System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting patient data; means for pre-processing the collected patient data; means for analyzing the pre-processed patient data; means for generating a personalized treatment plan based on the analysis; and means for transmitting the generated treatment plan to a terminal via data communication.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional treatment methods do not adequately take into account individual differences in each patient's genetic information, environmental factors, lifestyle habits, etc., and therefore do not provide appropriate results for many patients. For this reason, there is a need to provide treatment plans optimized for each patient and improve medical outcomes. [Means for solving the problem]

[0005] The present invention provides a system including means for collecting, preprocessing, and analyzing patient data. Specifically, the system collects a patient's genetic information, environmental factors, and lifestyle data, preprocesses the data, and then analyzes it. The system also includes means for generating an individualized treatment plan based on the analysis results and transmitting the treatment plan to a terminal via data communication. The terminal further includes means for receiving and visually displaying the individualized treatment plan and means for collecting feedback from physicians and patients. The collected feedback is retransmitted and used to improve the treatment plan. In this way, it becomes possible to provide precise personalized medicine optimized for each patient.

[0006] "Patient data" refers to information related to a patient's health condition and lifestyle, such as genetic information, environmental factors, and lifestyle data.

[0007] "Preprocessing" refers to the process of interpolating or removing incomplete or outlier values ​​from collected data and standardizing the data.

[0008] "Analysis" is the process of performing statistical analysis and feature extraction based on the preprocessed data to evaluate the patient's health condition.

[0009] An "individualized treatment plan" is one that takes into account a patient's specific genetic information, environmental factors, and lifestyle and includes optimized treatments (such as diet, exercise programs, and medications).

[0010] "Data communication" is the process of encrypting the generated treatment plan and securely transmitting it to the terminal.

[0011] A "terminal" is a device that receives a treatment plan sent from the server and visually displays it to the user.

[0012] "Feedback" is information provided by doctors and patients regarding their opinions on treatment plans and implementation results.

[0013] A "generative AI algorithm" is an algorithm that automatically creates an individualized treatment plan based on analyzed data. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention relates to a system for generating personalized treatment plans. Specifically, it realizes highly accurate personalized medicine by linking together the elements of a server, terminal, and user, and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0036] Server Processing

[0037] Data collection and preprocessing

[0038] The server collects patient data from electronic medical record systems and wearable devices. This includes basic patient data (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. The collected data is first cleaned, and incomplete or outliers are interpolated or removed. The data is then converted into a standard format.

[0039] Data analysis and treatment plan generation

[0040] The preprocessed data is then analyzed by the server. First, genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for the patient. This treatment plan includes dietary therapy, exercise programs, and drug therapy.

[0041] data communication

[0042] The generated treatment plan is encrypted and sent to the device using a secure communication protocol to ensure confidentiality.

[0043] Terminal handling

[0044] Data reception and display

[0045] The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The device then displays the treatment plan in a visually easy-to-understand format. For example, daily meal plans and exercise programs can be presented in graphs or lists.

[0046] Feedback collection and resubmission

[0047] The device provides a form where doctors and patients can enter feedback about the treatment plan, which is then sent back to the server and used to improve the treatment plan.

[0048] User Action

[0049] Review and modify your treatment plan

[0050] The user (doctor) uses the device to check the patient's personalized treatment plan. If necessary, the doctor will suggest adjustments to the patient's diet or exercise program. The user (patient) checks the treatment plan on their own device and adjusts their lifestyle according to the instructions. Daily diet and exercise details are recorded on the device.

[0051] Evaluation of treatment effect

[0052] The user (doctor) evaluates the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[0053] Specific examples

[0054] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm generates a treatment plan that combines dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[0055] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal plan and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is retransmitted to the server. Based on the feedback, the doctor checks the effectiveness of the treatment plan and modifies it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[0056] The present invention is expected to realize personalized treatment for each patient, significantly improving the quality and effectiveness of medical care.

[0057] The processing flow will be explained below.

[0058] Server Processing

[0059] Step 1: Data collection

[0060] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood sugar level, and exercise volume from the wearable device worn by the patient.

[0061] Step 2: Data cleaning

[0062] The server detects incomplete or outliers from the collected data and performs appropriate interpolation or deletion to ensure the quality of the data.

[0063] Step 3: Data Standardization

[0064] The server converts the cleaned data into a standard format and stores it in a consistent format, facilitating subsequent analysis.

[0065] Step 4: Feature extraction

[0066] The server extracts key features from genetic information, environmental factors, and lifestyle data, including specific gene variants, living environment factors, and diet and exercise habits.

[0067] Step 5: Statistical analysis

[0068] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (for example, HbA1c value or BMI).

[0069] Step 6: Applying generative AI algorithms

[0070] Based on the results of statistical analysis and characteristic data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and medication.

[0071] Step 7: Encrypt and send your treatment plan

[0072] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol.

[0073] Terminal handling

[0074] Step 1: Receive and decrypt data

[0075] The terminal receives and decrypts the encrypted treatment plan sent from the server, making the treatment plan available on the terminal.

[0076] Step 2: Save your treatment plan

[0077] The device then associates the received treatment plan with the patient's account and stores it for future reference.

[0078] Step 3: Update the User Interface

[0079] The device displays the treatment plan in a visually easy-to-understand format, including diet menus, exercise plans, and medication schedules in graphs and lists.

[0080] Step 4: Submit a feedback form

[0081] The device provides a form where doctors and patients can enter feedback on the treatment plan, allowing the results of the treatment plan's application and areas for improvement to be collected.

[0082] Step 5: Resend your feedback

[0083] The device sends the collected feedback to a server, which uses this information to generate the next treatment plan.

[0084] User Action

[0085] Step 1: Review your treatment plan

[0086] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[0087] Step 2: Implementing the treatment plan

[0088] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. The user (doctor) checks whether the patient is following the plan.

[0089] Step 3: Provide feedback

[0090] The user (patient) records the progress of treatment and changes in physical condition on the device, and the user (doctor) provides feedback to evaluate the effectiveness of treatment based on the patient data.

[0091] Step 4: Adjusting your treatment plan

[0092] The user (doctor) modifies the treatment plan as needed based on the feedback and treatment data, and this new plan is provided to the patient again via the server and device.

[0093] The above are the specific processing steps for carrying out the present invention. This system makes it possible to efficiently realize precise personalized medicine optimized for each patient.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Providing personalized medicine requires the effective collection and analysis of diverse patient data and the rapid generation of highly accurate treatment plans. However, conventional systems face many challenges, including data incompleteness and outliers, limitations in analytical methods, and the need to ensure secure data communication. In particular, there are issues with the standardization of data collected in different formats, the insufficient analysis of data in real time, and the insufficient security and feedback of generated treatment plans.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes a means for collecting patient data, a means for cleaning the collected patient data and converting it into a standard format, a means for extracting features from the preprocessed patient data and performing statistical analysis, a means for generating an individualized treatment plan using a generative AI algorithm based on the analysis results, and a means for encrypting the generated treatment plan and transmitting it to a terminal using a secure communication protocol, thereby enabling the generation of a treatment plan quickly and accurately while maintaining the integrity and security of the data.

[0099] "Patient data" refers to a set of data necessary to realize personalized medicine, including basic patient information (age, gender, medical history), real-time data such as heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[0100] The "cleaning means" refers to a process for completing or deleting incomplete data or abnormal values ​​from collected patient data, thereby improving the quality of the data.

[0101] "Means for converting to a standard format" refers to a means for converting patient data collected in different formats into a unified data format (e.g., CSV, JSON).

[0102] A "means for extracting features" is a means for extracting important data characteristics or patterns to be analyzed from collected and pre-processed patient data.

[0103] A "means for performing statistical analysis" is a means for performing data analysis using statistical methods based on patient data to derive meaningful information.

[0104] A "generative AI algorithm" is an algorithm that uses machine learning and natural language processing to generate an individualized treatment plan based on input data.

[0105] A "treatment plan" is a personalized medical plan that includes dietary therapy, exercise program, medication, etc., optimized based on patient data.

[0106] "Encryption means" refers to a means for encrypting data to protect the treatment plan from malicious third parties during data communication.

[0107] A "secure communications protocol" is a protocol (e.g., HTTPS, TLS) used to securely communicate data.

[0108] "Device" means a computer device (e.g., smartphone, tablet, PC) that patients and physicians access to view and enter data.

[0109] A "feedback tool" is a tool for collecting physician and patient opinions and evaluations of the treatment plan.

[0110] The "retransmission means" is a means for retransmitting collected feedback to the server and using it to improve the treatment plan.

[0111] This invention relates to a system for generating personalized treatment plans. Specifically, it is a system that realizes highly accurate personalized medicine by linking together the elements of a server, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0112] Server Processing

[0113] The server first collects patient data from electronic medical record systems and wearable devices (e.g., Fitbit, Apple Watch). This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. This data is obtained using APIs. For example, the OAuth 2.0 protocol is used to securely obtain the data.

[0114] The server then cleans the collected data, imputing or removing incomplete data and outliers using Python's Pandas library or R's dplyr package, and converts the data into a standard format (e.g., CSV, JSON) after importing it as a DataFrame.

[0115] The server performs feature extraction and statistical analysis based on the preprocessed data. Machine learning algorithms (e.g., PCA and clustering methods from scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python.

[0116] Based on the analysis results, a generative AI algorithm (e.g., GPT-4, BERT) generates an optimal treatment plan, which includes dietary therapy, exercise program, and medication. The generated treatment plan is saved in YAML or JSON format.

[0117] The server encrypts the stored treatment plan (e.g., AES-256) and transmits it to the terminal using a secure communication protocol (e.g., HTTPS, TLS).

[0118] Terminal handling

[0119] The device receives the treatment plan sent from the server and decrypts it. For example, it decrypts the data encrypted with AES-256 using a dedicated decryption key. The device then associates the decrypted treatment plan with the patient's account and stores it. This storage can be done using local storage or a database (e.g., SQLite, Firebase).

[0120] The saved treatment plan is displayed on the device in a visually easy-to-understand format (e.g., graph or list format). Visualization is achieved using front-end frameworks such as React or Flutter. For example, a daily meal plan or exercise program is displayed graphically.

[0121] The device also provides a form where doctors and patients can enter feedback on the treatment plan. The form is created using HTML and JavaScript. The feedback is collected and sent back to the server.

[0122] User Action

[0123] The user (doctor) uses the device to check the patient's treatment plan. For example, detailed plan information is visualized on a dashboard in the browser. The user (patient) also uses the device to check the treatment plan and adjust their daily life. The user (patient) records their daily diet and exercise details on the device, and this data is managed on the device.

[0124] Based on the collected feedback and recorded data, the user (doctor) evaluates the effectiveness of the treatment. Based on this evaluation, the effectiveness of the treatment plan can be confirmed and the plan can be revised if necessary. By repeating this process, the optimal personalized treatment can be provided to the patient.

[0125] Specific examples

[0126] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food records, and exercise data from the electronic medical record system and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm (e.g., GPT-4) generates a treatment plan that combines the optimal diet, exercise program, and drug therapy.

[0127] This treatment plan is encrypted and sent to the device. The device receives the treatment plan and displays it in a format that is easy for the patient and doctor to understand. The doctor and patient can then enter feedback on the treatment plan, and this information is sent back to the server. Based on the feedback, the doctor can modify the treatment plan and optimize it for further improvement, thereby continuously improving the patient's personalized treatment.

[0128] Example prompt

[0129] "Please explain the process for a 40-year-old male diabetic patient to generate a new treatment plan based on blood glucose, heart rate, and exercise data collected from a wearable device."

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] The server collects patient data from the electronic medical record system and wearable devices. As input, it uses the authentication information and query parameters of the electronic medical record system API and wearable device API. This allows the collection of basic patient information (age, gender, medical history) and real-time data (heart rate, blood glucose level, exercise amount). As output, it obtains the patient data in JSON format.

[0133] Step 2:

[0134] The server cleans the collected patient data and converts it into a standard format. It uses the JSON data obtained in step 1 as input. It uses the Python Pandas library to impute or remove incomplete data and outliers, and processes it as a DataFrame. The output is the cleaned data in a standard format (e.g., CSV, JSON).

[0135] Step 3:

[0136] The server extracts features from the preprocessed data and performs statistical analysis. The cleaned data obtained in step 2 is used as input. Machine learning algorithms (e.g., PCA and clustering methods in scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python. The output is the results of the feature extraction and statistical analysis.

[0137] Step 4:

[0138] The server generates a personalized treatment plan using a generative AI algorithm based on the analysis results. The analysis results obtained in step 3 are used as input. A generative AI algorithm (e.g., GPT-4, BERT) is used to generate a personalized treatment plan, including diet, exercise program, and medication. The output is a treatment plan in YAML or JSON format.

[0139] Step 5:

[0140] The server encrypts the generated treatment plan and sends it to the terminal using a secure communication protocol. The treatment plan obtained in step 4 is used as input. AES-256 is used for encryption, and HTTPS or TLS is used for data communication. The encrypted treatment plan data is sent to the terminal as output.

[0141] Step 6:

[0142] The device receives and decrypts the treatment plan sent from the server. As input, it receives encrypted data from the server. It uses a dedicated decryption key to decrypt the AES-256 encrypted data. As output, it obtains the decrypted treatment plan.

[0143] Step 7:

[0144] The device displays the received treatment plan in a visually easy-to-understand format. As input, it uses the decoded treatment plan obtained in step 6. It uses a front-end framework such as React or Flutter to graphically display the daily meal menu and exercise program. As output, the visualized treatment plan is provided to the user.

[0145] Step 8:

[0146] The terminal provides a form where doctors and patients can enter feedback on the treatment plan. As input, users' ratings and comments on the treatment plan are entered into the form. This feedback is sent to the server using JavaScript and HTML. As output, feedback data is obtained.

[0147] Step 9:

[0148] The user (doctor) uses a device to review the patient's treatment plan and make adjustments based on the feedback. As input, they use the treatment plan visualized in step 7 and the feedback collected in step 8. They adjust and modify the treatment plan and create a new one. As output, they obtain the modified treatment plan.

[0149] Step 10:

[0150] The user (patient) records their daily diet and exercise on a device. As input, they record their daily diet and exercise amount in the device's app. This allows daily lifestyle data to be managed. As output, the recorded lifestyle data is obtained.

[0151] (Application example 1)

[0152] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0153] In modern healthcare, efficiently delivering personalized treatment plans is a challenging task. Furthermore, systems that not only provide personalized treatment plans but also enable continuous feedback and adjustment of treatment are needed. It is also important to provide real-time health management content that is relevant to patients' daily lives. This will enable more accurate and effective treatment and improve patients' quality of life.

[0154] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0155] In this invention, the server includes means for collecting patient data, means for preprocessing the collected patient data, means for analyzing the preprocessed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to a terminal via data communication, and means for visually displaying the generated treatment plan, thereby enabling the generative AI model to analyze the patient data and provide personalized health content based on prompts.

[0156] This not only allows for efficient generation and delivery of personalized treatment plans, but also allows for feedback from doctors and patients to be collected and the treatment plans to be continuously improved based on that data. Furthermore, real-time data collected from wearable devices can be used to support daily health management, improving patients' quality of life.

[0157] "Patient Data" is information about a patient, including genetic information, environmental factors, lifestyle data, and real-time data from wearable devices.

[0158] "Preprocessing" is the process of cleaning collected patient data, interpolating or removing incomplete or outlier values, and converting it into a standard format.

[0159] "Analysis" refers to the means by which pre-processed patient data is used to extract features, perform statistical analysis, and generate personalized treatment plans.

[0160] A "personalized treatment plan" is a treatment and health management guideline optimized for a specific patient based on genetic information, environmental factors, lifestyle data, and analysis results.

[0161] A "generative AI model" is an artificial intelligence algorithm used to analyze patient data and generate a personalized treatment plan.

[0162] A "prompt" is a series of instructions or instructions entered into a generative AI model to operate it.

[0163] "Data communication" is the process of sending data from a server to a terminal or from a terminal to a server, using secure communication protocols such as encryption.

[0164] "Visually displaying" means displaying the generated treatment plan and feedback in a graphical format on a terminal.

[0165] "Feedback" refers to opinions and evaluations of the treatment plan provided by the doctor and patient, which are resubmitted and used to improve the treatment plan.

[0166] The present invention relates to a system for generating personalized treatment plans and providing them to doctors and patients. Specifically, the system realizes highly accurate personalized medicine by linking servers, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0167] Server Processing

[0168] The server performs the following process:

[0169] 1. Data collection: Collect patient data from electronic medical record systems and wearable devices. This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume.

[0170] 2. Data preprocessing: The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[0171] 3. Data analysis and treatment plan generation: The pre-processed data is analyzed using a generative AI model. Genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, an optimized treatment plan (including diet, exercise program, and medication) is generated.

[0172] 4. Data communication: The generated treatment plan is encrypted and sent to the device using HTTPS and JSON Web Token (JWT) as secure communication protocols.

[0173] Terminal handling

[0174] The terminal performs the following process:

[0175] 1. Data reception and display: The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The treatment plan is then displayed in a visually easy-to-understand format (graph or list format).

[0176] 2. Feedback collection and resubmission: The terminal provides a form where doctors and patients can enter feedback on the treatment plan. The collected feedback is sent back to the server and used to improve the treatment plan.

[0177] User Action

[0178] Users (doctors and patients) perform the following processes:

[0179] 1. Review and modify treatment plan: The doctor uses the device to review the patient's personalized treatment plan. If necessary, the doctor will suggest dietary adjustments or changes to the exercise program. The patient will review the treatment plan on their own device and adjust their lifestyle accordingly. Daily diet and exercise information will be recorded on the device.

[0180] 2. Evaluation of treatment effectiveness: Doctors evaluate the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[0181] Technology used

[0182] The following technologies are used to realize this system:

[0183] Server: Amazon Web Services (AWS) or Microsoft Azure

[0184] Data analysis: Python, TensorFlow, scikit-learn

[0185] Frontend: React Native (for smartphone apps), Unity (for head-mounted displays)

[0186] Data collection: Bluetooth API (for integration with smartwatches and wearable devices)

[0187] Communication: HTTPS, JSON Web Token (JWT)

[0188] Specific examples

[0189] For example, consider a 40-year-old male patient diagnosed with diabetes. The server collects the patient's blood glucose level, food record, and exercise data from electronic medical records and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI model generates a treatment plan that combines a personalized diet, exercise program, and drug therapy. This treatment plan is encrypted and sent to the device.

[0190] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal menu and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is resent to the server. Based on the feedback, the doctor can check the effectiveness of the treatment plan and modify it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[0191] Example prompt sentence:

[0192] "Patient data: Age (40), Gender (Male), Blood Glucose Level (120, 140, 150), Exercise Amount (5000, 7000, 8000) Generative AI Algorithm: Generate optimal diet plan, exercise program, and medication based on this data."

