system

Abstract

Provide a system. A means for inputting health information from a user; means for transmitting the input health information to a server; means for anonymizing and storing the received health information in a server; A method for analyzing health information stored on a server using an AI model; A means to identify optimal treatment options based on the analysis results and notify physicians; means for transmitting the results of the treatment performed by the doctor to the server again; A means for storing the resubmitted treatment results in a database and updating the AI ​​model; A system including:

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] In order to address the serious labor shortage in recent years, and to utilize the workforce, especially among the elderly, it is necessary to address health issues, but many elderly people have given up on employment due to health issues. To solve this problem, a system is needed that can identify appropriate treatments, improve the health status of elderly people, and provide them with opportunities to return to work. Another issue is the lack of support for doctors to optimize treatment methods based on data on past treatment success. [Means for solving the problem]

[0005] The present invention relates to a system that inputs health information from users, transmits the information to a server, anonymizes and stores it, and analyzes it using an AI model. Specifically, it includes the following means:

[0006] 1. A means for users to input health information

[0007] 2. Means for sending the entered health information to the server

[0008] 3. Means for anonymizing and storing the received health information on the server

[0009] 4. A method for analyzing health information stored on a server using an AI model

[0010] 5. A means to identify optimal treatment options based on analysis results and inform physicians

[0011] 6. Means for sending the results of treatment performed by the doctor back to the server

[0012] 7. A means to store resubmitted treatment results in a database and update the AI ​​model

[0013] This will effectively improve the user's health and promote re-employment for the elderly. It will also improve the quality of medical care by suggesting optimal treatments to doctors based on past treatment data.

[0014] A "user" is an individual or entity that uses the system, and in particular, is an entity that provides health information.

[0015] "Health information" is data relating to the user's health condition, including diagnosis results, treatment history, symptoms, and the like.

[0016] A "terminal" is a device that a user uses to input health information and send it to a server.

[0017] "Server" refers to a computer system that receives, anonymizes, stores, and analyzes health information using AI models.

[0018] An "AI model" is an analytical model that uses artificial intelligence technology to identify the optimal treatment method based on past treatment data.

[0019] "Analysis" is the process of using AI models to process health information and identify optimal treatments.

[0020] A "treatment" is a medical procedure that a doctor would administer to a patient and is recommended by an AI model.

[0021] "Anonymization" is the process of processing a user's personal information so that it cannot be identified, and is done to protect privacy.

[0022] "Database" means an information storage and management system installed on a server, where anonymized health information and treatment results are stored.

[0023] "Notification" refers to the act of the server communicating recommended treatments to a doctor.

[0024] "Treatment results" are data relating to the results of treatment performed by a doctor, and are sent back to the server.

[0025] "Storage" refers to the act of recording the health information and treatment results received by the server in a database.

[0026] "Update" is the process of adding and correcting the learning data of the AI ​​model based on newly obtained treatment results. [Brief explanation of the drawings]

[0027] [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

[0028] 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.

[0029] First, the terms used in the following description will be explained.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] [First embodiment]

[0036] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0037] 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.

[0038] 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).

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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."

[0048] System Overview:

[0049] This invention relates to an AI analysis system that inputs health information and proposes treatment methods. This system includes processes such as anonymizing and storing the health information entered by the user, identifying appropriate treatment methods using an AI model, notifying doctors, and finally using the treatment results for further analysis.

[0050] System configuration:

[0051] The system includes the following means:

[0052] 1. User's device

[0053] 2. Server

[0054] 3. AI Model

[0055] 4. Database

[0056] System behavior:

[0057] When a user enters health information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device back to the server. The server stores the newly obtained treatment results in a database and updates the AI ​​model, improving the accuracy of the next analysis.

[0058] What the program does:

[0059] Entering and submitting health information:

[0060] A user uses a device to input health information such as diagnosis results, symptoms, and treatment history. The input information is encrypted and sent to a server. For example, Mr. Tanaka complains of knee pain and inputs the details into the device.

[0061] Anonymization and storage of information:

[0062] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[0063] Analysis by AI model:

[0064] The data stored on the server is analyzed by an AI model, which uses past treatment data to identify the best treatment based on the health information entered. For example, the AI ​​model identifies successful treatments from similar cases to recommend an effective treatment for knee pain.

