in a tone that aligns with the user's emotions.

[0819] Step 6:

[0820] After accepting health management suggestions, users input their feedback into a terminal. The input consists of the user's reactions and evaluations, while the output is data sent to the server for readjustment. This feedback is used to improve the accuracy of the generated AI model and serves as foundational data for making even more appropriate suggestions.

[0821] 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.

[0822] 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.

[0823] 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 robot 414.

[0824] 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.

[0825] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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."

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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 as being incorporated by reference.

[0842] The following is further disclosed regarding the embodiments described above.

[0843] (Claim 1)

[0844] A means for collecting medical data and preprocessing that data,

[0845] A means of receiving information from users in order to obtain individual health information,

[0846] A means for analyzing the aforementioned medical data and the aforementioned individual health information and executing a generative model for generating optimal medical recommendations,

[0847] Means for providing the generated medical proposal to the user,

[0848] A means for collecting user feedback on the aforementioned medical proposal and utilizing it to improve the accuracy of the model,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, wherein the generation model takes into account past medical history and allergy information to prevent medical accidents.

[0852] (Claim 3)

[0853] The system according to claim 1, which also provides personalized lifestyle improvement measures based on the results of analysis by the generative model.

[0854] "Example 1"

[0855] (Claim 1)

[0856] A method of collecting medical data from external sources, cleansing it, and performing cosmetic surgery,

[0857] A means of receiving individual health information from users and storing it in a database,

[0858] A means for analyzing the aforementioned medical data and the aforementioned individual health information using a generated AI model,

[0859] A means for generating and providing optimal medical proposals based on the aforementioned analysis results,

[0860] A means for collecting user feedback on the results of implementing the aforementioned medical proposal and improving the accuracy of the generated AI model,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, wherein the generated AI model takes into account past medical history and allergy information to prevent medical accidents.

[0864] (Claim 3)

[0865] The system according to claim 1, which provides personalized lifestyle improvement measures based on the results analyzed by a generative AI model.

[0866] "Application Example 1"

[0867] (Claim 1)

[0868] A device for collecting medical information and pre-processing that information,

[0869] A device that receives information from the user in order to acquire individual health data,

[0870] A device that analyzes the aforementioned medical information and the aforementioned individual health data and executes a generative model for generating optimal medical recommendations,

[0871] A device for providing the generated medical proposal to the user,

[0872] A device for collecting user feedback on the aforementioned medical proposal and utilizing it to improve the accuracy of the model,

[0873] A device that provides real-time optimized product recommendations based on the user's on-site health history via a dynamic user interface,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, wherein the generation model takes into account past medical history and allergy data to prevent medical accidents and uses a smart device to make product suggestions in real time.

[0877] (Claim 3)

[0878] The system according to claim 1, which provides personalized lifestyle improvement measures and optimized product recommendations based on the results of analysis by a generative model.

[0879] "Example 2 of combining an emotion engine"

[0880] (Claim 1)

[0881] A means for collecting medical information and pre-processing that information,

[0882] A means of receiving information from users in order to obtain individual health information,

[0883] A means for executing a generative model to analyze the aforementioned medical information and the aforementioned individual health information and generate optimal medical recommendations,

[0884] A means of using an emotion analysis engine to analyze the user's emotional state and adjust the content and expression of suggestions,

[0885] Means for providing the generated medical proposal to the user,

[0886] A means for collecting user responses to the aforementioned medical proposals and utilizing them to improve the accuracy of the model,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, wherein the generation model takes into account past medical history and allergy information to prevent medical accidents.

[0890] (Claim 3)

[0891] The system according to claim 1, which provides personalized lifestyle improvement measures based on the results of analysis by a generative model.

[0892] "Application example 2 when combining with an emotional engine"

[0893] (Claim 1)

[0894] A device for collecting medical-related data and preprocessing that information,

[0895] A device that receives information from users in order to obtain individual health information,

[0896] A device that analyzes the aforementioned medical-related data and the aforementioned individual health information and executes a generation algorithm to generate optimal health management suggestions,

[0897] A device for providing the generated health management proposal to the user,

[0898] A device for collecting user responses to the aforementioned health management proposals and utilizing them to improve the accuracy of the algorithm,

[0899] A device for recognizing the user's emotions and adjusting suggestions based on those emotions,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, wherein the generation algorithm takes into account past health management history and allergy information to prevent medical accidents.

[0903] (Claim 3)

[0904] The system according to claim 1, which provides personalized lifestyle improvement strategies based on the results of analysis by a generation algorithm, and further adjusts the suggestions considering the user's emotional state. [Explanation of symbols]

[0905] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting medical data and preprocessing that data, A means of receiving information from users in order to obtain individual health information, A means for analyzing the aforementioned medical data and the aforementioned individual health information and executing a generative model for generating optimal medical recommendations, Means for providing the generated medical proposal to the user, A means for collecting user feedback on the aforementioned medical proposal and utilizing it to improve the accuracy of the model, A system that includes this.

2. The system according to claim 1, wherein the generation model takes into account past medical history and allergy information to prevent medical accidents.

3. The system according to claim 1, which also provides personalized lifestyle improvement measures based on the results of analysis by the generative model.

Images