[0193] This will enable personalized treatment for each patient, and is expected to significantly improve the quality and effectiveness of medical care.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] The server collects patient data from wearable devices and electronic medical record systems. Input data includes real-time data such as the patient's age, gender, medical history, heart rate, blood glucose level, and exercise volume. This allows a wide range of patient information to be captured by the server for preprocessing in the next step.

[0197] Step 2:

[0198] The server preprocesses the collected patient data. It cleans the input data, interpolates or removes incomplete or outliers, and converts it into a standard format. The data cleaning is performed using the Python pandas library, and an anomaly detection algorithm from scikit-learn is used to detect outliers. This results in high-quality data suitable for analysis.

[0199] Step 3:

[0200] The server analyzes the preprocessed data, extracting features related to genetic information, environmental factors, and lifestyle, and performing statistical analysis. Data analysis is performed using TensorFlow and the scikit-learn library. This allows for the extraction of features for each patient, and analysis results based on these features are obtained.

[0201] Step 4:

[0202] The server uses a generative AI model to generate an individualized treatment plan based on the analysis results. Specifically, it proposes dietary therapy, exercise programs, and drug therapy based on the input data and prompts. This results in a treatment plan optimized for each individual patient.

[0203] Step 5:

[0204] The server encrypts the generated treatment plan and sends it to the device. The encryption uses JSON Web Token (JWT) and HTTPS as the communication protocol, ensuring secure data transmission to the device.

[0205] Step 6:

[0206] The device receives and decrypts the transmitted treatment plan. The input data is the encrypted treatment plan, and the output is the decrypted treatment plan. This allows the data to be viewed on the device.

[0207] Step 7:

[0208] The device visually displays the treatment plan, specifically showing dietary menus and exercise programs in graph and list format. The user interface is implemented using React Native, allowing users to visually understand the plan.

[0209] Step 8:

[0210] Users (doctors and patients) enter feedback on the treatment plan into the terminal. The feedback data is collected through a form and resubmitted to the server in the next step. This allows information that reflects the actual treatment situation to be obtained.

[0211] Step 9:

[0212] The device then retransmits the collected feedback data to the server, where it is encrypted and securely transmitted to the server, where it is used to optimize the next treatment plan.

[0213] Step 10:

[0214] The server receives the feedback data again and uses it to generate the next treatment plan. By repeating the data preprocessing and analysis steps described above, the treatment plan is continuously improved based on the latest data, thereby providing the optimal treatment for the patient.

[0215] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0216] The present invention relates to a system that analyzes patient data and generates personalized treatment plans. Furthermore, the present invention relates to a system that incorporates an emotion engine that recognizes user emotions and reflects them in treatment plans. This system provides patients with optimized medical services through collaboration between the server, terminal, and user elements.

[0217] Server Processing

[0218] Data collection and preprocessing

[0219] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose level, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format.

[0220] Data analysis and treatment plan generation

[0221] The preprocessed data is analyzed by a server. Genetic information, environmental factors, and lifestyle characteristics are extracted and statistical analysis is performed. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[0222] data communication

[0223] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[0224] Terminal handling

[0225] Data reception and display

[0226] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[0227] Emotion engine processing

[0228] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and input content when entering feedback, and generates emotional data.

[0229] Feedback collection and resubmission

[0230] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[0231] User Action

[0232] Review and implement treatment plans

[0233] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[0234] Providing Feedback

[0235] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[0236] Adjusting your treatment plan

[0237] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0238] Specific examples

[0239] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan combining dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[0240] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[0241] The present invention is expected to realize personalized treatment for each patient and provide more effective and comfortable medical services by taking into consideration the patient's feelings.

[0242] The processing flow will be explained below.

[0243] Server Processing

[0244] Step 1: Data collection

[0245] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood glucose level, and exercise volume from the wearable device worn by the patient.

[0246] Step 2: Data cleaning

[0247] The server cleans the collected data, detecting incomplete or outliers and interpolating or removing them appropriately, thereby ensuring the quality of the data.

[0248] Step 3: Data Standardization

[0249] The server converts the cleaned data into a standard format, storing the data in a consistent format to facilitate subsequent analysis.

[0250] Step 4: Feature extraction

[0251] The server extracts key features from the patient's genetic information, environmental factors, and lifestyle data, such as specific gene polymorphisms, living environment factors, and dietary and exercise habits.

[0252] Step 5: Statistical analysis

[0253] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (e.g., HbA1c value, BMI) from the analysis results.

[0254] Step 6: Applying generative AI algorithms

[0255] Based on the results of the statistical analysis and the extracted feature data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and drug therapy.

[0256] Step 7: Encrypt and send your treatment plan

[0257] The server encrypts the generated treatment plan and transmits it to the terminal using a secure communication protocol.

[0258] Terminal handling

[0259] Step 1: Receive and decrypt data

[0260] The device receives the encrypted treatment plan sent from the server and decrypts it, allowing the treatment plan to be displayed on the device.

[0261] Step 2: Save your treatment plan

[0262] The device then associates the received treatment plan with the patient's account and stores it, allowing the user to view the saved treatment plan at any time.

[0263] Step 3: Update the User Interface

[0264] The device displays the treatment plan in a visually easy-to-understand format, showing diet menus, exercise plans, and medication schedules in graphs and lists.

[0265] Step 4: Emotion Recognition with the Emotion Engine

[0266] The emotion engine installed in the device analyzes facial expressions, tone of voice, input content, etc. when the user confirms the treatment plan, and generates emotion data.

[0267] Step 5: Submit a feedback form

[0268] The terminal provides a form where doctors and patients can enter feedback on the treatment plan, and the emotion engine also captures emotional data when the feedback is entered.

[0269] Step 6: Resend your feedback

[0270] The device sends the collected feedback and emotional data to a server, which uses this data to generate the next treatment plan.

[0271] User Action

[0272] Step 1: Review your treatment plan

[0273] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[0274] Step 2: Implementing the treatment plan

[0275] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. Doctors can check on the device whether the patient is following the plan.

[0276] Step 3: Provide feedback

[0277] The user (patient) records the progress of treatment and changes in their physical condition on the device. The emotion engine also collects emotional data obtained during this input. The doctor provides feedback to evaluate the effectiveness of treatment based on the patient's data.

[0278] Step 4: Adjusting your treatment plan

[0279] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0280] The above are the specific processing steps for implementing the present invention. This system provides personalized medical care optimized for each patient and realizes effective treatment that takes into account the user's emotions.

[0281] Example 2

[0282] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0283] Conventional medical systems lack the data analysis necessary to generate personalized treatment plans for each patient, resulting in ineffective treatment. Furthermore, because they do not take the patient's emotions into consideration, it is difficult to implement treatment plans, leading to a decline in the patient's motivation to receive treatment.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0285] In this invention, the server includes a means for collecting patient data, a means for preprocessing the collected patient data, a means for analyzing the preprocessed patient data, a means for generating an individualized treatment plan using a generating AI algorithm, and a means for encrypting the generated treatment plan and transmitting it to a terminal via data communication. This allows for a highly individualized treatment plan to be provided for each patient, and also enables the generation of a treatment plan that takes into account the patient's emotional data.

[0286] "Patient data" refers to data including information such as a patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[0287] "Preprocessing" refers to the process of interpolating or removing incomplete data or outliers from collected data and converting it into a standard format.

[0288] "Analysis" refers to performing statistical analysis and feature extraction on preprocessed data and analyzing it using generative AI algorithms.

[0289] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on patient data.

[0290] "Treatment plan" refers to a specific treatment method for each patient, including diet, exercise program, and drug therapy.

[0291] "Encryption" refers to the conversion of data using encryption techniques to securely communicate the generated treatment plan.

[0292] "Data communication" is the process of sending encrypted data over a network to a terminal.

[0293] A "terminal" is a device that is accessed by patients and doctors and has the function of visually displaying the received treatment plan and collecting feedback.

[0294] The "emotion engine" is an engine that analyzes the user's facial expressions and tone of voice to generate emotion data.

[0295] "Feedback" refers to information provided by doctors and patients regarding treatment plans, such as their opinions, progress, and changes in physical condition.

[0296] "Resubmit" refers to sending the collected feedback and emotion data to the server.

[0297] This invention is a system that analyzes patient data and generates personalized treatment plans. It also combines an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[0298] Server Processing

[0299] The server accesses electronic medical record systems and wearable devices to collect real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. To do this, data is securely acquired using the FHIR (Fast Healthcare Interoperability Resources) protocol, and data is acquired from wearable devices via Bluetooth or Wi-Fi. The collected data is first cleaned, and incomplete data and outliers are interpolated or removed, and then converted into a standard format. Here, a data frame is created using the Python Pandas library and the cleaning process is performed.

[0300] The preprocessed data is then analyzed using a generative AI algorithm. The AI ​​module uses Pytorch and TensorFlow to analyze the patient's genetic information and lifestyle characteristics. Statistical analysis is performed using SciPy and NumPy to statistically evaluate various health indicators. Based on the results of this analysis, a personalized treatment plan is generated that combines diet, exercise programs, and medication. This treatment plan is encrypted using AES encryption technology and securely transmitted to the device using the Transport Layer Security (TLS) protocol.

[0301] Terminal handling

[0302] The device receives and decrypts the encrypted data sent from the server. This is done using a private key stored on the device and a Python cryptography library. The decrypted treatment plan is then stored in association with the patient's account. The stored treatment plan is visually displayed in a web interface using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules.

[0303] Additionally, the device is equipped with an emotion engine to recognize the user's emotions. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through the camera and microphone. This data is analyzed using an emotion analysis library (e.g., DeepFace or OpenCV). The feedback and emotion data collected from the doctor and patient are again AES encrypted and sent to the server.

[0304] User Action

[0305] The user (doctor) checks the personalized treatment plan displayed on the device and makes adjustments as necessary. For example, when changing the dosage of medication, the user inputs the dosage into the interface on the device. The user (patient) follows the treatment plan displayed on the device and carries out daily diet and exercise. The exercise program includes video links of specific exercises, which the user follows.

[0306] The user (patient) inputs the progress of treatment and changes in physical condition via a terminal. These inputs are analyzed by the emotion engine, and emotional data is collected at the same time. For example, negative emotional data is sent along with feedback such as "Today's exercise was tough." The server analyzes the collected feedback and emotional data to further optimize the next treatment plan. The new treatment plan is then sent back to the terminal and provided to the user.

[0307] Specific examples

[0308] For example, a 40-year-old male patient is diagnosed with diabetes. Using this system, the server collects the patient's blood glucose level, food records, and exercise data from electronic medical records and wearable devices. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan that combines dietary therapy, exercise programs, and drug therapy. This treatment plan is then encrypted and sent to the device.

[0309] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[0310] Prompt Sentence Examples

[0311] "We want to generate personalized treatment plans based on patient data obtained from electronic medical records and wearable devices. We want to use an emotion engine to analyze the patient's emotional data and reflect it in the treatment plan."

[0312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0313] Step 1:

[0314] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. This data collection uses the FHIR protocol and Bluetooth or Wi-Fi. Data is collected from each device and stored on the server. Input data includes raw data from electronic medical records and wearable devices, and data stored on the server is output.

[0315] Step 2:

[0316] The server performs preprocessing on the collected data. This includes cleaning the data. Specifically, it interpolates or removes incomplete data and outliers, and converts the data into a standard format. It uses the Python Pandas library to create a data frame and performs the cleaning process. The input data is the collected raw data, and the preprocessed, clean data is output.

[0317] Step 3:

[0318] The server analyzes the preprocessed data. The analysis involves extracting the patient's genetic information and lifestyle characteristics using Pytorch and TensorFlow. It then performs statistical analysis using SciPy and NumPy. This process extracts health indicators and trends. The input data is the preprocessed data, and the output is the analysis results.

[0319] Step 4:

[0320] The server uses a generative AI algorithm based on the analysis results to generate a personalized treatment plan. This treatment plan includes dietary therapy, exercise program, and drug therapy. The AI ​​algorithm generates the optimal plan based on past data and analysis results. The analysis results are used as input data, and the generated treatment plan is output.

[0321] Step 5:

[0322] The server encrypts the generated treatment plan and sends it to the terminal using the TLS protocol. The data is securely protected using AES encryption technology. The generated treatment plan is the input data, and the encrypted data is output and sent to the terminal.

[0323] Step 6:

[0324] The device receives the encrypted data sent from the server and decrypts it using a private key stored on the device and the Python cryptography library. The input data is the encrypted data, and the output is the decrypted treatment plan.

[0325] Step 7:

[0326] The device associates the decrypted treatment plan with the patient's account, stores it, and visually displays it using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules. The decrypted treatment plan is the input data, and the visually displayed treatment plan is the output.

[0327] Step 8:

[0328] The device uses an emotion engine to analyze the user's emotional data. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through a camera and microphone, and analyzes them using an emotion analysis library (DeepFace or OpenCV). The input data is facial expression data and tone of voice, and the output is emotional data.

[0329] Step 9:

[0330] The device collects feedback and emotion data from doctors and patients, re-encrypts it, and sends it to the server. The collected feedback and emotion data is AES encrypted and securely transmitted using the TLS protocol. The input data is feedback and emotion data, and the encrypted data is output and sent to the server.

[0331] Step 10:

[0332] The server analyzes the collected feedback and emotion data and reflects it in the generation of the next treatment plan, thereby providing a more effective and personalized treatment plan. The input data are feedback and emotion data, and the output is the analysis results and an improved treatment plan.

[0333] (Application example 2)

[0334] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0335] In the current medical system, patients' emotional state is not taken into account when generating personalized treatment plans, which can affect treatment effectiveness. It is also difficult for doctors and nurses to grasp a patient's emotional state in real time, making it difficult to optimize treatment plans. Another problem is that emotional data is not properly reflected in the process of collecting feedback on patient treatment plans.

[0336] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting patient data, means for pre-processing the collected patient data, means for analyzing the pre-processed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to the terminal via data communication, means for analyzing collected user emotion data, and means for reflecting the analyzed emotion data in the treatment plan. This makes it possible to collect patient emotion data in real time and appropriately adjust the treatment plan based on the feedback.

[0337] "Patient data" refers to data that includes medical information such as the patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise.

[0338] "Preprocessing" refers to processes such as cleaning the collected data, interpolating, removing outliers, and converting it to a standard format.

[0339] "Analysis" refers to the statistical analysis of genetic information, environmental factors, and lifestyle data to extract characteristics.

[0340] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on collected data.

[0341] "Data communication" is a means of sending and receiving data using the Internet or dedicated lines.

[0342] The "emotion engine" is a system that generates emotion data from the user's facial expressions, tone of voice, etc.

[0343] A "treatment plan" is a personalized medical plan that may include diet, exercise program, medication, etc.

[0344] A "terminal" is an electronic device such as a smartphone, tablet, or smart glasses.

[0345] "Feedback" is information about the effectiveness of the treatment plan and the patient's emotional state.

[0346] "Collection" refers to the process or means of gathering data.

[0347] "Visual display" means displaying data in an easy-to-read manner on a screen or display.

[0348] This invention is a system that analyzes patient data and generates personalized treatment plans. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[0349] Server Processing

[0350] Data collection and preprocessing

[0351] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[0352] Data analysis and treatment plan generation

[0353] The pre-processed data is then analyzed by a generative AI algorithm. The server extracts genetic information, environmental factors, and lifestyle characteristics and performs statistical analysis. Based on the results of this analysis, an optimized treatment plan is generated for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[0354] data communication

[0355] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[0356] Terminal handling

[0357] Data reception and display

[0358] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[0359] Emotion engine processing

[0360] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice when inputting feedback, and generates emotion data. This emotion engine collects and analyzes the user's emotion data using the camera and microphone of the smart glasses.

[0361] Feedback collection and resubmission

[0362] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[0363] User Action

[0364] Review and implement treatment plans

[0365] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[0366] Providing Feedback

[0367] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[0368] Adjusting your treatment plan

[0369] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0370] Specific examples

[0371] For example, a clinic will incorporate smart glasses into the treatment plan for diabetic patients. When a patient comes to the clinic, the doctor will check the patient's current treatment plan through the smart glasses and collect emotional data in real time. If the patient expresses dissatisfaction with the diet, the emotion engine will detect this and send it to the server. The doctor will then adjust the treatment plan to find a more suitable approach for the patient.

[0372] Prompt Sentence Examples

[0373] "Enter patient feedback and collect data. The emotion engine uses the camera and microphone in the smart glasses to analyze the patient's facial expressions and tone of voice. Send the acquired emotion data and feedback on the effectiveness of the treatment plan to the server."

[0374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0375] Step 1:

[0376] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format, resulting in accurate and consistent data.

[0377] Input: Patient data from electronic medical record systems and wearable devices

[0378] Output: Cleaned and converted data into a standard format

[0379] Step 2:

[0380] The server then analyzes the pre-processed data using a generative AI algorithm, extracting genetic information, environmental factors, and lifestyle characteristics and conducting statistical analysis. Based on the results of this analysis, a personalized treatment plan is generated.

[0381] Input: Preprocessed patient data

[0382] Output: personalized treatment plan

[0383] Step 3:

[0384] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol, ensuring the safety of patient data.

[0385] Input: personalized treatment plan

[0386] Output: Encrypted treatment plan

[0387] Step 4:

[0388] The device receives and decrypts the treatment plan sent from the server, which is then stored in association with the patient's account and displayed in a visually accessible format (e.g., lists and graphs of dietary menus, exercise programs, and medication schedules).

[0389] Input: Encrypted treatment plan

[0390] Output: Visually displayed treatment plan

[0391] Step 5:

[0392] The emotion engine installed in the device uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice to generate emotion data, allowing the device to grasp their emotional state in real time.

[0393] Input: User's facial expression, tone of voice

[0394] Output: Generated emotion data

[0395] Step 6:

[0396] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[0397] Input: Doctor and patient feedback, sentiment data

[0398] Output: Feedback and emotion data sent to the server

[0399] Step 7:

[0400] The user (doctor) uses the device to review the patient's personalized treatment plan and make adjustments as needed, using emotional data and feedback to evaluate the effectiveness of the treatment plan and select a more appropriate treatment method for the patient.

[0401] Input: Treatment plan, emotional data, feedback

[0402] Output: Tailored treatment plan

[0403] Step 8:

[0404] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0405] Input: Feedback, emotion data

[0406] Output: Improved treatment plan

[0407] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0413] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0415] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0417] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0418] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0419] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0420] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0422] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0423] The present invention relates to a system for generating personalized treatment plans. Specifically, it realizes highly accurate personalized medicine by linking together the elements of a server, terminal, and user, and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0424] Server Processing

[0425] Data collection and preprocessing

[0426] The server collects patient data from electronic medical record systems and wearable devices. This includes basic patient data (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. The collected data is first cleaned, and incomplete or outliers are interpolated or removed. The data is then converted into a standard format.