[0065] Notification of recommended treatment:

[0066] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan, enabling the doctor to provide optimal treatment efficiently.

[0067] Treatment result feedback:

[0068] The doctor performs the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results.

[0069] Data update and training:

[0070] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[0071] Examples:

[0072] User inputs knee pain

[0073] Tanaka enters details about his knee pain into the device and sends them to the server.

[0074] Anonymization and Analysis of Information

[0075] The server anonymizes the information it receives, stores it in a database, and then analyzes it using an AI model to identify the best treatment for knee pain based on past successful treatments.

[0076] Notification of recommended treatment

[0077] The doctor in charge will be notified of the identified treatment, and the doctor will plan and implement the treatment.

[0078] Treatment result feedback

[0079] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[0080] Through this series of processes, the system will effectively improve the user's health, support doctors' treatment, and contribute to resolving the labor shortage problem in society as a whole.

[0081] The processing flow will be explained below.

[0082] Step 1:

[0083] The user enters health information from the device. The user accurately fills in the input form with their symptoms, diagnosis results, treatment history, etc. The entered information includes specific descriptions of symptoms and past diagnosis information.

[0084] Step 2:

[0085] The device sends the entered health information to the server. The device encrypts the health information to ensure safe transmission, and then sends the data to the server via the Internet.

[0086] Step 3:

[0087] The server anonymizes the received health information. The server removes personally identifiable information from the received data to generate anonymized data.

[0088] Step 4:

[0089] The server stores the de-identified data in a database, where the de-identified health information is securely recorded and available for subsequent analysis.

[0090] Step 5:

[0091] The server inputs the health information stored in the database into the AI ​​model for analysis. The server supplies the health information to the AI ​​model, which then analyzes the optimal treatment based on past data.

[0092] Step 6:

[0093] The server notifies the doctor of the optimal treatment identified by the AI ​​model, and then sends the analysis results to the doctor's dedicated device, where the doctor receives the information.

[0094] Step 7:

[0095] The doctor will carry out treatment based on the recommended treatment. The doctor will refer to the treatment method notified by the server and plan and carry out specific treatment for the patient.

[0096] Step 8:

[0097] The doctor sends the treatment results from the device to the server. After the treatment is completed, the doctor records the results in detail and reports them to the server using the device.

[0098] Step 9:

[0099] The server stores the received treatment results in a database. Newly obtained treatment results are recorded in the database and are used again as learning data for the AI ​​model.

[0100] Step 10:

[0101] The server updates the AI ​​model based on the latest treatment results stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the quality of subsequent analyses.

[0102] Through this series of steps, the system can effectively manage users' health information and provide doctors with optimal treatment methods, thereby helping users solve their health problems and contributing to alleviating the labor shortage.

[0103] Example 1

[0104] 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."

[0105] Conventional health information analysis systems often lack sufficient protection of the privacy of input information, accuracy of analysis, and re-learning capabilities. Furthermore, they lack the ability to identify effective treatments and provide prompt feedback on the results. This results in inefficient medical support for users and a heavy burden on medical professionals. Furthermore, input information and treatment results are not encrypted, posing a risk of information leaks.

[0106] 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.

[0107] In this invention, the server includes a means for encrypting health information and treatment results sent from the user terminal, a means for anonymizing and storing the received health information, and a means for identifying the optimal treatment based on the analysis results and notifying medical professionals. This ensures privacy protection and enables improved analysis accuracy and rapid treatment identification using AI models. Furthermore, feedback on treatment results advances learning throughout the system, further improving the accuracy of the next analysis.

[0108] 1. "User" refers to the individual or group of people who input health information into the system.

[0109] 2. "Health Information" means data about a user's body, such as diagnostic results, symptoms, and treatment history.

[0110] 3. "Server" refers to the computer system that receives, processes, stores, and analyzes health information sent by users.

[0111] 4. "Anonymization" refers to the process of removing or transforming personally identifiable information so that it can no longer be used to identify the original individual.

[0112] 5. "Storage" means the act of recording received health information and treatment results in a database.