[0427] Data analysis and treatment plan generation

[0428] The preprocessed data is then analyzed by the server. First, genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for the patient. This treatment plan includes dietary therapy, exercise programs, and drug therapy.

[0429] data communication

[0430] The generated treatment plan is encrypted and sent to the device using a secure communication protocol to ensure confidentiality.

[0431] Terminal handling

[0432] Data reception and display

[0433] The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The device then displays the treatment plan in a visually easy-to-understand format. For example, daily meal plans and exercise programs can be presented in graphs or lists.

[0434] Feedback collection and resubmission

[0435] The device provides a form where doctors and patients can enter feedback about the treatment plan, which is then sent back to the server and used to improve the treatment plan.

[0436] User Action

[0437] Review and modify your treatment plan

[0438] The user (doctor) uses the device to check the patient's personalized treatment plan. If necessary, the doctor will suggest adjustments to the patient's diet or exercise program. The user (patient) checks the treatment plan on their own device and adjusts their lifestyle according to the instructions. Daily diet and exercise details are recorded on the device.

[0439] Evaluation of treatment effect

[0440] The user (doctor) evaluates the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[0441] Specific examples

[0442] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm generates a treatment plan that combines dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[0443] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal plan and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is retransmitted to the server. Based on the feedback, the doctor checks the effectiveness of the treatment plan and modifies it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[0444] The present invention is expected to realize personalized treatment for each patient, significantly improving the quality and effectiveness of medical care.

[0445] The processing flow will be explained below.

[0446] Server Processing

[0447] Step 1: Data collection

[0448] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood sugar level, and exercise volume from the wearable device worn by the patient.

[0449] Step 2: Data cleaning

[0450] The server detects incomplete or outliers from the collected data and performs appropriate interpolation or deletion to ensure the quality of the data.

[0451] Step 3: Data Standardization

[0452] The server converts the cleaned data into a standard format and stores it in a consistent format, facilitating subsequent analysis.

[0453] Step 4: Feature extraction

[0454] The server extracts key features from genetic information, environmental factors, and lifestyle data, including specific gene variants, living environment factors, and diet and exercise habits.

[0455] Step 5: Statistical analysis

[0456] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (for example, HbA1c value or BMI).

[0457] Step 6: Applying generative AI algorithms

[0458] Based on the results of statistical analysis and characteristic data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and medication.

[0459] Step 7: Encrypt and send your treatment plan

[0460] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol.

[0461] Terminal handling

[0462] Step 1: Receive and decrypt data

[0463] The terminal receives and decrypts the encrypted treatment plan sent from the server, making the treatment plan available on the terminal.

[0464] Step 2: Save your treatment plan

[0465] The device then associates the received treatment plan with the patient's account and stores it for future reference.

[0466] Step 3: Update the User Interface

[0467] The device displays the treatment plan in a visually easy-to-understand format, including diet menus, exercise plans, and medication schedules in graphs and lists.

[0468] Step 4: Submit a feedback form

[0469] The device provides a form where doctors and patients can enter feedback on the treatment plan, allowing the results of the treatment plan's application and areas for improvement to be collected.

[0470] Step 5: Resend your feedback

[0471] The device sends the collected feedback to a server, which uses this information to generate the next treatment plan.

[0472] User Action

[0473] Step 1: Review your treatment plan

[0474] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[0475] Step 2: Implementing the treatment plan

[0476] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. The user (doctor) checks whether the patient is following the plan.

[0477] Step 3: Provide feedback

[0478] The user (patient) records the progress of treatment and changes in physical condition on the device, and the user (doctor) provides feedback to evaluate the effectiveness of treatment based on the patient data.

[0479] Step 4: Adjusting your treatment plan

[0480] The user (doctor) modifies the treatment plan as needed based on the feedback and treatment data, and this new plan is provided to the patient again via the server and device.

[0481] The above are the specific processing steps for carrying out the present invention. This system makes it possible to efficiently realize precise personalized medicine optimized for each patient.

[0482] Example 1

[0483] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0484] Providing personalized medicine requires the effective collection and analysis of diverse patient data and the rapid generation of highly accurate treatment plans. However, conventional systems face many challenges, including data incompleteness and outliers, limitations in analytical methods, and the need to ensure secure data communication. In particular, there are issues with the standardization of data collected in different formats, the insufficient analysis of data in real time, and the insufficient security and feedback of generated treatment plans.

[0485] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0486] In this invention, the server includes a means for collecting patient data, a means for cleaning the collected patient data and converting it into a standard format, a means for extracting features from the preprocessed patient data and performing statistical analysis, a means for generating an individualized treatment plan using a generative AI algorithm based on the analysis results, and a means for encrypting the generated treatment plan and transmitting it to a terminal using a secure communication protocol, thereby enabling the generation of a treatment plan quickly and accurately while maintaining the integrity and security of the data.

[0487] "Patient data" refers to a set of data necessary to realize personalized medicine, including basic patient information (age, gender, medical history), real-time data such as heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[0488] The "cleaning means" refers to a process for completing or deleting incomplete data or abnormal values ​​from collected patient data, thereby improving the quality of the data.

[0489] "Means for converting to a standard format" refers to a means for converting patient data collected in different formats into a unified data format (e.g., CSV, JSON).

[0490] A "means for extracting features" is a means for extracting important data characteristics or patterns to be analyzed from collected and pre-processed patient data.

[0491] A "means for performing statistical analysis" is a means for performing data analysis using statistical methods based on patient data to derive meaningful information.

[0492] A "generative AI algorithm" is an algorithm that uses machine learning and natural language processing to generate an individualized treatment plan based on input data.

[0493] A "treatment plan" is a personalized medical plan that includes dietary therapy, exercise program, medication, etc., optimized based on patient data.

[0494] "Encryption means" refers to a means for encrypting data to protect the treatment plan from malicious third parties during data communication.

[0495] A "secure communications protocol" is a protocol (e.g., HTTPS, TLS) used to securely communicate data.

[0496] "Device" means a computer device (e.g., smartphone, tablet, PC) that patients and physicians access to view and enter data.

[0497] A "feedback tool" is a tool for collecting physician and patient opinions and evaluations of the treatment plan.

[0498] The "retransmission means" is a means for retransmitting collected feedback to the server and using it to improve the treatment plan.

[0499] This invention relates to a system for generating personalized treatment plans. Specifically, it is a system that realizes highly accurate personalized medicine by linking together the elements of a server, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0500] Server Processing

[0501] The server first collects patient data from electronic medical record systems and wearable devices (e.g., Fitbit, Apple Watch). This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. This data is obtained using APIs. For example, the OAuth 2.0 protocol is used to securely obtain the data.

[0502] The server then cleans the collected data, imputing or removing incomplete data and outliers using Python's Pandas library or R's dplyr package, and converts the data into a standard format (e.g., CSV, JSON) after importing it as a DataFrame.

[0503] The server performs feature extraction and statistical analysis based on the preprocessed data. Machine learning algorithms (e.g., PCA and clustering methods from scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python.

[0504] Based on the analysis results, a generative AI algorithm (e.g., GPT-4, BERT) generates an optimal treatment plan, which includes dietary therapy, exercise program, and medication. The generated treatment plan is saved in YAML or JSON format.

[0505] The server encrypts the stored treatment plan (e.g., AES-256) and transmits it to the terminal using a secure communication protocol (e.g., HTTPS, TLS).

[0506] Terminal handling

[0507] The device receives the treatment plan sent from the server and decrypts it. For example, it decrypts the data encrypted with AES-256 using a dedicated decryption key. The device then associates the decrypted treatment plan with the patient's account and stores it. This storage can be done using local storage or a database (e.g., SQLite, Firebase).

[0508] The saved treatment plan is displayed on the device in a visually easy-to-understand format (e.g., graph or list format). Visualization is achieved using front-end frameworks such as React or Flutter. For example, a daily meal plan or exercise program is displayed graphically.

[0509] The device also provides a form where doctors and patients can enter feedback on the treatment plan. The form is created using HTML and JavaScript. The feedback is collected and sent back to the server.

[0510] User Action

[0511] The user (doctor) uses the device to check the patient's treatment plan. For example, detailed plan information is visualized on a dashboard in the browser. The user (patient) also uses the device to check the treatment plan and adjust their daily life. The user (patient) records their daily diet and exercise details on the device, and this data is managed on the device.

[0512] Based on the collected feedback and recorded data, the user (doctor) evaluates the effectiveness of the treatment. Based on this evaluation, the effectiveness of the treatment plan can be confirmed and the plan can be revised if necessary. By repeating this process, the optimal personalized treatment can be provided to the patient.

[0513] Specific examples

[0514] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food records, and exercise data from the electronic medical record system and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm (e.g., GPT-4) generates a treatment plan that combines the optimal diet, exercise program, and drug therapy.

[0515] This treatment plan is encrypted and sent to the device. The device receives the treatment plan and displays it in a format that is easy for the patient and doctor to understand. The doctor and patient can then enter feedback on the treatment plan, and this information is sent back to the server. Based on the feedback, the doctor can modify the treatment plan and optimize it for further improvement, thereby continuously improving the patient's personalized treatment.

[0516] Example prompt

[0517] "Please explain the process for a 40-year-old male diabetic patient to generate a new treatment plan based on blood glucose, heart rate, and exercise data collected from a wearable device."

[0518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0519] Step 1:

[0520] The server collects patient data from the electronic medical record system and wearable devices. As input, it uses the authentication information and query parameters of the electronic medical record system API and wearable device API. This allows the collection of basic patient information (age, gender, medical history) and real-time data (heart rate, blood glucose level, exercise amount). As output, it obtains the patient data in JSON format.

[0521] Step 2:

[0522] The server cleans the collected patient data and converts it into a standard format. It uses the JSON data obtained in step 1 as input. It uses the Python Pandas library to impute or remove incomplete data and outliers, and processes it as a DataFrame. The output is the cleaned data in a standard format (e.g., CSV, JSON).

[0523] Step 3:

[0524] The server extracts features from the preprocessed data and performs statistical analysis. The cleaned data obtained in step 2 is used as input. Machine learning algorithms (e.g., PCA and clustering methods in scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python. The output is the results of the feature extraction and statistical analysis.

[0525] Step 4:

[0526] The server generates a personalized treatment plan using a generative AI algorithm based on the analysis results. The analysis results obtained in step 3 are used as input. A generative AI algorithm (e.g., GPT-4, BERT) is used to generate a personalized treatment plan, including diet, exercise program, and medication. The output is a treatment plan in YAML or JSON format.

[0527] Step 5:

[0528] The server encrypts the generated treatment plan and sends it to the terminal using a secure communication protocol. The treatment plan obtained in step 4 is used as input. AES-256 is used for encryption, and HTTPS or TLS is used for data communication. The encrypted treatment plan data is sent to the terminal as output.

[0529] Step 6:

[0530] The device receives and decrypts the treatment plan sent from the server. As input, it receives encrypted data from the server. It uses a dedicated decryption key to decrypt the AES-256 encrypted data. As output, it obtains the decrypted treatment plan.

[0531] Step 7:

[0532] The device displays the received treatment plan in a visually easy-to-understand format. As input, it uses the decoded treatment plan obtained in step 6. It uses a front-end framework such as React or Flutter to graphically display the daily meal menu and exercise program. As output, the visualized treatment plan is provided to the user.

[0533] Step 8:

[0534] The terminal provides a form where doctors and patients can enter feedback on the treatment plan. As input, users' ratings and comments on the treatment plan are entered into the form. This feedback is sent to the server using JavaScript and HTML. As output, feedback data is obtained.

[0535] Step 9:

[0536] The user (doctor) uses a device to review the patient's treatment plan and make adjustments based on the feedback. As input, they use the treatment plan visualized in step 7 and the feedback collected in step 8. They adjust and modify the treatment plan and create a new one. As output, they obtain the modified treatment plan.

[0537] Step 10:

[0538] The user (patient) records their daily diet and exercise on a device. As input, they record their daily diet and exercise amount in the device's app. This allows daily lifestyle data to be managed. As output, the recorded lifestyle data is obtained.

[0539] (Application example 1)

[0540] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0541] In modern healthcare, efficiently delivering personalized treatment plans is a challenging task. Furthermore, systems that not only provide personalized treatment plans but also enable continuous feedback and adjustment of treatment are needed. It is also important to provide real-time health management content that is relevant to patients' daily lives. This will enable more accurate and effective treatment and improve patients' quality of life.

[0542] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0543] In this invention, the server includes means for collecting patient data, means for preprocessing the collected patient data, means for analyzing the preprocessed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to a terminal via data communication, and means for visually displaying the generated treatment plan, thereby enabling the generative AI model to analyze the patient data and provide personalized health content based on prompts.

[0544] This not only allows for efficient generation and delivery of personalized treatment plans, but also allows for feedback from doctors and patients to be collected and the treatment plans to be continuously improved based on that data. Furthermore, real-time data collected from wearable devices can be used to support daily health management, improving patients' quality of life.

[0545] "Patient Data" is information about a patient, including genetic information, environmental factors, lifestyle data, and real-time data from wearable devices.

[0546] "Preprocessing" is the process of cleaning collected patient data, interpolating or removing incomplete or outlier values, and converting it into a standard format.

[0547] "Analysis" refers to the means by which pre-processed patient data is used to extract features, perform statistical analysis, and generate personalized treatment plans.

[0548] A "personalized treatment plan" is a treatment and health management guideline optimized for a specific patient based on genetic information, environmental factors, lifestyle data, and analysis results.

[0549] A "generative AI model" is an artificial intelligence algorithm used to analyze patient data and generate a personalized treatment plan.

[0550] A "prompt" is a series of instructions or instructions entered into a generative AI model to operate it.

[0551] "Data communication" is the process of sending data from a server to a terminal or from a terminal to a server, using secure communication protocols such as encryption.

[0552] "Visually displaying" means displaying the generated treatment plan and feedback in a graphical format on a terminal.

[0553] "Feedback" refers to opinions and evaluations of the treatment plan provided by the doctor and patient, which are resubmitted and used to improve the treatment plan.

[0554] The present invention relates to a system for generating personalized treatment plans and providing them to doctors and patients. Specifically, the system realizes highly accurate personalized medicine by linking servers, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0555] Server Processing

[0556] The server performs the following process:

[0557] 1. Data collection: Collect patient data from electronic medical record systems and wearable devices. This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume.

[0558] 2. Data preprocessing: The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[0559] 3. Data analysis and treatment plan generation: The pre-processed data is analyzed using a generative AI model. Genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, an optimized treatment plan (including diet, exercise program, and medication) is generated.

[0560] 4. Data communication: The generated treatment plan is encrypted and sent to the device using HTTPS and JSON Web Token (JWT) as secure communication protocols.

[0561] Terminal handling

[0562] The terminal performs the following process:

[0563] 1. Data reception and display: The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The treatment plan is then displayed in a visually easy-to-understand format (graph or list format).

[0564] 2. Feedback collection and resubmission: The terminal provides a form where doctors and patients can enter feedback on the treatment plan. The collected feedback is sent back to the server and used to improve the treatment plan.

[0565] User Action

[0566] Users (doctors and patients) perform the following processes:

[0567] 1. Review and modify treatment plan: The doctor uses the device to review the patient's personalized treatment plan. If necessary, the doctor will suggest dietary adjustments or changes to the exercise program. The patient will review the treatment plan on their own device and adjust their lifestyle accordingly. Daily diet and exercise information will be recorded on the device.

[0568] 2. Evaluation of treatment effectiveness: Doctors evaluate the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[0569] Technology used

[0570] The following technologies are used to realize this system:

[0571] Server: Amazon Web Services (AWS) or Microsoft Azure

[0572] Data analysis: Python, TensorFlow, scikit-learn

[0573] Frontend: React Native (for smartphone apps), Unity (for head-mounted displays)

[0574] Data collection: Bluetooth API (for integration with smartwatches and wearable devices)

[0575] Communication: HTTPS, JSON Web Token (JWT)

[0576] Specific examples

[0577] For example, consider a 40-year-old male patient diagnosed with diabetes. The server collects the patient's blood glucose level, food record, and exercise data from electronic medical records and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI model generates a treatment plan that combines a personalized diet, exercise program, and drug therapy. This treatment plan is encrypted and sent to the device.

[0578] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal menu and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is resent to the server. Based on the feedback, the doctor can check the effectiveness of the treatment plan and modify it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[0579] Example prompt sentence:

[0580] "Patient data: Age (40), Gender (Male), Blood Glucose Level (120, 140, 150), Exercise Amount (5000, 7000, 8000) Generative AI Algorithm: Generate optimal diet plan, exercise program, and medication based on this data."

[0581] This will enable personalized treatment for each patient, and is expected to significantly improve the quality and effectiveness of medical care.

[0582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0583] Step 1:

[0584] The server collects patient data from wearable devices and electronic medical record systems. Input data includes real-time data such as the patient's age, gender, medical history, heart rate, blood glucose level, and exercise volume. This allows a wide range of patient information to be captured by the server for preprocessing in the next step.

[0585] Step 2:

[0586] The server preprocesses the collected patient data. It cleans the input data, interpolates or removes incomplete or outliers, and converts it into a standard format. The data cleaning is performed using the Python pandas library, and an anomaly detection algorithm from scikit-learn is used to detect outliers. This results in high-quality data suitable for analysis.

[0587] Step 3:

[0588] The server analyzes the preprocessed data, extracting features related to genetic information, environmental factors, and lifestyle, and performing statistical analysis. Data analysis is performed using TensorFlow and the scikit-learn library. This allows for the extraction of features for each patient, and analysis results based on these features are obtained.

[0589] Step 4:

[0590] The server uses a generative AI model to generate an individualized treatment plan based on the analysis results. Specifically, it proposes dietary therapy, exercise programs, and drug therapy based on the input data and prompts. This results in a treatment plan optimized for each individual patient.

[0591] Step 5:

[0592] The server encrypts the generated treatment plan and sends it to the device. The encryption uses JSON Web Token (JWT) and HTTPS as the communication protocol, ensuring secure data transmission to the device.

[0593] Step 6:

[0594] The device receives and decrypts the transmitted treatment plan. The input data is the encrypted treatment plan, and the output is the decrypted treatment plan. This allows the data to be viewed on the device.

[0595] Step 7:

[0596] The device visually displays the treatment plan, specifically showing dietary menus and exercise programs in graph and list format. The user interface is implemented using React Native, allowing users to visually understand the plan.

[0597] Step 8:

[0598] Users (doctors and patients) enter feedback on the treatment plan into the terminal. The feedback data is collected through a form and resubmitted to the server in the next step. This allows information that reflects the actual treatment situation to be obtained.