[0113] 6. "Artificial intelligence model" refers to an algorithm that learns from past data and makes predictions and analyses on new data.

[0114] 7. “Analysis” refers to the process of using artificial intelligence models to process input data and derive meaningful results.

[0115] 8. "Therapy" means a medical procedure or method of treatment for a specific health problem.

[0116] 9. "Notification" refers to the act of notifying a specific person or system of analysis results or important information.

[0117] 10. "Healthcare professional" refers to a medical professional, such as a doctor or nurse, who has the qualifications and knowledge to diagnose and treat.

[0118] 11. "Feedback" means the act of re-entering the results and evaluation of treatment into the system to help improve it next time.

[0119] 12. "Encryption" refers to the process of converting data into a form that is unreadable to third parties using a specific key.

[0120] 13. "Database" means a system that can systematically collect, store, manage, and search multiple data.

[0121] The present invention relates to a system that inputs health information, analyzes it, and proposes optimal treatments. This system is composed of a series of processes including users, terminals, servers, artificial intelligence models, and databases.

[0122] First, the user uses the device to input their own health information. The input information includes diagnosis results, symptoms, treatment history, etc. The device then encrypts this information using encryption technology such as AES (Advanced Encryption Standard) and securely transmits it to the server.

[0123] The server anonymizes the received health information. Specifically, it converts the information into a format that does not allow the original individual to be identified by deleting elements that could identify the individual and assigning an anonymization ID. The anonymized information is then stored as is in a database. This database can be, for example, a system such as MySQL (registered trademark).

[0124] The server then retrieves the anonymized data stored in the database and inputs it into an artificial intelligence model, which is built using the Python libraries Tensorflow® and PyTorch, and performs analysis based on past treatment data. The analysis results in the identification of the optimal treatment method.

[0125] The server then notifies the medical professional in charge of the AI ​​model's analysis results via email or a dedicated application, and the medical professional uses the recommended treatment to create a specific treatment plan.

[0126] After the treatment is performed, the medical professional will provide feedback on the treatment results to the server via the device. The device will then re-encrypt this feedback information and send it to the server. The server will then store the treatment results in a database and update the AI ​​model. This will allow the new data to be reflected in the next analysis, improving analysis accuracy.

[0127] As a concrete example, consider the case where a user complains of knee pain. Detailed information about the knee pain is entered into a device and sent to a server. The server anonymizes and stores the information, then analyzes it using an artificial intelligence model to identify the optimal treatment. The analysis results are then notified to the doctor in charge, who then administers the treatment. The treatment results are then fed back to the server, and the entire system continues to learn, improving the accuracy of the next analysis.

[0128] Examples of prompts for a generative AI model might include:

[0129] "Query the AI ​​model for the success rate of a treatment for a 50-year-old man complaining of knee pain."

[0130] "The AI ​​model proposes a list of treatments that have improved knee pain."

[0131] "An AI model identifies optimal treatment options based on past successful knee pain treatments."

[0132] In this way, the system can effectively improve the health status of users and provide valuable support for medical professionals.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1:

[0135] Entering and submitting health information

[0136] User: Enters health information. Specifically, the user enters symptoms, diagnosis, and treatment history into the device. For example, the user enters details of knee pain.

[0137] Terminal: The entered information is encrypted using AES and sent to the server.

[0138] Input: Health information provided by the user.

[0139] Output: Encrypted health information.

[0140] Step 2:

[0141] Anonymization and storage of information

[0142] Server: Anonymizes the received health information by removing any personal identifying information and assigning an anonymized ID.

[0143] Server: The anonymized information is stored in a database, for example a MySQL database.

[0144] Input: Encrypted health information.

[0145] Output: Anonymized data.

[0146] Step 3:

[0147] Analysis using AI models

[0148] Server: Retrieves anonymized data stored in a database and inputs it into an artificial intelligence model.

[0149] AI models, using TensorFlow and PyTorch to perform analysis and generate optimal treatment recommendations, for example, identifying the best treatment for knee pain.

[0150] Input: De-identified health information.

[0151] Output: Treatment recommendations as a result of the analysis.

[0152] Step 4:

[0153] Notification of recommended treatment

[0154] Server: Receives the analysis results of the AI ​​model and notifies the medical professional in charge via email or a dedicated application.