[0599] Step 9:

[0600] The device then retransmits the collected feedback data to the server, where it is encrypted and securely transmitted to the server, where it is used to optimize the next treatment plan.

[0601] Step 10:

[0602] The server receives the feedback data again and uses it to generate the next treatment plan. By repeating the data preprocessing and analysis steps described above, the treatment plan is continuously improved based on the latest data, thereby providing the optimal treatment for the patient.

[0603] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0604] The present invention relates to a system that analyzes patient data and generates personalized treatment plans. Furthermore, the present invention relates to a system that incorporates an emotion engine that recognizes user emotions and reflects them in treatment plans. This system provides patients with optimized medical services through collaboration between the server, terminal, and user elements.

[0605] Server Processing

[0606] Data collection and preprocessing

[0607] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose level, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format.

[0608] Data analysis and treatment plan generation

[0609] The preprocessed data is analyzed by a server. Genetic information, environmental factors, and lifestyle characteristics are extracted and statistical analysis is performed. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[0610] data communication

[0611] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[0612] Terminal handling

[0613] Data reception and display

[0614] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[0615] Emotion engine processing

[0616] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and input content when entering feedback, and generates emotional data.

[0617] Feedback collection and resubmission

[0618] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[0619] User Action

[0620] Review and implement treatment plans

[0621] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[0622] Providing Feedback

[0623] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[0624] Adjusting your treatment plan

[0625] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0626] Specific examples

[0627] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan combining dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[0628] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[0629] The present invention is expected to realize personalized treatment for each patient and provide more effective and comfortable medical services by taking into consideration the patient's feelings.

[0630] The processing flow will be explained below.

[0631] Server Processing

[0632] Step 1: Data collection

[0633] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood glucose level, and exercise volume from the wearable device worn by the patient.

[0634] Step 2: Data cleaning

[0635] The server cleans the collected data, detecting incomplete or outliers and interpolating or removing them appropriately, thereby ensuring the quality of the data.

[0636] Step 3: Data Standardization

[0637] The server converts the cleaned data into a standard format, storing the data in a consistent format to facilitate subsequent analysis.

[0638] Step 4: Feature extraction

[0639] The server extracts key features from the patient's genetic information, environmental factors, and lifestyle data, such as specific gene polymorphisms, living environment factors, and dietary and exercise habits.

[0640] Step 5: Statistical analysis

[0641] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (e.g., HbA1c value, BMI) from the analysis results.

[0642] Step 6: Applying generative AI algorithms

[0643] Based on the results of the statistical analysis and the extracted feature data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and drug therapy.

[0644] Step 7: Encrypt and send your treatment plan

[0645] The server encrypts the generated treatment plan and transmits it to the terminal using a secure communication protocol.

[0646] Terminal handling

[0647] Step 1: Receive and decrypt data

[0648] The device receives the encrypted treatment plan sent from the server and decrypts it, allowing the treatment plan to be displayed on the device.

[0649] Step 2: Save your treatment plan

[0650] The device then associates the received treatment plan with the patient's account and stores it, allowing the user to view the saved treatment plan at any time.

[0651] Step 3: Update the User Interface

[0652] The device displays the treatment plan in a visually easy-to-understand format, showing diet menus, exercise plans, and medication schedules in graphs and lists.

[0653] Step 4: Emotion Recognition with the Emotion Engine

[0654] The emotion engine installed in the device analyzes facial expressions, tone of voice, input content, etc. when the user confirms the treatment plan, and generates emotion data.

[0655] Step 5: Submit a feedback form

[0656] The terminal provides a form where doctors and patients can enter feedback on the treatment plan, and the emotion engine also captures emotional data when the feedback is entered.

[0657] Step 6: Resend your feedback

[0658] The device sends the collected feedback and emotional data to a server, which uses this data to generate the next treatment plan.

[0659] User Action

[0660] Step 1: Review your treatment plan

[0661] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[0662] Step 2: Implementing the treatment plan

[0663] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. Doctors can check on the device whether the patient is following the plan.

[0664] Step 3: Provide feedback

[0665] The user (patient) records the progress of treatment and changes in their physical condition on the device. The emotion engine also collects emotional data obtained during this input. The doctor provides feedback to evaluate the effectiveness of treatment based on the patient's data.

[0666] Step 4: Adjusting your treatment plan

[0667] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0668] The above are the specific processing steps for implementing the present invention. This system provides personalized medical care optimized for each patient and realizes effective treatment that takes into account the user's emotions.

[0669] Example 2

[0670] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0671] Conventional medical systems lack the data analysis necessary to generate personalized treatment plans for each patient, resulting in ineffective treatment. Furthermore, because they do not take the patient's emotions into consideration, it is difficult to implement treatment plans, leading to a decline in the patient's motivation to receive treatment.

[0672] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0673] In this invention, the server includes a means for collecting patient data, a means for preprocessing the collected patient data, a means for analyzing the preprocessed patient data, a means for generating an individualized treatment plan using a generating AI algorithm, and a means for encrypting the generated treatment plan and transmitting it to a terminal via data communication. This allows for a highly individualized treatment plan to be provided for each patient, and also enables the generation of a treatment plan that takes into account the patient's emotional data.

[0674] "Patient data" refers to data including information such as a patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[0675] "Preprocessing" refers to the process of interpolating or removing incomplete data or outliers from collected data and converting it into a standard format.

[0676] "Analysis" refers to performing statistical analysis and feature extraction on preprocessed data and analyzing it using generative AI algorithms.

[0677] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on patient data.

[0678] "Treatment plan" refers to a specific treatment method for each patient, including diet, exercise program, and drug therapy.

[0679] "Encryption" refers to the conversion of data using encryption techniques to securely communicate the generated treatment plan.

[0680] "Data communication" is the process of sending encrypted data over a network to a terminal.

[0681] A "terminal" is a device that is accessed by patients and doctors and has the function of visually displaying the received treatment plan and collecting feedback.

[0682] The "emotion engine" is an engine that analyzes the user's facial expressions and tone of voice to generate emotion data.

[0683] "Feedback" refers to information provided by doctors and patients regarding treatment plans, such as their opinions, progress, and changes in physical condition.

[0684] "Resubmit" refers to sending the collected feedback and emotion data to the server.

[0685] This invention is a system that analyzes patient data and generates personalized treatment plans. It also combines an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[0686] Server Processing

[0687] The server accesses electronic medical record systems and wearable devices to collect real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. To do this, data is securely acquired using the FHIR (Fast Healthcare Interoperability Resources) protocol, and data is acquired from wearable devices via Bluetooth or Wi-Fi. The collected data is first cleaned, and incomplete data and outliers are interpolated or removed, and then converted into a standard format. Here, a data frame is created using the Python Pandas library and the cleaning process is performed.

[0688] The preprocessed data is then analyzed using a generative AI algorithm. The AI ​​module uses Pytorch and TensorFlow to analyze the patient's genetic information and lifestyle characteristics. Statistical analysis is performed using SciPy and NumPy to statistically evaluate various health indicators. Based on the results of this analysis, a personalized treatment plan is generated that combines diet, exercise programs, and medication. This treatment plan is encrypted using AES encryption technology and securely transmitted to the device using the Transport Layer Security (TLS) protocol.

[0689] Terminal handling

[0690] The device receives and decrypts the encrypted data sent from the server. This is done using a private key stored on the device and a Python cryptography library. The decrypted treatment plan is then stored in association with the patient's account. The stored treatment plan is visually displayed in a web interface using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules.

[0691] Additionally, the device is equipped with an emotion engine to recognize the user's emotions. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through the camera and microphone. This data is analyzed using an emotion analysis library (e.g., DeepFace or OpenCV). The feedback and emotion data collected from the doctor and patient are again AES encrypted and sent to the server.

[0692] User Action

[0693] The user (doctor) checks the personalized treatment plan displayed on the device and makes adjustments as necessary. For example, when changing the dosage of medication, the user inputs the dosage into the interface on the device. The user (patient) follows the treatment plan displayed on the device and carries out daily diet and exercise. The exercise program includes video links of specific exercises, which the user follows.

[0694] The user (patient) inputs the progress of treatment and changes in physical condition via a terminal. These inputs are analyzed by the emotion engine, and emotional data is collected at the same time. For example, negative emotional data is sent along with feedback such as "Today's exercise was tough." The server analyzes the collected feedback and emotional data to further optimize the next treatment plan. The new treatment plan is then sent back to the terminal and provided to the user.

[0695] Specific examples

[0696] For example, a 40-year-old male patient is diagnosed with diabetes. Using this system, the server collects the patient's blood glucose level, food records, and exercise data from electronic medical records and wearable devices. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan that combines dietary therapy, exercise programs, and drug therapy. This treatment plan is then encrypted and sent to the device.

[0697] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[0698] Prompt Sentence Examples

[0699] "We want to generate personalized treatment plans based on patient data obtained from electronic medical records and wearable devices. We want to use an emotion engine to analyze the patient's emotional data and reflect it in the treatment plan."

[0700] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0701] Step 1:

[0702] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. This data collection uses the FHIR protocol and Bluetooth or Wi-Fi. Data is collected from each device and stored on the server. Input data includes raw data from electronic medical records and wearable devices, and data stored on the server is output.

[0703] Step 2:

[0704] The server performs preprocessing on the collected data. This includes cleaning the data. Specifically, it interpolates or removes incomplete data and outliers, and converts the data into a standard format. It uses the Python Pandas library to create a data frame and performs the cleaning process. The input data is the collected raw data, and the preprocessed, clean data is output.

[0705] Step 3:

[0706] The server analyzes the preprocessed data. The analysis involves extracting the patient's genetic information and lifestyle characteristics using Pytorch and TensorFlow. It then performs statistical analysis using SciPy and NumPy. This process extracts health indicators and trends. The input data is the preprocessed data, and the output is the analysis results.

[0707] Step 4:

[0708] The server uses a generative AI algorithm based on the analysis results to generate a personalized treatment plan. This treatment plan includes dietary therapy, exercise program, and drug therapy. The AI ​​algorithm generates the optimal plan based on past data and analysis results. The analysis results are used as input data, and the generated treatment plan is output.

[0709] Step 5:

[0710] The server encrypts the generated treatment plan and sends it to the terminal using the TLS protocol. The data is securely protected using AES encryption technology. The generated treatment plan is the input data, and the encrypted data is output and sent to the terminal.

[0711] Step 6:

[0712] The device receives the encrypted data sent from the server and decrypts it using a private key stored on the device and the Python cryptography library. The input data is the encrypted data, and the output is the decrypted treatment plan.

[0713] Step 7:

[0714] The device associates the decrypted treatment plan with the patient's account, stores it, and visually displays it using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules. The decrypted treatment plan is the input data, and the visually displayed treatment plan is the output.

[0715] Step 8:

[0716] The device uses an emotion engine to analyze the user's emotional data. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through a camera and microphone, and analyzes them using an emotion analysis library (DeepFace or OpenCV). The input data is facial expression data and tone of voice, and the output is emotional data.

[0717] Step 9:

[0718] The device collects feedback and emotion data from doctors and patients, re-encrypts it, and sends it to the server. The collected feedback and emotion data is AES encrypted and securely transmitted using the TLS protocol. The input data is feedback and emotion data, and the encrypted data is output and sent to the server.

[0719] Step 10:

[0720] The server analyzes the collected feedback and emotion data and reflects it in the generation of the next treatment plan, thereby providing a more effective and personalized treatment plan. The input data are feedback and emotion data, and the output is the analysis results and an improved treatment plan.

[0721] (Application example 2)

[0722] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0723] In the current medical system, patients' emotional state is not taken into account when generating personalized treatment plans, which can affect treatment effectiveness. It is also difficult for doctors and nurses to grasp a patient's emotional state in real time, making it difficult to optimize treatment plans. Another problem is that emotional data is not properly reflected in the process of collecting feedback on patient treatment plans.

[0724] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting patient data, means for pre-processing the collected patient data, means for analyzing the pre-processed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to the terminal via data communication, means for analyzing collected user emotion data, and means for reflecting the analyzed emotion data in the treatment plan. This makes it possible to collect patient emotion data in real time and appropriately adjust the treatment plan based on the feedback.

[0725] "Patient data" refers to data that includes medical information such as the patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise.

[0726] "Preprocessing" refers to processes such as cleaning the collected data, interpolating, removing outliers, and converting it to a standard format.

[0727] "Analysis" refers to the statistical analysis of genetic information, environmental factors, and lifestyle data to extract characteristics.

[0728] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on collected data.

[0729] "Data communication" is a means of sending and receiving data using the Internet or dedicated lines.

[0730] The "emotion engine" is a system that generates emotion data from the user's facial expressions, tone of voice, etc.

[0731] A "treatment plan" is a personalized medical plan that may include diet, exercise program, medication, etc.

[0732] A "terminal" is an electronic device such as a smartphone, tablet, or smart glasses.

[0733] "Feedback" is information about the effectiveness of the treatment plan and the patient's emotional state.

[0734] "Collection" refers to the process or means of gathering data.

[0735] "Visual display" means displaying data in an easy-to-read manner on a screen or display.

[0736] This invention is a system that analyzes patient data and generates personalized treatment plans. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[0737] Server Processing

[0738] Data collection and preprocessing

[0739] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[0740] Data analysis and treatment plan generation

[0741] The pre-processed data is then analyzed by a generative AI algorithm. The server extracts genetic information, environmental factors, and lifestyle characteristics and performs statistical analysis. Based on the results of this analysis, an optimized treatment plan is generated for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[0742] data communication

[0743] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[0744] Terminal handling

[0745] Data reception and display

[0746] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[0747] Emotion engine processing

[0748] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice when inputting feedback, and generates emotion data. This emotion engine collects and analyzes the user's emotion data using the camera and microphone of the smart glasses.

[0749] Feedback collection and resubmission

[0750] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[0751] User Action

[0752] Review and implement treatment plans

[0753] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[0754] Providing Feedback

[0755] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[0756] Adjusting your treatment plan

[0757] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0758] Specific examples

[0759] For example, a clinic will incorporate smart glasses into the treatment plan for diabetic patients. When a patient comes to the clinic, the doctor will check the patient's current treatment plan through the smart glasses and collect emotional data in real time. If the patient expresses dissatisfaction with the diet, the emotion engine will detect this and send it to the server. The doctor will then adjust the treatment plan to find a more suitable approach for the patient.

[0760] Prompt Sentence Examples

[0761] "Enter patient feedback and collect data. The emotion engine uses the camera and microphone in the smart glasses to analyze the patient's facial expressions and tone of voice. Send the acquired emotion data and feedback on the effectiveness of the treatment plan to the server."

[0762] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0763] Step 1:

[0764] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format, resulting in accurate and consistent data.

[0765] Input: Patient data from electronic medical record systems and wearable devices

[0766] Output: Cleaned and converted data into a standard format

[0767] Step 2:

[0768] The server then analyzes the pre-processed data using a generative AI algorithm, extracting genetic information, environmental factors, and lifestyle characteristics and conducting statistical analysis. Based on the results of this analysis, a personalized treatment plan is generated.

[0769] Input: Preprocessed patient data

[0770] Output: personalized treatment plan

[0771] Step 3:

[0772] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol, ensuring the safety of patient data.

[0773] Input: personalized treatment plan

[0774] Output: Encrypted treatment plan

[0775] Step 4:

[0776] The device receives and decrypts the treatment plan sent from the server, which is then stored in association with the patient's account and displayed in a visually accessible format (e.g., lists and graphs of dietary menus, exercise programs, and medication schedules).

[0777] Input: Encrypted treatment plan

[0778] Output: Visually displayed treatment plan

[0779] Step 5:

[0780] The emotion engine installed in the device uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice to generate emotion data, allowing the device to grasp their emotional state in real time.

[0781] Input: User's facial expression, tone of voice

[0782] Output: Generated emotion data

[0783] Step 6:

[0784] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[0785] Input: Doctor and patient feedback, sentiment data

[0786] Output: Feedback and emotion data sent to the server

[0787] Step 7:

[0788] The user (doctor) uses the device to review the patient's personalized treatment plan and make adjustments as needed, using emotional data and feedback to evaluate the effectiveness of the treatment plan and select a more appropriate treatment method for the patient.

[0789] Input: Treatment plan, emotional data, feedback

[0790] Output: Tailored treatment plan

[0791] Step 8:

[0792] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[0793] Input: Feedback, emotion data

[0794] Output: Improved treatment plan

[0795] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0796] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0797] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0798] [Third embodiment]

[0799] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0800] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0801] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0802] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0803] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0804] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0805] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0806] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0807] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0808] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0809] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0810] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0811] The present invention relates to a system for generating personalized treatment plans. Specifically, it realizes highly accurate personalized medicine by linking together the elements of a server, terminal, and user, and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0812] Server Processing

[0813] Data collection and preprocessing

[0814] The server collects patient data from electronic medical record systems and wearable devices. This includes basic patient data (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. The collected data is first cleaned, and incomplete or outliers are interpolated or removed. The data is then converted into a standard format.

[0815] Data analysis and treatment plan generation

[0816] The preprocessed data is then analyzed by the server. First, genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for the patient. This treatment plan includes dietary therapy, exercise programs, and drug therapy.

[0817] data communication

[0818] The generated treatment plan is encrypted and sent to the device using a secure communication protocol to ensure confidentiality.

[0819] Terminal handling

[0820] Data reception and display

[0821] The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The device then displays the treatment plan in a visually easy-to-understand format. For example, daily meal plans and exercise programs can be presented in graphs or lists.

[0822] Feedback collection and resubmission

[0823] The device provides a form where doctors and patients can enter feedback about the treatment plan, which is then sent back to the server and used to improve the treatment plan.

[0824] User Action

[0825] Review and modify your treatment plan

[0826] The user (doctor) uses the device to check the patient's personalized treatment plan. If necessary, the doctor will suggest adjustments to the patient's diet or exercise program. The user (patient) checks the treatment plan on their own device and adjusts their lifestyle according to the instructions. Daily diet and exercise details are recorded on the device.

[0827] Evaluation of treatment effect

[0828] The user (doctor) evaluates the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[0829] Specific examples

[0830] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm generates a treatment plan that combines dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[0831] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal plan and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is retransmitted to the server. Based on the feedback, the doctor checks the effectiveness of the treatment plan and modifies it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[0832] The present invention is expected to realize personalized treatment for each patient, significantly improving the quality and effectiveness of medical care.

[0833] The processing flow will be explained below.

[0834] Server Processing

[0835] Step 1: Data collection

[0836] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood sugar level, and exercise volume from the wearable device worn by the patient.

[0837] Step 2: Data cleaning

[0838] The server detects incomplete or outliers from the collected data and performs appropriate interpolation or deletion to ensure the quality of the data.

[0839] Step 3: Data Standardization

[0840] The server converts the cleaned data into a standard format and stores it in a consistent format, facilitating subsequent analysis.

[0841] Step 4: Feature extraction

[0842] The server extracts key features from genetic information, environmental factors, and lifestyle data, including specific gene variants, living environment factors, and diet and exercise habits.

[0843] Step 5: Statistical analysis

[0844] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (for example, HbA1c value or BMI).

[0845] Step 6: Applying generative AI algorithms

[0846] Based on the results of statistical analysis and characteristic data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and medication.

[0847] Step 7: Encrypt and send your treatment plan

[0848] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol.

[0849] Terminal handling

[0850] Step 1: Receive and decrypt data

[0851] The terminal receives and decrypts the encrypted treatment plan sent from the server, making the treatment plan available on the terminal.

[0852] Step 2: Save your treatment plan

[0853] The device then associates the received treatment plan with the patient's account and stores it for future reference.

[0854] Step 3: Update the User Interface

[0855] The device displays the treatment plan in a visually easy-to-understand format, including diet menus, exercise plans, and medication schedules in graphs and lists.

[0856] Step 4: Submit a feedback form

[0857] The device provides a form where doctors and patients can enter feedback on the treatment plan, allowing the results of the treatment plan's application and areas for improvement to be collected.

[0858] Step 5: Resend your feedback

[0859] The device sends the collected feedback to a server, which uses this information to generate the next treatment plan.

[0860] User Action

[0861] Step 1: Review your treatment plan

[0862] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[0863] Step 2: Implementing the treatment plan

[0864] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. The user (doctor) checks whether the patient is following the plan.

[0865] Step 3: Provide feedback

[0866] The user (patient) records the progress of treatment and changes in physical condition on the device, and the user (doctor) provides feedback to evaluate the effectiveness of treatment based on the patient data.

[0867] Step 4: Adjusting your treatment plan

[0868] The user (doctor) modifies the treatment plan as needed based on the feedback and treatment data, and this new plan is provided to the patient again via the server and device.

[0869] The above are the specific processing steps for carrying out the present invention. This system makes it possible to efficiently realize precise personalized medicine optimized for each patient.

[0870] Example 1

[0871] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0872] Providing personalized medicine requires the effective collection and analysis of diverse patient data and the rapid generation of highly accurate treatment plans. However, conventional systems face many challenges, including data incompleteness and outliers, limitations in analytical methods, and the need to ensure secure data communication. In particular, there are issues with the standardization of data collected in different formats, the insufficient analysis of data in real time, and the insufficient security and feedback of generated treatment plans.

[0873] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0874] In this invention, the server includes a means for collecting patient data, a means for cleaning the collected patient data and converting it into a standard format, a means for extracting features from the preprocessed patient data and performing statistical analysis, a means for generating an individualized treatment plan using a generative AI algorithm based on the analysis results, and a means for encrypting the generated treatment plan and transmitting it to a terminal using a secure communication protocol, thereby enabling the generation of a treatment plan quickly and accurately while maintaining the integrity and security of the data.

[0875] "Patient data" refers to a set of data necessary to realize personalized medicine, including basic patient information (age, gender, medical history), real-time data such as heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[0876] The "cleaning means" refers to a process for completing or deleting incomplete data or abnormal values ​​from collected patient data, thereby improving the quality of the data.

[0877] "Means for converting to a standard format" refers to a means for converting patient data collected in different formats into a unified data format (e.g., CSV, JSON).

[0878] A "means for extracting features" is a means for extracting important data characteristics or patterns to be analyzed from collected and pre-processed patient data.

[0879] A "means for performing statistical analysis" is a means for performing data analysis using statistical methods based on patient data to derive meaningful information.

[0880] A "generative AI algorithm" is an algorithm that uses machine learning and natural language processing to generate an individualized treatment plan based on input data.

[0881] A "treatment plan" is a personalized medical plan that includes dietary therapy, exercise program, medication, etc., optimized based on patient data.

[0882] "Encryption means" refers to a means for encrypting data to protect the treatment plan from malicious third parties during data communication.

[0883] A "secure communications protocol" is a protocol (e.g., HTTPS, TLS) used to securely communicate data.

[0884] "Device" means a computer device (e.g., smartphone, tablet, PC) that patients and physicians access to view and enter data.

[0885] A "feedback tool" is a tool for collecting physician and patient opinions and evaluations of the treatment plan.

[0886] The "retransmission means" is a means for retransmitting collected feedback to the server and using it to improve the treatment plan.

[0887] This invention relates to a system for generating personalized treatment plans. Specifically, it is a system that realizes highly accurate personalized medicine by linking together the elements of a server, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0888] Server Processing

[0889] The server first collects patient data from electronic medical record systems and wearable devices (e.g., Fitbit, Apple Watch). This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. This data is obtained using APIs. For example, the OAuth 2.0 protocol is used to securely obtain the data.

[0890] The server then cleans the collected data, imputing or removing incomplete data and outliers using Python's Pandas library or R's dplyr package, and converts the data into a standard format (e.g., CSV, JSON) after importing it as a DataFrame.

[0891] The server performs feature extraction and statistical analysis based on the preprocessed data. Machine learning algorithms (e.g., PCA and clustering methods from scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python.

[0892] Based on the analysis results, a generative AI algorithm (e.g., GPT-4, BERT) generates an optimal treatment plan, which includes dietary therapy, exercise program, and medication. The generated treatment plan is saved in YAML or JSON format.

[0893] The server encrypts the stored treatment plan (e.g., AES-256) and transmits it to the terminal using a secure communication protocol (e.g., HTTPS, TLS).

[0894] Terminal handling

[0895] The device receives the treatment plan sent from the server and decrypts it. For example, it decrypts the data encrypted with AES-256 using a dedicated decryption key. The device then associates the decrypted treatment plan with the patient's account and stores it. This storage can be done using local storage or a database (e.g., SQLite, Firebase).

[0896] The saved treatment plan is displayed on the device in a visually easy-to-understand format (e.g., graph or list format). Visualization is achieved using front-end frameworks such as React or Flutter. For example, a daily meal plan or exercise program is displayed graphically.

[0897] The device also provides a form where doctors and patients can enter feedback on the treatment plan. The form is created using HTML and JavaScript. The feedback is collected and sent back to the server.

[0898] User Action

[0899] The user (doctor) uses the device to check the patient's treatment plan. For example, detailed plan information is visualized on a dashboard in the browser. The user (patient) also uses the device to check the treatment plan and adjust their daily life. The user (patient) records their daily diet and exercise details on the device, and this data is managed on the device.

[0900] Based on the collected feedback and recorded data, the user (doctor) evaluates the effectiveness of the treatment. Based on this evaluation, the effectiveness of the treatment plan can be confirmed and the plan can be revised if necessary. By repeating this process, the optimal personalized treatment can be provided to the patient.

[0901] Specific examples

[0902] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food records, and exercise data from the electronic medical record system and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm (e.g., GPT-4) generates a treatment plan that combines the optimal diet, exercise program, and drug therapy.

[0903] This treatment plan is encrypted and sent to the device. The device receives the treatment plan and displays it in a format that is easy for the patient and doctor to understand. The doctor and patient can then enter feedback on the treatment plan, and this information is sent back to the server. Based on the feedback, the doctor can modify the treatment plan and optimize it for further improvement, thereby continuously improving the patient's personalized treatment.

[0904] Example prompt

[0905] "Please explain the process for a 40-year-old male diabetic patient to generate a new treatment plan based on blood glucose, heart rate, and exercise data collected from a wearable device."

[0906] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0907] Step 1:

[0908] The server collects patient data from the electronic medical record system and wearable devices. As input, it uses the authentication information and query parameters of the electronic medical record system API and wearable device API. This allows the collection of basic patient information (age, gender, medical history) and real-time data (heart rate, blood glucose level, exercise amount). As output, it obtains the patient data in JSON format.

[0909] Step 2:

[0910] The server cleans the collected patient data and converts it into a standard format. It uses the JSON data obtained in step 1 as input. It uses the Python Pandas library to impute or remove incomplete data and outliers, and processes it as a DataFrame. The output is the cleaned data in a standard format (e.g., CSV, JSON).

[0911] Step 3:

[0912] The server extracts features from the preprocessed data and performs statistical analysis. The cleaned data obtained in step 2 is used as input. Machine learning algorithms (e.g., PCA and clustering methods in scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python. The output is the results of the feature extraction and statistical analysis.

[0913] Step 4:

[0914] The server generates a personalized treatment plan using a generative AI algorithm based on the analysis results. The analysis results obtained in step 3 are used as input. A generative AI algorithm (e.g., GPT-4, BERT) is used to generate a personalized treatment plan, including diet, exercise program, and medication. The output is a treatment plan in YAML or JSON format.

[0915] Step 5:

[0916] The server encrypts the generated treatment plan and sends it to the terminal using a secure communication protocol. The treatment plan obtained in step 4 is used as input. AES-256 is used for encryption, and HTTPS or TLS is used for data communication. The encrypted treatment plan data is sent to the terminal as output.

[0917] Step 6:

[0918] The device receives and decrypts the treatment plan sent from the server. As input, it receives encrypted data from the server. It uses a dedicated decryption key to decrypt the AES-256 encrypted data. As output, it obtains the decrypted treatment plan.

[0919] Step 7:

[0920] The device displays the received treatment plan in a visually easy-to-understand format. As input, it uses the decoded treatment plan obtained in step 6. It uses a front-end framework such as React or Flutter to graphically display the daily meal menu and exercise program. As output, the visualized treatment plan is provided to the user.

[0921] Step 8:

[0922] The terminal provides a form where doctors and patients can enter feedback on the treatment plan. As input, users' ratings and comments on the treatment plan are entered into the form. This feedback is sent to the server using JavaScript and HTML. As output, feedback data is obtained.

[0923] Step 9:

[0924] The user (doctor) uses a device to review the patient's treatment plan and make adjustments based on the feedback. As input, they use the treatment plan visualized in step 7 and the feedback collected in step 8. They adjust and modify the treatment plan and create a new one. As output, they obtain the modified treatment plan.

[0925] Step 10:

[0926] The user (patient) records their daily diet and exercise on a device. As input, they record their daily diet and exercise amount in the device's app. This allows daily lifestyle data to be managed. As output, the recorded lifestyle data is obtained.

[0927] (Application example 1)

[0928] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0929] In modern healthcare, efficiently delivering personalized treatment plans is a challenging task. Furthermore, systems that not only provide personalized treatment plans but also enable continuous feedback and adjustment of treatment are needed. It is also important to provide real-time health management content that is relevant to patients' daily lives. This will enable more accurate and effective treatment and improve patients' quality of life.

[0930] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0931] In this invention, the server includes means for collecting patient data, means for preprocessing the collected patient data, means for analyzing the preprocessed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to a terminal via data communication, and means for visually displaying the generated treatment plan, thereby enabling the generative AI model to analyze the patient data and provide personalized health content based on prompts.

[0932] This not only allows for efficient generation and delivery of personalized treatment plans, but also allows for feedback from doctors and patients to be collected and the treatment plans to be continuously improved based on that data. Furthermore, real-time data collected from wearable devices can be used to support daily health management, improving patients' quality of life.

[0933] "Patient Data" is information about a patient, including genetic information, environmental factors, lifestyle data, and real-time data from wearable devices.

[0934] "Preprocessing" is the process of cleaning collected patient data, interpolating or removing incomplete or outlier values, and converting it into a standard format.

[0935] "Analysis" refers to the means by which pre-processed patient data is used to extract features, perform statistical analysis, and generate personalized treatment plans.

[0936] A "personalized treatment plan" is a treatment and health management guideline optimized for a specific patient based on genetic information, environmental factors, lifestyle data, and analysis results.

[0937] A "generative AI model" is an artificial intelligence algorithm used to analyze patient data and generate a personalized treatment plan.

[0938] A "prompt" is a series of instructions or instructions entered into a generative AI model to operate it.

[0939] "Data communication" is the process of sending data from a server to a terminal or from a terminal to a server, using secure communication protocols such as encryption.

[0940] "Visually displaying" means displaying the generated treatment plan and feedback in a graphical format on a terminal.

[0941] "Feedback" refers to opinions and evaluations of the treatment plan provided by the doctor and patient, which are resubmitted and used to improve the treatment plan.

[0942] The present invention relates to a system for generating personalized treatment plans and providing them to doctors and patients. Specifically, the system realizes highly accurate personalized medicine by linking servers, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[0943] Server Processing

[0944] The server performs the following process:

[0945] 1. Data collection: Collect patient data from electronic medical record systems and wearable devices. This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume.

[0946] 2. Data preprocessing: The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[0947] 3. Data analysis and treatment plan generation: The pre-processed data is analyzed using a generative AI model. Genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, an optimized treatment plan (including diet, exercise program, and medication) is generated.

[0948] 4. Data communication: The generated treatment plan is encrypted and sent to the device using HTTPS and JSON Web Token (JWT) as secure communication protocols.

[0949] Terminal handling

[0950] The terminal performs the following process:

[0951] 1. Data reception and display: The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The treatment plan is then displayed in a visually easy-to-understand format (graph or list format).

[0952] 2. Feedback collection and resubmission: The terminal provides a form where doctors and patients can enter feedback on the treatment plan. The collected feedback is sent back to the server and used to improve the treatment plan.

[0953] User Action

[0954] Users (doctors and patients) perform the following processes:

[0955] 1. Review and modify treatment plan: The doctor uses the device to review the patient's personalized treatment plan. If necessary, the doctor will suggest dietary adjustments or changes to the exercise program. The patient will review the treatment plan on their own device and adjust their lifestyle accordingly. Daily diet and exercise information will be recorded on the device.

[0956] 2. Evaluation of treatment effectiveness: Doctors evaluate the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[0957] Technology used

[0958] The following technologies are used to realize this system:

[0959] Server: Amazon Web Services (AWS) or Microsoft Azure

[0960] Data analysis: Python, TensorFlow, scikit-learn

[0961] Frontend: React Native (for smartphone apps), Unity (for head-mounted displays)

[0962] Data collection: Bluetooth API (for integration with smartwatches and wearable devices)

[0963] Communication: HTTPS, JSON Web Token (JWT)

[0964] Specific examples

[0965] For example, consider a 40-year-old male patient diagnosed with diabetes. The server collects the patient's blood glucose level, food record, and exercise data from electronic medical records and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI model generates a treatment plan that combines a personalized diet, exercise program, and drug therapy. This treatment plan is encrypted and sent to the device.

[0966] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal menu and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is resent to the server. Based on the feedback, the doctor can check the effectiveness of the treatment plan and modify it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[0967] Example prompt sentence:

[0968] "Patient data: Age (40), Gender (Male), Blood Glucose Level (120, 140, 150), Exercise Amount (5000, 7000, 8000) Generative AI Algorithm: Generate optimal diet plan, exercise program, and medication based on this data."

[0969] This will enable personalized treatment for each patient, and is expected to significantly improve the quality and effectiveness of medical care.

[0970] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0971] Step 1:

[0972] The server collects patient data from wearable devices and electronic medical record systems. Input data includes real-time data such as the patient's age, gender, medical history, heart rate, blood glucose level, and exercise volume. This allows a wide range of patient information to be captured by the server for preprocessing in the next step.

[0973] Step 2:

[0974] The server preprocesses the collected patient data. It cleans the input data, interpolates or removes incomplete or outliers, and converts it into a standard format. The data cleaning is performed using the Python pandas library, and an anomaly detection algorithm from scikit-learn is used to detect outliers. This results in high-quality data suitable for analysis.

[0975] Step 3:

[0976] The server analyzes the preprocessed data, extracting features related to genetic information, environmental factors, and lifestyle, and performing statistical analysis. Data analysis is performed using TensorFlow and the scikit-learn library. This allows for the extraction of features for each patient, and analysis results based on these features are obtained.

[0977] Step 4:

[0978] The server uses a generative AI model to generate an individualized treatment plan based on the analysis results. Specifically, it proposes dietary therapy, exercise programs, and drug therapy based on the input data and prompts. This results in a treatment plan optimized for each individual patient.

[0979] Step 5:

[0980] The server encrypts the generated treatment plan and sends it to the device. The encryption uses JSON Web Token (JWT) and HTTPS as the communication protocol, ensuring secure data transmission to the device.

[0981] Step 6:

[0982] The device receives and decrypts the transmitted treatment plan. The input data is the encrypted treatment plan, and the output is the decrypted treatment plan. This allows the data to be viewed on the device.

[0983] Step 7:

[0984] The device visually displays the treatment plan, specifically showing dietary menus and exercise programs in graph and list format. The user interface is implemented using React Native, allowing users to visually understand the plan.

[0985] Step 8:

[0986] Users (doctors and patients) enter feedback on the treatment plan into the terminal. The feedback data is collected through a form and resubmitted to the server in the next step. This allows information that reflects the actual treatment situation to be obtained.

[0987] Step 9:

[0988] The device then retransmits the collected feedback data to the server, where it is encrypted and securely transmitted to the server, where it is used to optimize the next treatment plan.

[0989] Step 10:

[0990] The server receives the feedback data again and uses it to generate the next treatment plan. By repeating the data preprocessing and analysis steps described above, the treatment plan is continuously improved based on the latest data, thereby providing the optimal treatment for the patient.

[0991] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0992] The present invention relates to a system that analyzes patient data and generates personalized treatment plans. Furthermore, the present invention relates to a system that incorporates an emotion engine that recognizes user emotions and reflects them in treatment plans. This system provides patients with optimized medical services through collaboration between the server, terminal, and user elements.

[0993] Server Processing

[0994] Data collection and preprocessing

[0995] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose level, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format.

[0996] Data analysis and treatment plan generation

[0997] The preprocessed data is analyzed by a server. Genetic information, environmental factors, and lifestyle characteristics are extracted and statistical analysis is performed. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[0998] data communication

[0999] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[1000] Terminal handling

[1001] Data reception and display

[1002] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[1003] Emotion engine processing

[1004] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and input content when entering feedback, and generates emotional data.

[1005] Feedback collection and resubmission

[1006] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[1007] User Action

[1008] Review and implement treatment plans

[1009] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[1010] Providing Feedback

[1011] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[1012] Adjusting your treatment plan

[1013] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1014] Specific examples

[1015] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan combining dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[1016] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[1017] The present invention is expected to realize personalized treatment for each patient and provide more effective and comfortable medical services by taking into consideration the patient's feelings.

[1018] The processing flow will be explained below.

[1019] Server Processing

[1020] Step 1: Data collection

[1021] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood glucose level, and exercise volume from the wearable device worn by the patient.

[1022] Step 2: Data cleaning

[1023] The server cleans the collected data, detecting incomplete or outliers and interpolating or removing them appropriately, thereby ensuring the quality of the data.