[0155] Input: Analysis results.

[0156] Output: Notification to medical professionals.

[0157] Step 5:

[0158] Treatment result feedback

[0159] Medical professionals: record the results of the treatments performed on a dedicated form.

[0160] On the device: Form entry information is encrypted and sent to the server.

[0161] Input: Treatment results.

[0162] Output: Encrypted treatment results.

[0163] Step 6:

[0164] Data Update and Training

[0165] Server: Receives the encrypted treatment results and stores them in a database.

[0166] Server: Updates the AI ​​model based on treatment results to improve the accuracy of the next analysis.

[0167] Input: Treatment results.

[0168] Output: The updated AI model.

[0169] Each step of this system works to appropriately process the input data and ultimately improve the user's health and provide effective support to medical professionals.

[0170] (Application example 1)

[0171] 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."

[0172] Conventional medical systems have difficulty efficiently collecting and analyzing users' health information and providing optimal treatment. Furthermore, follow-up after treatment is insufficient, especially regarding self-care. This has made continuous health management and providing optimal treatment methods challenging.

[0173] 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.

[0174] In this invention, the server includes means for inputting health information from a user, means for transmitting the input health information to the server, means for anonymizing and storing the received health information in the server, means for analyzing the health information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, means for storing the retransmitted treatment results in a database and updating the AI ​​model, means for selecting an optimal video based on the health information and delivering it to a user terminal, means for inputting feedback after watching the video, and means for further improving the accuracy of the AI ​​model based on the input feedback. This makes it possible to provide individually customized treatments and self-care information based on the user's health information.

[0175] "Health information" refers to data relating to a user's personal health, such as diagnostic results, symptoms, and treatment history.

[0176] A "server" is a computer system that receives, stores, processes, and transmits data over a network.

[0177] "Anonymization" is the process of removing or masking personally identifiable information to protect an individual's privacy.

[0178] "Storage" is the act of recording and safely storing data.

[0179] An "AI model" is an algorithm that has been trained to perform a specific task using artificial intelligence techniques.

[0180] "Analysis" is the process of extracting information from input data and deriving results.

[0181] A "treatment" is a medical procedure or method for solving or improving a user's health problem.

[0182] "Notification" is the act of communicating information or results to other systems or people.

[0183] "Feedback" is information about opinions and results provided by users.

[0184] "Video" is visual content that combines a series of images.

[0185] "Distribution" is the act of transmitting digital content to users over a network.

[0186] A "terminal" is a device that a user directly operates to input and receive information.

[0187] "Encryption" is a technology that converts data to keep it secure and prevents unauthorized access.

[0188] The present invention is a system that collects health information from a user and uses an AI model to suggest optimal treatments and self-care information based on that information. Specific embodiments for carrying out the present invention will be described in detail below.

[0189] System configuration

[0190] This system is realized by combining the following hardware and software elements.

[0191] 1. User Device

[0192] Input and output devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs).

[0193] 2. Server

[0194] A computer system equipped with a high-performance processor and large-capacity storage device. Cloud services such as AWS (registered trademark) (Amazon Web Services) and GCP (Google (registered trademark) Cloud Platform) can also be used.

[0195] 3. AI Model

[0196] Models trained using machine learning libraries such as TensorFlow and PyTorch analyze a user's health information and recommend optimal treatments.

[0197] 4. Database

[0198] A relational database system, such as MongoDB or MySQL, to securely store anonymized health information and treatment results.

[0199] System Operation

[0200] Entering health information

[0201] Users input their own health information using devices such as smartphones or HMDs, for example, recording detailed symptoms such as knee pain or stiff shoulders, diagnosis results, and treatment history.

[0202] Transmission and anonymization of information

[0203] Health information entered from the device is sent to a server, which then anonymizes the information and stores it in a database while protecting the user's privacy.

[0204] Analysis using AI models

[0205] The data stored on the server is analyzed by an AI model, which uses past treatment data to recommend the optimal treatment and fitness videos for the entered health information.

[0206] Selection and distribution of recommended videos

[0207] Based on the analysis results, videos on optimal training and self-care are selected and delivered to the user's device. For example, a stretching video to relieve knee pain may be suggested.