[1024] Step 3: Data Standardization

[1025] The server converts the cleaned data into a standard format, storing the data in a consistent format to facilitate subsequent analysis.

[1026] Step 4: Feature extraction

[1027] The server extracts key features from the patient's genetic information, environmental factors, and lifestyle data, such as specific gene polymorphisms, living environment factors, and dietary and exercise habits.

[1028] Step 5: Statistical analysis

[1029] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (e.g., HbA1c value, BMI) from the analysis results.

[1030] Step 6: Applying generative AI algorithms

[1031] Based on the results of the statistical analysis and the extracted feature data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and drug therapy.

[1032] Step 7: Encrypt and send your treatment plan

[1033] The server encrypts the generated treatment plan and transmits it to the terminal using a secure communication protocol.

[1034] Terminal handling

[1035] Step 1: Receive and decrypt data

[1036] The device receives the encrypted treatment plan sent from the server and decrypts it, allowing the treatment plan to be displayed on the device.

[1037] Step 2: Save your treatment plan

[1038] The device then associates the received treatment plan with the patient's account and stores it, allowing the user to view the saved treatment plan at any time.

[1039] Step 3: Update the User Interface

[1040] The device displays the treatment plan in a visually easy-to-understand format, showing diet menus, exercise plans, and medication schedules in graphs and lists.

[1041] Step 4: Emotion Recognition with the Emotion Engine

[1042] The emotion engine installed in the device analyzes facial expressions, tone of voice, input content, etc. when the user confirms the treatment plan, and generates emotion data.

[1043] Step 5: Submit a feedback form

[1044] The terminal provides a form where doctors and patients can enter feedback on the treatment plan, and the emotion engine also captures emotional data when the feedback is entered.

[1045] Step 6: Resend your feedback

[1046] The device sends the collected feedback and emotional data to a server, which uses this data to generate the next treatment plan.

[1047] User Action

[1048] Step 1: Review your treatment plan

[1049] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[1050] Step 2: Implementing the treatment plan

[1051] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. Doctors can check on the device whether the patient is following the plan.

[1052] Step 3: Provide feedback

[1053] The user (patient) records the progress of treatment and changes in their physical condition on the device. The emotion engine also collects emotional data obtained during this input. The doctor provides feedback to evaluate the effectiveness of treatment based on the patient's data.

[1054] Step 4: Adjusting your treatment plan

[1055] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1056] The above are the specific processing steps for implementing the present invention. This system provides personalized medical care optimized for each patient and realizes effective treatment that takes into account the user's emotions.

[1057] Example 2

[1058] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1059] Conventional medical systems lack the data analysis necessary to generate personalized treatment plans for each patient, resulting in ineffective treatment. Furthermore, because they do not take the patient's emotions into consideration, it is difficult to implement treatment plans, leading to a decline in the patient's motivation to receive treatment.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1061] In this invention, the server includes a means for collecting patient data, a means for preprocessing the collected patient data, a means for analyzing the preprocessed patient data, a means for generating an individualized treatment plan using a generating AI algorithm, and a means for encrypting the generated treatment plan and transmitting it to a terminal via data communication. This allows for a highly individualized treatment plan to be provided for each patient, and also enables the generation of a treatment plan that takes into account the patient's emotional data.

[1062] "Patient data" refers to data including information such as a patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[1063] "Preprocessing" refers to the process of interpolating or removing incomplete data or outliers from collected data and converting it into a standard format.

[1064] "Analysis" refers to performing statistical analysis and feature extraction on preprocessed data and analyzing it using generative AI algorithms.

[1065] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on patient data.

[1066] "Treatment plan" refers to a specific treatment method for each patient, including diet, exercise program, and drug therapy.

[1067] "Encryption" refers to the conversion of data using encryption techniques to securely communicate the generated treatment plan.

[1068] "Data communication" is the process of sending encrypted data over a network to a terminal.

[1069] A "terminal" is a device that is accessed by patients and doctors and has the function of visually displaying the received treatment plan and collecting feedback.

[1070] The "emotion engine" is an engine that analyzes the user's facial expressions and tone of voice to generate emotion data.

[1071] "Feedback" refers to information provided by doctors and patients regarding treatment plans, such as their opinions, progress, and changes in physical condition.

[1072] "Resubmit" refers to sending the collected feedback and emotion data to the server.

[1073] This invention is a system that analyzes patient data and generates personalized treatment plans. It also combines an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[1074] Server Processing

[1075] The server accesses electronic medical record systems and wearable devices to collect real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. To do this, data is securely acquired using the FHIR (Fast Healthcare Interoperability Resources) protocol, and data is acquired from wearable devices via Bluetooth or Wi-Fi. The collected data is first cleaned, and incomplete data and outliers are interpolated or removed, and then converted into a standard format. Here, a data frame is created using the Python Pandas library and the cleaning process is performed.

[1076] The preprocessed data is then analyzed using a generative AI algorithm. The AI ​​module uses Pytorch and TensorFlow to analyze the patient's genetic information and lifestyle characteristics. Statistical analysis is performed using SciPy and NumPy to statistically evaluate various health indicators. Based on the results of this analysis, a personalized treatment plan is generated that combines diet, exercise programs, and medication. This treatment plan is encrypted using AES encryption technology and securely transmitted to the device using the Transport Layer Security (TLS) protocol.

[1077] Terminal handling

[1078] The device receives and decrypts the encrypted data sent from the server. This is done using a private key stored on the device and a Python cryptography library. The decrypted treatment plan is then stored in association with the patient's account. The stored treatment plan is visually displayed in a web interface using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules.

[1079] Additionally, the device is equipped with an emotion engine to recognize the user's emotions. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through the camera and microphone. This data is analyzed using an emotion analysis library (e.g., DeepFace or OpenCV). The feedback and emotion data collected from the doctor and patient are again AES encrypted and sent to the server.

[1080] User Action

[1081] The user (doctor) checks the personalized treatment plan displayed on the device and makes adjustments as necessary. For example, when changing the dosage of medication, the user inputs the dosage into the interface on the device. The user (patient) follows the treatment plan displayed on the device and carries out daily diet and exercise. The exercise program includes video links of specific exercises, which the user follows.

[1082] The user (patient) inputs the progress of treatment and changes in physical condition via a terminal. These inputs are analyzed by the emotion engine, and emotional data is collected at the same time. For example, negative emotional data is sent along with feedback such as "Today's exercise was tough." The server analyzes the collected feedback and emotional data to further optimize the next treatment plan. The new treatment plan is then sent back to the terminal and provided to the user.

[1083] Specific examples

[1084] For example, a 40-year-old male patient is diagnosed with diabetes. Using this system, the server collects the patient's blood glucose level, food records, and exercise data from electronic medical records and wearable devices. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan that combines dietary therapy, exercise programs, and drug therapy. This treatment plan is then encrypted and sent to the device.

[1085] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[1086] Prompt Sentence Examples

[1087] "We want to generate personalized treatment plans based on patient data obtained from electronic medical records and wearable devices. We want to use an emotion engine to analyze the patient's emotional data and reflect it in the treatment plan."

[1088] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1089] Step 1:

[1090] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. This data collection uses the FHIR protocol and Bluetooth or Wi-Fi. Data is collected from each device and stored on the server. Input data includes raw data from electronic medical records and wearable devices, and data stored on the server is output.

[1091] Step 2:

[1092] The server performs preprocessing on the collected data. This includes cleaning the data. Specifically, it interpolates or removes incomplete data and outliers, and converts the data into a standard format. It uses the Python Pandas library to create a data frame and performs the cleaning process. The input data is the collected raw data, and the preprocessed, clean data is output.

[1093] Step 3:

[1094] The server analyzes the preprocessed data. The analysis involves extracting the patient's genetic information and lifestyle characteristics using Pytorch and TensorFlow. It then performs statistical analysis using SciPy and NumPy. This process extracts health indicators and trends. The input data is the preprocessed data, and the output is the analysis results.

[1095] Step 4:

[1096] The server uses a generative AI algorithm based on the analysis results to generate a personalized treatment plan. This treatment plan includes dietary therapy, exercise program, and drug therapy. The AI ​​algorithm generates the optimal plan based on past data and analysis results. The analysis results are used as input data, and the generated treatment plan is output.

[1097] Step 5:

[1098] The server encrypts the generated treatment plan and sends it to the terminal using the TLS protocol. The data is securely protected using AES encryption technology. The generated treatment plan is the input data, and the encrypted data is output and sent to the terminal.

[1099] Step 6:

[1100] The device receives the encrypted data sent from the server and decrypts it using a private key stored on the device and the Python cryptography library. The input data is the encrypted data, and the output is the decrypted treatment plan.

[1101] Step 7:

[1102] The device associates the decrypted treatment plan with the patient's account, stores it, and visually displays it using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules. The decrypted treatment plan is the input data, and the visually displayed treatment plan is the output.

[1103] Step 8:

[1104] The device uses an emotion engine to analyze the user's emotional data. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through a camera and microphone, and analyzes them using an emotion analysis library (DeepFace or OpenCV). The input data is facial expression data and tone of voice, and the output is emotional data.

[1105] Step 9:

[1106] The device collects feedback and emotion data from doctors and patients, re-encrypts it, and sends it to the server. The collected feedback and emotion data is AES encrypted and securely transmitted using the TLS protocol. The input data is feedback and emotion data, and the encrypted data is output and sent to the server.

[1107] Step 10:

[1108] The server analyzes the collected feedback and emotion data and reflects it in the generation of the next treatment plan, thereby providing a more effective and personalized treatment plan. The input data are feedback and emotion data, and the output is the analysis results and an improved treatment plan.

[1109] (Application example 2)

[1110] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1111] In the current medical system, patients' emotional state is not taken into account when generating personalized treatment plans, which can affect treatment effectiveness. It is also difficult for doctors and nurses to grasp a patient's emotional state in real time, making it difficult to optimize treatment plans. Another problem is that emotional data is not properly reflected in the process of collecting feedback on patient treatment plans.

[1112] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting patient data, means for pre-processing the collected patient data, means for analyzing the pre-processed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to the terminal via data communication, means for analyzing collected user emotion data, and means for reflecting the analyzed emotion data in the treatment plan. This makes it possible to collect patient emotion data in real time and appropriately adjust the treatment plan based on the feedback.

[1113] "Patient data" refers to data that includes medical information such as the patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise.

[1114] "Preprocessing" refers to processes such as cleaning the collected data, interpolating, removing outliers, and converting it to a standard format.

[1115] "Analysis" refers to the statistical analysis of genetic information, environmental factors, and lifestyle data to extract characteristics.

[1116] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on collected data.

[1117] "Data communication" is a means of sending and receiving data using the Internet or dedicated lines.

[1118] The "emotion engine" is a system that generates emotion data from the user's facial expressions, tone of voice, etc.

[1119] A "treatment plan" is a personalized medical plan that may include diet, exercise program, medication, etc.

[1120] A "terminal" is an electronic device such as a smartphone, tablet, or smart glasses.

[1121] "Feedback" is information about the effectiveness of the treatment plan and the patient's emotional state.

[1122] "Collection" refers to the process or means of gathering data.

[1123] "Visual display" means displaying data in an easy-to-read manner on a screen or display.

[1124] This invention is a system that analyzes patient data and generates personalized treatment plans. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[1125] Server Processing

[1126] Data collection and preprocessing

[1127] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[1128] Data analysis and treatment plan generation

[1129] The pre-processed data is then analyzed by a generative AI algorithm. The server extracts genetic information, environmental factors, and lifestyle characteristics and performs statistical analysis. Based on the results of this analysis, an optimized treatment plan is generated for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[1130] data communication

[1131] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[1132] Terminal handling

[1133] Data reception and display

[1134] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[1135] Emotion engine processing

[1136] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice when inputting feedback, and generates emotion data. This emotion engine collects and analyzes the user's emotion data using the camera and microphone of the smart glasses.

[1137] Feedback collection and resubmission

[1138] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[1139] User Action

[1140] Review and implement treatment plans

[1141] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[1142] Providing Feedback

[1143] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[1144] Adjusting your treatment plan

[1145] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1146] Specific examples

[1147] For example, a clinic will incorporate smart glasses into the treatment plan for diabetic patients. When a patient comes to the clinic, the doctor will check the patient's current treatment plan through the smart glasses and collect emotional data in real time. If the patient expresses dissatisfaction with the diet, the emotion engine will detect this and send it to the server. The doctor will then adjust the treatment plan to find a more suitable approach for the patient.

[1148] Prompt Sentence Examples

[1149] "Enter patient feedback and collect data. The emotion engine uses the camera and microphone in the smart glasses to analyze the patient's facial expressions and tone of voice. Send the acquired emotion data and feedback on the effectiveness of the treatment plan to the server."

[1150] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1151] Step 1:

[1152] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format, resulting in accurate and consistent data.

[1153] Input: Patient data from electronic medical record systems and wearable devices

[1154] Output: Cleaned and converted data into a standard format

[1155] Step 2:

[1156] The server then analyzes the pre-processed data using a generative AI algorithm, extracting genetic information, environmental factors, and lifestyle characteristics and conducting statistical analysis. Based on the results of this analysis, a personalized treatment plan is generated.

[1157] Input: Preprocessed patient data

[1158] Output: personalized treatment plan

[1159] Step 3:

[1160] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol, ensuring the safety of patient data.

[1161] Input: personalized treatment plan

[1162] Output: Encrypted treatment plan

[1163] Step 4:

[1164] The device receives and decrypts the treatment plan sent from the server, which is then stored in association with the patient's account and displayed in a visually accessible format (e.g., lists and graphs of dietary menus, exercise programs, and medication schedules).

[1165] Input: Encrypted treatment plan

[1166] Output: Visually displayed treatment plan

[1167] Step 5:

[1168] The emotion engine installed in the device uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice to generate emotion data, allowing the device to grasp their emotional state in real time.

[1169] Input: User's facial expression, tone of voice

[1170] Output: Generated emotion data

[1171] Step 6:

[1172] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[1173] Input: Doctor and patient feedback, sentiment data

[1174] Output: Feedback and emotion data sent to the server

[1175] Step 7:

[1176] The user (doctor) uses the device to review the patient's personalized treatment plan and make adjustments as needed, using emotional data and feedback to evaluate the effectiveness of the treatment plan and select a more appropriate treatment method for the patient.

[1177] Input: Treatment plan, emotional data, feedback

[1178] Output: Tailored treatment plan

[1179] Step 8:

[1180] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1181] Input: Feedback, emotion data

[1182] Output: Improved treatment plan

[1183] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1184] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1185] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1186] [Fourth embodiment]

[1187] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1188] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1189] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1190] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1191] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1192] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1193] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1194] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1195] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1196] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1197] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1198] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1199] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1200] The present invention relates to a system for generating personalized treatment plans. Specifically, it realizes highly accurate personalized medicine by linking together the elements of a server, terminal, and user, and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[1201] Server Processing

[1202] Data collection and preprocessing

[1203] The server collects patient data from electronic medical record systems and wearable devices. This includes basic patient data (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. The collected data is first cleaned, and incomplete or outliers are interpolated or removed. The data is then converted into a standard format.

[1204] Data analysis and treatment plan generation

[1205] The preprocessed data is then analyzed by the server. First, genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for the patient. This treatment plan includes dietary therapy, exercise programs, and drug therapy.

[1206] data communication

[1207] The generated treatment plan is encrypted and sent to the device using a secure communication protocol to ensure confidentiality.

[1208] Terminal handling

[1209] Data reception and display

[1210] The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The device then displays the treatment plan in a visually easy-to-understand format. For example, daily meal plans and exercise programs can be presented in graphs or lists.

[1211] Feedback collection and resubmission

[1212] The device provides a form where doctors and patients can enter feedback about the treatment plan, which is then sent back to the server and used to improve the treatment plan.

[1213] User Action

[1214] Review and modify your treatment plan

[1215] The user (doctor) uses the device to check the patient's personalized treatment plan. If necessary, the doctor will suggest adjustments to the patient's diet or exercise program. The user (patient) checks the treatment plan on their own device and adjusts their lifestyle according to the instructions. Daily diet and exercise details are recorded on the device.

[1216] Evaluation of treatment effect

[1217] The user (doctor) evaluates the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[1218] Specific examples

[1219] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm generates a treatment plan that combines dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[1220] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal plan and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is retransmitted to the server. Based on the feedback, the doctor checks the effectiveness of the treatment plan and modifies it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[1221] The present invention is expected to realize personalized treatment for each patient, significantly improving the quality and effectiveness of medical care.

[1222] The processing flow will be explained below.

[1223] Server Processing

[1224] Step 1: Data collection

[1225] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood sugar level, and exercise volume from the wearable device worn by the patient.

[1226] Step 2: Data cleaning

[1227] The server detects incomplete or outliers from the collected data and performs appropriate interpolation or deletion to ensure the quality of the data.

[1228] Step 3: Data Standardization

[1229] The server converts the cleaned data into a standard format and stores it in a consistent format, facilitating subsequent analysis.

[1230] Step 4: Feature extraction

[1231] The server extracts key features from genetic information, environmental factors, and lifestyle data, including specific gene variants, living environment factors, and diet and exercise habits.

[1232] Step 5: Statistical analysis

[1233] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (for example, HbA1c value or BMI).

[1234] Step 6: Applying generative AI algorithms

[1235] Based on the results of statistical analysis and characteristic data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and medication.

[1236] Step 7: Encrypt and send your treatment plan

[1237] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol.

[1238] Terminal handling

[1239] Step 1: Receive and decrypt data

[1240] The terminal receives and decrypts the encrypted treatment plan sent from the server, making the treatment plan available on the terminal.

[1241] Step 2: Save your treatment plan

[1242] The device then associates the received treatment plan with the patient's account and stores it for future reference.

[1243] Step 3: Update the User Interface

[1244] The device displays the treatment plan in a visually easy-to-understand format, including diet menus, exercise plans, and medication schedules in graphs and lists.

[1245] Step 4: Submit a feedback form

[1246] The device provides a form where doctors and patients can enter feedback on the treatment plan, allowing the results of the treatment plan's application and areas for improvement to be collected.

[1247] Step 5: Resend your feedback

[1248] The device sends the collected feedback to a server, which uses this information to generate the next treatment plan.

[1249] User Action

[1250] Step 1: Review your treatment plan

[1251] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[1252] Step 2: Implementing the treatment plan

[1253] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. The user (doctor) checks whether the patient is following the plan.

[1254] Step 3: Provide feedback

[1255] The user (patient) records the progress of treatment and changes in physical condition on the device, and the user (doctor) provides feedback to evaluate the effectiveness of treatment based on the patient data.

[1256] Step 4: Adjusting your treatment plan

[1257] The user (doctor) modifies the treatment plan as needed based on the feedback and treatment data, and this new plan is provided to the patient again via the server and device.

[1258] The above are the specific processing steps for carrying out the present invention. This system makes it possible to efficiently realize precise personalized medicine optimized for each patient.

[1259] Example 1

[1260] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1261] Providing personalized medicine requires the effective collection and analysis of diverse patient data and the rapid generation of highly accurate treatment plans. However, conventional systems face many challenges, including data incompleteness and outliers, limitations in analytical methods, and the need to ensure secure data communication. In particular, there are issues with the standardization of data collected in different formats, the insufficient analysis of data in real time, and the insufficient security and feedback of generated treatment plans.

[1262] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1263] In this invention, the server includes a means for collecting patient data, a means for cleaning the collected patient data and converting it into a standard format, a means for extracting features from the preprocessed patient data and performing statistical analysis, a means for generating an individualized treatment plan using a generative AI algorithm based on the analysis results, and a means for encrypting the generated treatment plan and transmitting it to a terminal using a secure communication protocol, thereby enabling the generation of a treatment plan quickly and accurately while maintaining the integrity and security of the data.

[1264] "Patient data" refers to a set of data necessary to realize personalized medicine, including basic patient information (age, gender, medical history), real-time data such as heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[1265] The "cleaning means" refers to a process for completing or deleting incomplete data or abnormal values ​​from collected patient data, thereby improving the quality of the data.

[1266] "Means for converting to a standard format" refers to a means for converting patient data collected in different formats into a unified data format (e.g., CSV, JSON).

[1267] A "means for extracting features" is a means for extracting important data characteristics or patterns to be analyzed from collected and pre-processed patient data.

[1268] A "means for performing statistical analysis" is a means for performing data analysis using statistical methods based on patient data to derive meaningful information.

[1269] A "generative AI algorithm" is an algorithm that uses machine learning and natural language processing to generate an individualized treatment plan based on input data.

[1270] A "treatment plan" is a personalized medical plan that includes dietary therapy, exercise program, medication, etc., optimized based on patient data.

[1271] "Encryption means" refers to a means for encrypting data to protect the treatment plan from malicious third parties during data communication.

[1272] A "secure communications protocol" is a protocol (e.g., HTTPS, TLS) used to securely communicate data.

[1273] "Device" means a computer device (e.g., smartphone, tablet, PC) that patients and physicians access to view and enter data.

[1274] A "feedback tool" is a tool for collecting physician and patient opinions and evaluations of the treatment plan.

[1275] The "retransmission means" is a means for retransmitting collected feedback to the server and using it to improve the treatment plan.

[1276] This invention relates to a system for generating personalized treatment plans. Specifically, it is a system that realizes highly accurate personalized medicine by linking together the elements of a server, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[1277] Server Processing

[1278] The server first collects patient data from electronic medical record systems and wearable devices (e.g., Fitbit, Apple Watch). This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume. This data is obtained using APIs. For example, the OAuth 2.0 protocol is used to securely obtain the data.

[1279] The server then cleans the collected data, imputing or removing incomplete data and outliers using Python's Pandas library or R's dplyr package, and converts the data into a standard format (e.g., CSV, JSON) after importing it as a DataFrame.

[1280] The server performs feature extraction and statistical analysis based on the preprocessed data. Machine learning algorithms (e.g., PCA and clustering methods from scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python.

[1281] Based on the analysis results, a generative AI algorithm (e.g., GPT-4, BERT) generates an optimal treatment plan, which includes dietary therapy, exercise program, and medication. The generated treatment plan is saved in YAML or JSON format.

[1282] The server encrypts the stored treatment plan (e.g., AES-256) and transmits it to the terminal using a secure communication protocol (e.g., HTTPS, TLS).

[1283] Terminal handling

[1284] The device receives the treatment plan sent from the server and decrypts it. For example, it decrypts the data encrypted with AES-256 using a dedicated decryption key. The device then associates the decrypted treatment plan with the patient's account and stores it. This storage can be done using local storage or a database (e.g., SQLite, Firebase).

[1285] The saved treatment plan is displayed on the device in a visually easy-to-understand format (e.g., graph or list format). Visualization is achieved using front-end frameworks such as React or Flutter. For example, a daily meal plan or exercise program is displayed graphically.

[1286] The device also provides a form where doctors and patients can enter feedback on the treatment plan. The form is created using HTML and JavaScript. The feedback is collected and sent back to the server.

[1287] User Action

[1288] The user (doctor) uses the device to check the patient's treatment plan. For example, detailed plan information is visualized on a dashboard in the browser. The user (patient) also uses the device to check the treatment plan and adjust their daily life. The user (patient) records their daily diet and exercise details on the device, and this data is managed on the device.

[1289] Based on the collected feedback and recorded data, the user (doctor) evaluates the effectiveness of the treatment. Based on this evaluation, the effectiveness of the treatment plan can be confirmed and the plan can be revised if necessary. By repeating this process, the optimal personalized treatment can be provided to the patient.

[1290] Specific examples

[1291] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food records, and exercise data from the electronic medical record system and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI algorithm (e.g., GPT-4) generates a treatment plan that combines the optimal diet, exercise program, and drug therapy.

[1292] This treatment plan is encrypted and sent to the device. The device receives the treatment plan and displays it in a format that is easy for the patient and doctor to understand. The doctor and patient can then enter feedback on the treatment plan, and this information is sent back to the server. Based on the feedback, the doctor can modify the treatment plan and optimize it for further improvement, thereby continuously improving the patient's personalized treatment.

[1293] Example prompt

[1294] "Please explain the process for a 40-year-old male diabetic patient to generate a new treatment plan based on blood glucose, heart rate, and exercise data collected from a wearable device."

[1295] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1296] Step 1:

[1297] The server collects patient data from the electronic medical record system and wearable devices. As input, it uses the authentication information and query parameters of the electronic medical record system API and wearable device API. This allows the collection of basic patient information (age, gender, medical history) and real-time data (heart rate, blood glucose level, exercise amount). As output, it obtains the patient data in JSON format.

[1298] Step 2:

[1299] The server cleans the collected patient data and converts it into a standard format. It uses the JSON data obtained in step 1 as input. It uses the Python Pandas library to impute or remove incomplete data and outliers, and processes it as a DataFrame. The output is the cleaned data in a standard format (e.g., CSV, JSON).

[1300] Step 3:

[1301] The server extracts features from the preprocessed data and performs statistical analysis. The cleaned data obtained in step 2 is used as input. Machine learning algorithms (e.g., PCA and clustering methods in scikit-learn) are used to extract features from genetic information, environmental factors, and lifestyle data. Statistical analysis is performed using statistical libraries in R and Python. The output is the results of the feature extraction and statistical analysis.

[1302] Step 4:

[1303] The server generates a personalized treatment plan using a generative AI algorithm based on the analysis results. The analysis results obtained in step 3 are used as input. A generative AI algorithm (e.g., GPT-4, BERT) is used to generate a personalized treatment plan, including diet, exercise program, and medication. The output is a treatment plan in YAML or JSON format.

[1304] Step 5:

[1305] The server encrypts the generated treatment plan and sends it to the terminal using a secure communication protocol. The treatment plan obtained in step 4 is used as input. AES-256 is used for encryption, and HTTPS or TLS is used for data communication. The encrypted treatment plan data is sent to the terminal as output.

[1306] Step 6:

[1307] The device receives and decrypts the treatment plan sent from the server. As input, it receives encrypted data from the server. It uses a dedicated decryption key to decrypt the AES-256 encrypted data. As output, it obtains the decrypted treatment plan.

[1308] Step 7:

[1309] The device displays the received treatment plan in a visually easy-to-understand format. As input, it uses the decoded treatment plan obtained in step 6. It uses a front-end framework such as React or Flutter to graphically display the daily meal menu and exercise program. As output, the visualized treatment plan is provided to the user.

[1310] Step 8:

[1311] The terminal provides a form where doctors and patients can enter feedback on the treatment plan. As input, users' ratings and comments on the treatment plan are entered into the form. This feedback is sent to the server using JavaScript and HTML. As output, feedback data is obtained.

[1312] Step 9:

[1313] The user (doctor) uses a device to review the patient's treatment plan and make adjustments based on the feedback. As input, they use the treatment plan visualized in step 7 and the feedback collected in step 8. They adjust and modify the treatment plan and create a new one. As output, they obtain the modified treatment plan.

[1314] Step 10:

[1315] The user (patient) records their daily diet and exercise on a device. As input, they record their daily diet and exercise amount in the device's app. This allows daily lifestyle data to be managed. As output, the recorded lifestyle data is obtained.

[1316] (Application example 1)

[1317] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1318] In modern healthcare, efficiently delivering personalized treatment plans is a challenging task. Furthermore, systems that not only provide personalized treatment plans but also enable continuous feedback and adjustment of treatment are needed. It is also important to provide real-time health management content that is relevant to patients' daily lives. This will enable more accurate and effective treatment and improve patients' quality of life.

[1319] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1320] In this invention, the server includes means for collecting patient data, means for preprocessing the collected patient data, means for analyzing the preprocessed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to a terminal via data communication, and means for visually displaying the generated treatment plan, thereby enabling the generative AI model to analyze the patient data and provide personalized health content based on prompts.

[1321] This not only allows for efficient generation and delivery of personalized treatment plans, but also allows for feedback from doctors and patients to be collected and the treatment plans to be continuously improved based on that data. Furthermore, real-time data collected from wearable devices can be used to support daily health management, improving patients' quality of life.

[1322] "Patient Data" is information about a patient, including genetic information, environmental factors, lifestyle data, and real-time data from wearable devices.

[1323] "Preprocessing" is the process of cleaning collected patient data, interpolating or removing incomplete or outlier values, and converting it into a standard format.

[1324] "Analysis" refers to the means by which pre-processed patient data is used to extract features, perform statistical analysis, and generate personalized treatment plans.

[1325] A "personalized treatment plan" is a treatment and health management guideline optimized for a specific patient based on genetic information, environmental factors, lifestyle data, and analysis results.

[1326] A "generative AI model" is an artificial intelligence algorithm used to analyze patient data and generate a personalized treatment plan.

[1327] A "prompt" is a series of instructions or instructions entered into a generative AI model to operate it.

[1328] "Data communication" is the process of sending data from a server to a terminal or from a terminal to a server, using secure communication protocols such as encryption.

[1329] "Visually displaying" means displaying the generated treatment plan and feedback in a graphical format on a terminal.

[1330] "Feedback" refers to opinions and evaluations of the treatment plan provided by the doctor and patient, which are resubmitted and used to improve the treatment plan.

[1331] The present invention relates to a system for generating personalized treatment plans and providing them to doctors and patients. Specifically, the system realizes highly accurate personalized medicine by linking servers, terminals, and users and making advanced use of patient data such as genetic information, environmental factors, and lifestyle data.

[1332] Server Processing

[1333] The server performs the following process:

[1334] 1. Data collection: Collect patient data from electronic medical record systems and wearable devices. This data includes basic patient information (age, gender, medical history) and real-time data such as heart rate, blood glucose level, and exercise volume.

[1335] 2. Data preprocessing: The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[1336] 3. Data analysis and treatment plan generation: The pre-processed data is analyzed using a generative AI model. Genetic information, environmental factors, and lifestyle characteristics are extracted, followed by statistical analysis. Based on the results of this analysis, an optimized treatment plan (including diet, exercise program, and medication) is generated.

[1337] 4. Data communication: The generated treatment plan is encrypted and sent to the device using HTTPS and JSON Web Token (JWT) as secure communication protocols.

[1338] Terminal handling

[1339] The terminal performs the following process:

[1340] 1. Data reception and display: The device receives and decrypts the treatment plan sent from the server. The received treatment plan is stored in association with the patient's account. The treatment plan is then displayed in a visually easy-to-understand format (graph or list format).

[1341] 2. Feedback collection and resubmission: The terminal provides a form where doctors and patients can enter feedback on the treatment plan. The collected feedback is sent back to the server and used to improve the treatment plan.

[1342] User Action

[1343] Users (doctors and patients) perform the following processes:

[1344] 1. Review and modify treatment plan: The doctor uses the device to review the patient's personalized treatment plan. If necessary, the doctor will suggest dietary adjustments or changes to the exercise program. The patient will review the treatment plan on their own device and adjust their lifestyle accordingly. Daily diet and exercise information will be recorded on the device.

[1345] 2. Evaluation of treatment effectiveness: Doctors evaluate the effectiveness of treatment based on patient feedback and data recorded on the device. This evaluation determines the next treatment plan and allows for continuous improvement.

[1346] Technology used

[1347] The following technologies are used to realize this system:

[1348] Server: Amazon Web Services (AWS) or Microsoft Azure

[1349] Data analysis: Python, TensorFlow, scikit-learn

[1350] Frontend: React Native (for smartphone apps), Unity (for head-mounted displays)

[1351] Data collection: Bluetooth API (for integration with smartwatches and wearable devices)

[1352] Communication: HTTPS, JSON Web Token (JWT)

[1353] Specific examples

[1354] For example, consider a 40-year-old male patient diagnosed with diabetes. The server collects the patient's blood glucose level, food record, and exercise data from electronic medical records and wearable devices. The collected data is preprocessed, and feature extraction and statistical analysis are performed. Based on the analysis results, a generative AI model generates a treatment plan that combines a personalized diet, exercise program, and drug therapy. This treatment plan is encrypted and sent to the device.

[1355] The device receives the treatment plan and displays it in an easy-to-understand format for the patient and doctor. For example, a daily meal menu and exercise plan are displayed graphically. The doctor and patient then enter feedback on the treatment plan, and this information is resent to the server. Based on the feedback, the doctor can check the effectiveness of the treatment plan and modify it if necessary. By repeating this process, the optimal personalized treatment is provided to the patient.

[1356] Example prompt sentence:

[1357] "Patient data: Age (40), Gender (Male), Blood Glucose Level (120, 140, 150), Exercise Amount (5000, 7000, 8000) Generative AI Algorithm: Generate optimal diet plan, exercise program, and medication based on this data."

[1358] This will enable personalized treatment for each patient, and is expected to significantly improve the quality and effectiveness of medical care.

[1359] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1360] Step 1:

[1361] The server collects patient data from wearable devices and electronic medical record systems. Input data includes real-time data such as the patient's age, gender, medical history, heart rate, blood glucose level, and exercise volume. This allows a wide range of patient information to be captured by the server for preprocessing in the next step.

[1362] Step 2:

[1363] The server preprocesses the collected patient data. It cleans the input data, interpolates or removes incomplete or outliers, and converts it into a standard format. The data cleaning is performed using the Python pandas library, and an anomaly detection algorithm from scikit-learn is used to detect outliers. This results in high-quality data suitable for analysis.

[1364] Step 3:

[1365] The server analyzes the preprocessed data, extracting features related to genetic information, environmental factors, and lifestyle, and performing statistical analysis. Data analysis is performed using TensorFlow and the scikit-learn library. This allows for the extraction of features for each patient, and analysis results based on these features are obtained.

[1366] Step 4:

[1367] The server uses a generative AI model to generate an individualized treatment plan based on the analysis results. Specifically, it proposes dietary therapy, exercise programs, and drug therapy based on the input data and prompts. This results in a treatment plan optimized for each individual patient.

[1368] Step 5:

[1369] The server encrypts the generated treatment plan and sends it to the device. The encryption uses JSON Web Token (JWT) and HTTPS as the communication protocol, ensuring secure data transmission to the device.

[1370] Step 6:

[1371] The device receives and decrypts the transmitted treatment plan. The input data is the encrypted treatment plan, and the output is the decrypted treatment plan. This allows the data to be viewed on the device.

[1372] Step 7:

[1373] The device visually displays the treatment plan, specifically showing dietary menus and exercise programs in graph and list format. The user interface is implemented using React Native, allowing users to visually understand the plan.

[1374] Step 8:

[1375] Users (doctors and patients) enter feedback on the treatment plan into the terminal. The feedback data is collected through a form and resubmitted to the server in the next step. This allows information that reflects the actual treatment situation to be obtained.

[1376] Step 9:

[1377] The device then retransmits the collected feedback data to the server, where it is encrypted and securely transmitted to the server, where it is used to optimize the next treatment plan.

[1378] Step 10:

[1379] The server receives the feedback data again and uses it to generate the next treatment plan. By repeating the data preprocessing and analysis steps described above, the treatment plan is continuously improved based on the latest data, thereby providing the optimal treatment for the patient.

[1380] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1381] The present invention relates to a system that analyzes patient data and generates personalized treatment plans. Furthermore, the present invention relates to a system that incorporates an emotion engine that recognizes user emotions and reflects them in treatment plans. This system provides patients with optimized medical services through collaboration between the server, terminal, and user elements.

[1382] Server Processing

[1383] Data collection and preprocessing

[1384] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose level, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format.

[1385] Data analysis and treatment plan generation

[1386] The preprocessed data is analyzed by a server. Genetic information, environmental factors, and lifestyle characteristics are extracted and statistical analysis is performed. Based on the results of this analysis, a generative AI algorithm generates an optimized treatment plan for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[1387] data communication

[1388] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[1389] Terminal handling

[1390] Data reception and display

[1391] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[1392] Emotion engine processing

[1393] The device is also equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, tone of voice, and input content when entering feedback, and generates emotional data.

[1394] Feedback collection and resubmission

[1395] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[1396] User Action

[1397] Review and implement treatment plans

[1398] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[1399] Providing Feedback

[1400] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[1401] Adjusting your treatment plan

[1402] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1403] Specific examples

[1404] For example, if a 40-year-old male patient is diagnosed with diabetes, the server collects the patient's blood glucose level, food record, and exercise data from the electronic medical record and wearable device. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan combining dietary therapy, exercise program, and drug therapy. This treatment plan is then encrypted and sent to the device.

[1405] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[1406] The present invention is expected to realize personalized treatment for each patient and provide more effective and comfortable medical services by taking into consideration the patient's feelings.

[1407] The processing flow will be explained below.

[1408] Server Processing

[1409] Step 1: Data collection

[1410] The server retrieves basic patient data (age, gender, medical history) from the electronic medical record system, and also collects real-time data such as heart rate, blood glucose level, and exercise volume from the wearable device worn by the patient.

[1411] Step 2: Data cleaning

[1412] The server cleans the collected data, detecting incomplete or outliers and interpolating or removing them appropriately, thereby ensuring the quality of the data.

[1413] Step 3: Data Standardization

[1414] The server converts the cleaned data into a standard format, storing the data in a consistent format to facilitate subsequent analysis.

[1415] Step 4: Feature extraction

[1416] The server extracts key features from the patient's genetic information, environmental factors, and lifestyle data, such as specific gene polymorphisms, living environment factors, and dietary and exercise habits.

[1417] Step 5: Statistical analysis

[1418] The server performs statistical analysis using the feature-extracted data and calculates indicators for evaluating the patient's health condition (e.g., HbA1c value, BMI) from the analysis results.