[0208] Treatment results and feedback

[0209] After the user watches the recommended videos and performs training, the results are input as feedback from the device to the server, which then stores the newly obtained feedback in a database and updates the AI ​​model to improve its accuracy.

[0210] Specific examples

[0211] Example 1: When a user complains of knee pain and inputs it into the system, the AI ​​model uses past data to suggest the optimal stretching method and delivers a training video.

[0212] Example 2: If a user feels stiff shoulders, the system will select the optimal massage method and self-care video and provide it to the user.

[0213] Prompt Sentence Examples

[0214] If a user types in knee pain, recommend the best treatment based on past data. Select training videos to relieve knee pain and provide their URLs.

[0215] This allows users to obtain optimal treatment and self-care information according to their individual health conditions, enabling continuous health management.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] Input: The user inputs health information such as knee pain using a device such as a smartphone or HMD.

[0219] Processing: The device collects the information entered by the user and performs encryption processing before sending the data to the server. Encryption uses encryption technology such as AES (Advanced Encryption Standard).

[0220] Output: Encrypted health information is generated and sent to the server.

[0221] Step 2:

[0222] Input: The server that receives the encrypted health information.

[0223] Processing: The server decrypts the encrypted information and anonymizes it by removing any personally identifiable information. Anonymization may include removing identifiers and / or masking the data.

[0224] Output: De-identified health information is generated and stored in a database.

[0225] Step 3:

[0226] Input: De-identified health information stored in a database.

[0227] Processing: The server inputs the stored health information into an AI model for analysis. The AI ​​model, pre-trained using TensorFlow, recommends optimal treatments and self-care methods based on past treatment data.

[0228] Output: The analysis identifies optimal treatments and fitness videos.

[0229] Step 4:

[0230] Input: Analysis results identified by the AI ​​model.

[0231] Processing: The server automatically selects the appropriate video based on the analysis results and generates its URL. The video selection involves comparing metadata and tagging content.

[0232] Output: A URL for the selected video is generated.

[0233] Step 5:

[0234] Input: Server-generated video URL.

[0235] Process: The server delivers the video URL to the user's device, securely using the HTTPS protocol.

[0236] Output: The video URL is displayed on the user's device.

[0237] Step 6:

[0238] Input: User watches videos and performs training on device.

[0239] Processing: After completing the training, the user inputs their feedback into the terminal. The feedback includes the effectiveness of the training and their impressions.

[0240] Output: Feedback data is generated and sent to the server.

[0241] Step 7:

[0242] Input: Feedback data submitted by the user.

[0243] Processing: The server analyzes the received feedback data and stores it in a database. The AI ​​model is updated based on the stored feedback to improve accuracy. An online learning algorithm is used for updating.

[0244] Output: An updated AI model is generated and used for the next analysis.

[0245] These steps enable the present invention to provide personalized treatment and self-care information based on the user's health information.

[0246] 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.

[0247] System Overview:

[0248] This invention relates to an AI analysis system that inputs a user's health and emotional information, performs rigorous analysis, and provides optimal treatment methods. In addition to conventional health information processing, this system incorporates an emotion engine to provide treatment methods that take the user's emotional state into consideration.

[0249] System configuration:

[0250] The system includes the following means:

[0251] 1. User's device

[0252] 2. Server

[0253] 3. AI Model

[0254] 4. Emotion Engine

[0255] 5. Database

[0256] System behavior:

[0257] When a user enters health and emotional information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health and emotional information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device to the server again. The server stores the newly obtained treatment results in a database and updates the AI ​​model, improving the accuracy of the next analysis.

[0258] What the program does:

[0259] Entering and sending health and emotional information:

[0260] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information that is analyzed using the emotion engine. The input information is encrypted and sent to the server. For example, Mr. Tanaka complains of knee pain and inputs the details of the pain and anxiety he feels during treatment into the device.

[0261] Anonymization and storage of information:

[0262] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[0263] Analysis by AI model:

[0264] The data stored on the server is analyzed by an AI model. Based on past treatment data and emotional data, the AI ​​model identifies the optimal treatment method based on the input health and emotional information. For example, if a user is feeling anxious about knee pain, the AI ​​model will recommend the optimal method, including treatment to alleviate that anxiety.