[1419] Step 6: Applying generative AI algorithms

[1420] Based on the results of the statistical analysis and the extracted feature data, the server uses a generative AI algorithm to create a personalized treatment plan, which includes dietary therapy, exercise program, and drug therapy.

[1421] Step 7: Encrypt and send your treatment plan

[1422] The server encrypts the generated treatment plan and transmits it to the terminal using a secure communication protocol.

[1423] Terminal handling

[1424] Step 1: Receive and decrypt data

[1425] The device receives the encrypted treatment plan sent from the server and decrypts it, allowing the treatment plan to be displayed on the device.

[1426] Step 2: Save your treatment plan

[1427] The device then associates the received treatment plan with the patient's account and stores it, allowing the user to view the saved treatment plan at any time.

[1428] Step 3: Update the User Interface

[1429] The device displays the treatment plan in a visually easy-to-understand format, showing diet menus, exercise plans, and medication schedules in graphs and lists.

[1430] Step 4: Emotion Recognition with the Emotion Engine

[1431] The emotion engine installed in the device analyzes facial expressions, tone of voice, input content, etc. when the user confirms the treatment plan, and generates emotion data.

[1432] Step 5: Submit a feedback form

[1433] The terminal provides a form where doctors and patients can enter feedback on the treatment plan, and the emotion engine also captures emotional data when the feedback is entered.

[1434] Step 6: Resend your feedback

[1435] The device sends the collected feedback and emotional data to a server, which uses this data to generate the next treatment plan.

[1436] User Action

[1437] Step 1: Review your treatment plan

[1438] The user (doctor) checks the patient's personalized treatment plan through the terminal, and the user (patient) also checks their own treatment plan on the terminal.

[1439] Step 2: Implementing the treatment plan

[1440] The user (patient) follows the treatment plan displayed on the device and follows daily diet and exercise routines. Doctors can check on the device whether the patient is following the plan.

[1441] Step 3: Provide feedback

[1442] The user (patient) records the progress of treatment and changes in their physical condition on the device. The emotion engine also collects emotional data obtained during this input. The doctor provides feedback to evaluate the effectiveness of treatment based on the patient's data.

[1443] Step 4: Adjusting your treatment plan

[1444] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1445] The above are the specific processing steps for implementing the present invention. This system provides personalized medical care optimized for each patient and realizes effective treatment that takes into account the user's emotions.

[1446] Example 2

[1447] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1448] Conventional medical systems lack the data analysis necessary to generate personalized treatment plans for each patient, resulting in ineffective treatment. Furthermore, because they do not take the patient's emotions into consideration, it is difficult to implement treatment plans, leading to a decline in the patient's motivation to receive treatment.

[1449] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1450] In this invention, the server includes a means for collecting patient data, a means for preprocessing the collected patient data, a means for analyzing the preprocessed patient data, a means for generating an individualized treatment plan using a generating AI algorithm, and a means for encrypting the generated treatment plan and transmitting it to a terminal via data communication. This allows for a highly individualized treatment plan to be provided for each patient, and also enables the generation of a treatment plan that takes into account the patient's emotional data.

[1451] "Patient data" refers to data including information such as a patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise, as well as genetic information, environmental factors, and lifestyle data.

[1452] "Preprocessing" refers to the process of interpolating or removing incomplete data or outliers from collected data and converting it into a standard format.

[1453] "Analysis" refers to performing statistical analysis and feature extraction on preprocessed data and analyzing it using generative AI algorithms.

[1454] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on patient data.

[1455] "Treatment plan" refers to a specific treatment method for each patient, including diet, exercise program, and drug therapy.

[1456] "Encryption" refers to the conversion of data using encryption techniques to securely communicate the generated treatment plan.

[1457] "Data communication" is the process of sending encrypted data over a network to a terminal.

[1458] A "terminal" is a device that is accessed by patients and doctors and has the function of visually displaying the received treatment plan and collecting feedback.

[1459] The "emotion engine" is an engine that analyzes the user's facial expressions and tone of voice to generate emotion data.

[1460] "Feedback" refers to information provided by doctors and patients regarding treatment plans, such as their opinions, progress, and changes in physical condition.

[1461] "Resubmit" refers to sending the collected feedback and emotion data to the server.

[1462] This invention is a system that analyzes patient data and generates personalized treatment plans. It also combines an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[1463] Server Processing

[1464] The server accesses electronic medical record systems and wearable devices to collect real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. To do this, data is securely acquired using the FHIR (Fast Healthcare Interoperability Resources) protocol, and data is acquired from wearable devices via Bluetooth or Wi-Fi. The collected data is first cleaned, and incomplete data and outliers are interpolated or removed, and then converted into a standard format. Here, a data frame is created using the Python Pandas library and the cleaning process is performed.

[1465] The preprocessed data is then analyzed using a generative AI algorithm. The AI ​​module uses Pytorch and TensorFlow to analyze the patient's genetic information and lifestyle characteristics. Statistical analysis is performed using SciPy and NumPy to statistically evaluate various health indicators. Based on the results of this analysis, a personalized treatment plan is generated that combines diet, exercise programs, and medication. This treatment plan is encrypted using AES encryption technology and securely transmitted to the device using the Transport Layer Security (TLS) protocol.

[1466] Terminal handling

[1467] The device receives and decrypts the encrypted data sent from the server. This is done using a private key stored on the device and a Python cryptography library. The decrypted treatment plan is then stored in association with the patient's account. The stored treatment plan is visually displayed in a web interface using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules.

[1468] Additionally, the device is equipped with an emotion engine to recognize the user's emotions. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through the camera and microphone. This data is analyzed using an emotion analysis library (e.g., DeepFace or OpenCV). The feedback and emotion data collected from the doctor and patient are again AES encrypted and sent to the server.

[1469] User Action

[1470] The user (doctor) checks the personalized treatment plan displayed on the device and makes adjustments as necessary. For example, when changing the dosage of medication, the user inputs the dosage into the interface on the device. The user (patient) follows the treatment plan displayed on the device and carries out daily diet and exercise. The exercise program includes video links of specific exercises, which the user follows.

[1471] The user (patient) inputs the progress of treatment and changes in physical condition via a terminal. These inputs are analyzed by the emotion engine, and emotional data is collected at the same time. For example, negative emotional data is sent along with feedback such as "Today's exercise was tough." The server analyzes the collected feedback and emotional data to further optimize the next treatment plan. The new treatment plan is then sent back to the terminal and provided to the user.

[1472] Specific examples

[1473] For example, a 40-year-old male patient is diagnosed with diabetes. Using this system, the server collects the patient's blood glucose level, food records, and exercise data from electronic medical records and wearable devices. The emotion engine collects emotional data when the patient enters feedback and detects positive and negative emotions. The collected data is preprocessed, and after feature extraction and statistical analysis, the generative AI algorithm generates a treatment plan that combines dietary therapy, exercise programs, and drug therapy. This treatment plan is then encrypted and sent to the device.

[1474] The device receives the treatment plan and visually displays it to the patient and doctor. The emotion engine allows users to provide emotional data while reviewing the treatment plan. Doctors and patients input feedback on the treatment plan, which is sent to the server along with the emotional data. When the next treatment plan is generated, the emotional data is used to create a more effective plan that takes the patient's psychological state into account.

[1475] Prompt Sentence Examples

[1476] "We want to generate personalized treatment plans based on patient data obtained from electronic medical records and wearable devices. We want to use an emotion engine to analyze the patient's emotional data and reflect it in the treatment plan."

[1477] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1478] Step 1:

[1479] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. This data collection uses the FHIR protocol and Bluetooth or Wi-Fi. Data is collected from each device and stored on the server. Input data includes raw data from electronic medical records and wearable devices, and data stored on the server is output.

[1480] Step 2:

[1481] The server performs preprocessing on the collected data. This includes cleaning the data. Specifically, it interpolates or removes incomplete data and outliers, and converts the data into a standard format. It uses the Python Pandas library to create a data frame and performs the cleaning process. The input data is the collected raw data, and the preprocessed, clean data is output.

[1482] Step 3:

[1483] The server analyzes the preprocessed data. The analysis involves extracting the patient's genetic information and lifestyle characteristics using Pytorch and TensorFlow. It then performs statistical analysis using SciPy and NumPy. This process extracts health indicators and trends. The input data is the preprocessed data, and the output is the analysis results.

[1484] Step 4:

[1485] The server uses a generative AI algorithm based on the analysis results to generate a personalized treatment plan. This treatment plan includes dietary therapy, exercise program, and drug therapy. The AI ​​algorithm generates the optimal plan based on past data and analysis results. The analysis results are used as input data, and the generated treatment plan is output.

[1486] Step 5:

[1487] The server encrypts the generated treatment plan and sends it to the terminal using the TLS protocol. The data is securely protected using AES encryption technology. The generated treatment plan is the input data, and the encrypted data is output and sent to the terminal.

[1488] Step 6:

[1489] The device receives the encrypted data sent from the server and decrypts it using a private key stored on the device and the Python cryptography library. The input data is the encrypted data, and the output is the decrypted treatment plan.

[1490] Step 7:

[1491] The device associates the decrypted treatment plan with the patient's account, stores it, and visually displays it using a framework such as Django. The screen displays lists and graphs of meal plans, exercise programs, and medication schedules. The decrypted treatment plan is the input data, and the visually displayed treatment plan is the output.

[1492] Step 8:

[1493] The device uses an emotion engine to analyze the user's emotional data. When the user enters feedback into the treatment plan, the device collects facial expression data and tone of voice through a camera and microphone, and analyzes them using an emotion analysis library (DeepFace or OpenCV). The input data is facial expression data and tone of voice, and the output is emotional data.

[1494] Step 9:

[1495] The device collects feedback and emotion data from doctors and patients, re-encrypts it, and sends it to the server. The collected feedback and emotion data is AES encrypted and securely transmitted using the TLS protocol. The input data is feedback and emotion data, and the encrypted data is output and sent to the server.

[1496] Step 10:

[1497] The server analyzes the collected feedback and emotion data and reflects it in the generation of the next treatment plan, thereby providing a more effective and personalized treatment plan. The input data are feedback and emotion data, and the output is the analysis results and an improved treatment plan.

[1498] (Application example 2)

[1499] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1500] In the current medical system, patients' emotional state is not taken into account when generating personalized treatment plans, which can affect treatment effectiveness. It is also difficult for doctors and nurses to grasp a patient's emotional state in real time, making it difficult to optimize treatment plans. Another problem is that emotional data is not properly reflected in the process of collecting feedback on patient treatment plans.

[1501] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting patient data, means for pre-processing the collected patient data, means for analyzing the pre-processed patient data, means for generating an individualized treatment plan based on the analysis results, means for transmitting the generated treatment plan to the terminal via data communication, means for analyzing collected user emotion data, and means for reflecting the analyzed emotion data in the treatment plan. This makes it possible to collect patient emotion data in real time and appropriately adjust the treatment plan based on the feedback.

[1502] "Patient data" refers to data that includes medical information such as the patient's age, gender, medical history, heart rate, blood sugar level, and amount of exercise.

[1503] "Preprocessing" refers to processes such as cleaning the collected data, interpolating, removing outliers, and converting it to a standard format.

[1504] "Analysis" refers to the statistical analysis of genetic information, environmental factors, and lifestyle data to extract characteristics.

[1505] A "generative AI algorithm" is an algorithm that generates an individualized treatment plan based on collected data.

[1506] "Data communication" is a means of sending and receiving data using the Internet or dedicated lines.

[1507] The "emotion engine" is a system that generates emotion data from the user's facial expressions, tone of voice, etc.

[1508] A "treatment plan" is a personalized medical plan that may include diet, exercise program, medication, etc.

[1509] A "terminal" is an electronic device such as a smartphone, tablet, or smart glasses.

[1510] "Feedback" is information about the effectiveness of the treatment plan and the patient's emotional state.

[1511] "Collection" refers to the process or means of gathering data.

[1512] "Visual display" means displaying data in an easy-to-read manner on a screen or display.

[1513] This invention is a system that analyzes patient data and generates personalized treatment plans. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions and reflects them in the treatment plan. This system provides optimal medical services to patients through collaboration between the server, terminal, and user elements.

[1514] Server Processing

[1515] Data collection and preprocessing

[1516] The server collects real-time data such as basic patient data (age, gender, medical history), heart rate, blood glucose level, and exercise volume from electronic medical record systems and wearable devices. The collected data is first cleaned, and incomplete or outliers are interpolated or removed, and then converted into a standard format.

[1517] Data analysis and treatment plan generation

[1518] The pre-processed data is then analyzed by a generative AI algorithm. The server extracts genetic information, environmental factors, and lifestyle characteristics and performs statistical analysis. Based on the results of this analysis, an optimized treatment plan is generated for each patient. The plan includes dietary therapy, exercise program, and drug therapy.

[1519] data communication

[1520] The generated treatment plan is encrypted and sent to the device, using a secure communication protocol to protect the data.

[1521] Terminal handling

[1522] Data reception and display

[1523] The device receives and decrypts the treatment plan sent from the server, stores it in association with the patient's account, and displays it in a visually accessible format, including lists and graphs of dietary menus, exercise programs, and medication schedules.

[1524] Emotion engine processing

[1525] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice when inputting feedback, and generates emotion data. This emotion engine collects and analyzes the user's emotion data using the camera and microphone of the smart glasses.

[1526] Feedback collection and resubmission

[1527] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[1528] User Action

[1529] Review and implement treatment plans

[1530] The user (doctor) uses the device to check the patient's personalized treatment plan and make adjustments as necessary. The user (patient) follows the treatment plan displayed on the device and follows their daily diet and exercise routine.

[1531] Providing Feedback

[1532] When the user (patient) inputs information about the progress of treatment and changes in their physical condition via a terminal, emotional data is also collected by the emotion engine. The user (doctor) can use this data to evaluate the effectiveness of treatment and provide feedback.

[1533] Adjusting your treatment plan

[1534] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1535] Specific examples

[1536] For example, a clinic will incorporate smart glasses into the treatment plan for diabetic patients. When a patient comes to the clinic, the doctor will check the patient's current treatment plan through the smart glasses and collect emotional data in real time. If the patient expresses dissatisfaction with the diet, the emotion engine will detect this and send it to the server. The doctor will then adjust the treatment plan to find a more suitable approach for the patient.

[1537] Prompt Sentence Examples

[1538] "Enter patient feedback and collect data. The emotion engine uses the camera and microphone in the smart glasses to analyze the patient's facial expressions and tone of voice. Send the acquired emotion data and feedback on the effectiveness of the treatment plan to the server."

[1539] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1540] Step 1:

[1541] The server collects real-time data from electronic medical record systems and wearable devices, including basic patient information (age, gender, medical history), heart rate, blood glucose levels, and exercise volume. This data is first cleaned, with incomplete or outliers interpolated or removed, and then converted into a standard format, resulting in accurate and consistent data.

[1542] Input: Patient data from electronic medical record systems and wearable devices

[1543] Output: Cleaned and converted data into a standard format

[1544] Step 2:

[1545] The server then analyzes the pre-processed data using a generative AI algorithm, extracting genetic information, environmental factors, and lifestyle characteristics and conducting statistical analysis. Based on the results of this analysis, a personalized treatment plan is generated.

[1546] Input: Preprocessed patient data

[1547] Output: personalized treatment plan

[1548] Step 3:

[1549] The server encrypts the generated treatment plan and transmits it to the device using a secure communication protocol, ensuring the safety of patient data.

[1550] Input: personalized treatment plan

[1551] Output: Encrypted treatment plan

[1552] Step 4:

[1553] The device receives and decrypts the treatment plan sent from the server, which is then stored in association with the patient's account and displayed in a visually accessible format (e.g., lists and graphs of dietary menus, exercise programs, and medication schedules).

[1554] Input: Encrypted treatment plan

[1555] Output: Visually displayed treatment plan

[1556] Step 5:

[1557] The emotion engine installed in the device uses the smart glasses' camera and microphone to analyze the user's facial expressions and tone of voice to generate emotion data, allowing the device to grasp their emotional state in real time.

[1558] Input: User's facial expression, tone of voice

[1559] Output: Generated emotion data

[1560] Step 6:

[1561] The terminal collects emotional data along with feedback from the doctor and patient regarding the treatment plan, and the collected feedback and emotional data are retransmitted to the server.

[1562] Input: Doctor and patient feedback, sentiment data

[1563] Output: Feedback and emotion data sent to the server

[1564] Step 7:

[1565] The user (doctor) uses the device to review the patient's personalized treatment plan and make adjustments as needed, using emotional data and feedback to evaluate the effectiveness of the treatment plan and select a more appropriate treatment method for the patient.

[1566] Input: Treatment plan, emotional data, feedback

[1567] Output: Tailored treatment plan

[1568] Step 8:

[1569] The server analyzes the collected feedback and emotional data and uses a generative AI algorithm to refine the next treatment plan, which is then sent back to the device and provided to the user.

[1570] Input: Feedback, emotion data

[1571] Output: Improved treatment plan

[1572] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1573] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1574] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1575] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1576] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1577] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1578] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1579] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1580] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1581] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1582] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1583] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1584] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1585] 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.

[1586] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1587] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1588] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1589] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1590] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1591] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1592] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1593] The following is further disclosed regarding the above embodiment.

[1594] (Claim 1)

[1595] a means for collecting patient data;

[1596] a means for pre-processing the collected patient data;

[1597] means for analyzing the pre-processed patient data;

[1598] means for generating an individualized treatment plan based on the analysis results;

[1599] means for transmitting the generated treatment plan to a terminal via data communication;

[1600] A system including:

[1601] (Claim 2)

[1602] means for receiving and visually displaying the personalized treatment plan on a terminal;

[1603] a means for collecting physician and patient feedback from the device;

[1604] a means to resubmit collected feedback;

[1605] The system of claim 1 further comprising:

[1606] (Claim 3)

[1607] 10. The system of claim 1, wherein the collected patient data includes genetic information, environmental factors, and lifestyle data.

[1608] (Claim 4)

[1609] 10. The system of claim 1...

Claims

1. a means for collecting patient data; a means for pre-processing the collected patient data; means for analyzing the pre-processed patient data; means for generating an individualized treatment plan based on the analysis results; means for transmitting the generated treatment plan to a terminal via data communication; A system including:

2. means for receiving and visually displaying the personalized treatment plan on a terminal; a means for collecting physician and patient feedback from the device; a means to resubmit collected feedback; The system of claim 1 further comprising:

3. 10. The system of claim 1, wherein the collected patient data includes genetic information, environmental factors, and lifestyle data.

4. 10. The system of claim 1, wherein the analysis of the collected data includes statistical analysis and feature extraction.

5. The system of claim 1 , wherein the generated treatment plan includes a diet, an exercise program, and medication.

Images