[0265] Notification of recommended treatment:

[0266] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan. This allows the doctor to provide efficient treatment that takes into account the user's health and emotional information.

[0267] Treatment result feedback:

[0268] The doctor administers the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results and changes in his / her emotions.

[0269] Data update and training:

[0270] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[0271] Examples:

[0272] The user inputs knee pain and emotion data.

[0273] Tanaka enters details about his knee pain into the device and sends them to the server, while also inputting his own anxiety using the emotion engine.

[0274] Anonymization and Analysis of Information

[0275] The server anonymizes the information it receives and stores it in a database, after which it analyzes it using an AI model. Based on past successful treatments, it recommends a combination of the best treatment for knee pain and anxiety relief.

[0276] Notification of recommended treatment

[0277] The identified treatment will be notified to the doctor in charge, who will plan and implement the treatment. The doctor will also take into account the emotional information provided and take an appropriate approach to Mr. Tanaka.

[0278] Treatment result feedback

[0279] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[0280] Through this process, the system effectively manages the user's health and emotional state and provides optimal treatment methods, improving the user's overall quality of life and contributing to alleviating labor shortages.

[0281] The processing flow will be explained below.

[0282] Step 1:

[0283] The user inputs health and emotional information from a terminal. The user fills out an input form with their symptoms, diagnosis results, treatment history, and emotional state (e.g., anxiety, joy, anger, etc.). The emotion engine analyzes the user's emotional information in real time and assists in the input.

[0284] Step 2:

[0285] The device sends the entered health and emotional information to a server, which encrypts all data and transmits it to the server using a secure protocol.

[0286] Step 3:

[0287] The server anonymizes the health and emotional information it receives. The server then runs a process to remove personally identifiable information and de-identify the data. The resulting anonymous data is managed in a manner that protects the user's privacy.

[0288] Step 4:

[0289] The server stores the anonymized health and emotional information in a database, where it securely records the information for future analysis.

[0290] Step 5:

[0291] The server inputs the health and emotional information stored in the database into the AI ​​model for analysis. The server utilizes past treatment data and emotional data to perform analysis to identify the most appropriate treatment method for the user's symptoms. The AI ​​model then proposes the optimal treatment, taking into account both the user's health and emotional state.

[0292] Step 6:

[0293] The server notifies the doctor of the optimal treatment identified by the AI ​​model. The server then sends the analysis results to the doctor's dedicated device, where the doctor receives the information. The doctor then formulates a recommended treatment plan, taking into account the user's health and emotional information.

[0294] Step 7:

[0295] The doctor will then carry out treatment based on the recommended treatment. The doctor will plan and carry out specific treatment based on the treatment method and emotional information notified by the server. For example, the doctor will combine standard treatment for knee pain with counseling to alleviate the user's anxiety.

[0296] Step 8:

[0297] The doctor sends the treatment results and changes in the user's emotions from the device to the server. After the treatment is completed, the doctor records the treatment results and the user's emotional state in detail and reports them to the server using the device.

[0298] Step 9:

[0299] The server stores the received treatment results and emotion data in a database. Newly obtained treatment results and emotion data are recorded in the database and will be used for the next analysis.

[0300] Step 10:

[0301] The server updates the AI ​​model based on the latest treatment results and emotion data stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the accuracy of subsequent analyses.

[0302] Through these steps, the system will manage the user's health and emotional information in an advanced manner and provide the most appropriate treatment method quickly and effectively, thereby contributing to resolving the user's health problems and thereby helping to resolve the labor shortage problem in society as a whole.

[0303] Example 2

[0304] 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."

[0305] Conventional health information processing systems have had the challenge of making it difficult to provide treatment methods that take into account the user's psychological state. They also required comprehensive management, including anonymizing received information, securely storing data, and updating AI models to improve analysis accuracy. This resulted in problems that prevented users from fully improving their satisfaction and improving medical efficiency.

[0306] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting health information and emotional information from a user, means for transmitting the input health information and emotional information to the server, means for anonymizing and storing the received health information and emotional information, means for analyzing the health information and emotional information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, and means for storing the retransmitted treatment results in a database and updating the AI ​​model. This makes it possible to comprehensively manage the user's health condition and emotional information and provide an optimal treatment with improved analysis accuracy.

[0307] "Health information" is a general term for medical data such as a user's diagnosis, symptoms, and treatment history.

[0308] "Emotional information" is a general term for data relating to the user's psychological state and emotional fluctuations.

[0309] A "terminal" is an electronic device used by a user to input information, such as a smartphone or a personal computer.

[0310] A "server" is a central processing unit that receives information sent from a user and processes it, such as storing, analyzing, and notifying users.

[0311] "Anonymization" is a process to protect personal information by removing elements that can identify individuals from received information.

[0312] A "database" is an information storage system for safely storing anonymized information and treatment results.

[0313] An "AI model" is an artificial intelligence algorithm that analyzes past data and identifies the optimal treatment method.

[0314] "Analysis results" refers to the optimal treatment methods and recommendations obtained after the AI ​​model analyzes the input data.

[0315] "Notification" refers to the act of transmitting the analysis results from the server to the attending physician.

[0316] "Treatment results" refers to data that records the effects of treatment administered by a doctor and changes in the user's condition.

[0317] "Encryption" is a technology that converts information into a specific code to transmit it securely and prevent unauthorized access.

[0318] The present invention involves inputting a user's health and emotional information, sending it to a server, and analyzing the anonymized information with an AI model to identify the optimal treatment and notify the doctor. The treatment results are then sent back to the server, stored in a database, and the AI ​​model is updated to improve the system's analytical accuracy.

[0319] Enter and submit information

[0320] Users input their own health and emotional information using devices such as smartphones or PCs. Health information includes diagnosis results, symptoms, and treatment history, while emotional information includes psychological state analyzed using an emotion engine. Once the user has completed input, the information is encrypted and sent to the server.

[0321] Examples:

[0322] Mr. Tanaka complains of knee pain, enters detailed information about the pain and his anxiety during treatment into the terminal, and sends it.

[0323] Anonymization and storage of information

[0324] The information received by the server is anonymized by removing any personally identifiable information. This anonymized information is then stored in a highly secure database, ensuring the protection of personal information.

[0325] Analysis using AI models

[0326] The server retrieves the stored health and emotional information and inputs it into an AI model, which analyzes past treatment data and emotional data to identify the optimal treatment method. This AI model uses machine learning libraries such as TensorFlow and PyTorch.

[0327] Examples:

[0328] Data on Tanaka's knee pain and anxiety will be provided to the AI, which will analyze and identify the optimal treatment and anxiety relief methods.

[0329] Notification of recommended treatment

[0330] The server notifies the doctor of the analysis results, who then uses the results to create a specific treatment plan and provide the treatment to the user.

[0331] Treatment outcome feedback and updates

[0332] The doctor performs the treatment and sends the results from the device to the server. The treatment results are then anonymized again and stored in a database. Furthermore, this new treatment data is used to update the AI ​​model, improving the accuracy of the analysis the next time.

[0333] Specific examples of prompts to input to generative AI models

[0334] Below is an example of a prompt sentence to input to the generative AI model.

[0335] "A user enters data on their knee pain and anxiety via a device. Please explain in detail the process by which this information is anonymized, fed into an AI model to analyze the optimal treatment, and then communicates the results to the doctor."

[0336] This invention takes into account the user's psychological state and provides optimal treatment, thereby increasing user satisfaction and improving the quality of medical care. Furthermore, continuous data updates can improve analysis accuracy, which is expected to have long-term medical effects.

[0337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0338] Step 1:

[0339] The user inputs health and emotional information

[0340] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information. This input data is collected as text and numerical data based on the device's input form. Once input is complete, the data is sent by pressing the send button to proceed to the next step.

[0341] Input: Diagnosis results, symptoms, treatment history, emotional information (text and numerical data)

[0342] Output: Data submitted from the input form

[0343] Specific actions: For example, if Tanaka enters details of his knee pain and anxiety, he will enter data such as "Right knee pain, level 7 (out of 10)" and "Anxiety about treatment level 3 (out of 5)" into the terminal form.

[0344] Step 2:

[0345] The device sends the input information to the server

[0346] The device encrypts the health and emotional information entered by the user and sends it to the server using an encryption algorithm such as AES.

[0347] Input: Health and emotional information entered by the user

[0348] Output: Encrypted data

[0349] Specific operation: Tanaka's input data is AES encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0350] Step 3:

[0351] The server anonymizes the information

[0352] The server decrypts the encrypted data it receives, removes any personally identifiable information, and anonymizes it, assigning it a new unique ID.

[0353] Input: Encrypted user data

[0354] Output: Anonymized data

[0355] Specific operation: After Tanaka's data is decrypted, specific personal information such as name and address is removed and it is saved in the format "User ID: 12345".

[0356] Step 4:

[0357] The server stores the anonymized information in a database

[0358] The anonymized data is stored in a highly secure database, which is implemented using SQL and NoSQL technologies.

[0359] Input: Anonymized data

[0360] Output: Data stored in the database

[0361] Specific operation: Anonymized data on Tanaka's knee pain and anxiety is stored in an "anonymous database."

[0362] Step 5:

[0363] The server inputs the data into the AI ​​model

[0364] The server extracts the necessary patient information from the database and inputs it into the AI ​​model, which uses machine learning libraries such as TensorFlow and PyTorch.

[0365] Input: De-identified data extracted from the database

[0366] Output: Data input into the AI ​​model

[0367] Specific operation: Data on Tanaka's knee pain and anxiety is input into the AI ​​model by the server.

[0368] Step 6:

[0369] AI models analyze data and identify optimal treatment options

[0370] The AI ​​model uses deep learning techniques to analyze past treatment data and emotional data to identify the optimal treatment method.

[0371] Input: Data fed into the AI ​​model

[0372] Output: Recommendation of optimal treatment method

[0373] Specific operation: The AI ​​model analyzes Tanaka's data and outputs the result, "Knee treatment: physical therapy, emotional relaxation method: cognitive behavioral therapy."

[0374] Step 7:

[0375] The server notifies the doctor of the analysis results

[0376] The server then notifies the doctor of the analysis results via email or a dedicated medical application.

[0377] Input: Analysis results of the AI ​​model

[0378] Output:Notify doctor

[0379] Specific operation: The server sends the results of Tanaka's optimal treatment to his doctor via email.

[0380] Step 8:

[0381] The doctor administers the treatment

[0382] The doctor in charge will then provide treatment to the user based on the analysis results after receiving the notification, and treatment methods such as physical therapy or counseling will be selected.

[0383] Input: Treatment notified by the server

[0384] Output: Treatment performed

[0385] Specific action: The doctor will administer physical therapy and cognitive behavioral therapy to Tanaka.

[0386] Step 9:

[0387] The doctor sends the treatment results from the device to the server.

[0388] The doctor enters the treatment results into the terminal, encrypts them, and sends them to the server, again using an encryption algorithm such as AES.

[0389] Input: Treatment results

[0390] Output: Encrypted treatment outcome data

[0391] Specific operation: The doctor enters Tanaka's treatment results into the terminal and sends the AES-encrypted data to the server.

[0392] Step 10:

[0393] The server stores the treatment results in a database and updates the AI ​​model.

[0394] The server receives and anonymizes the treatment results, stores them in a database, and updates the AI ​​model based on this new data.

[0395] Input: Encrypted treatment outcome data

[0396] Output: De-identified treatment outcome data, updated AI model

[0397] Specific operation: Tanaka's treatment result data is anonymized and stored in a database, and the AI ​​model is retrained with new data.

[0398] (Application example 2)

[0399] 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."

[0400] Conventional medical systems identify treatment options based solely on the user's health information, making it difficult to provide optimal treatment and dietary recommendations that reflect the user's emotional state. Furthermore, there was no system that effectively collected users' treatment results and dietary feedback and quickly reflected the results in collaboration with food delivery services. This resulted in a lack of tools to improve users' overall health and quality of life.

[0401] The identification processing by the identification 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 inputting health information and emotional information from a user; means for transmitting the input health information and emotional information to the server; means for anonymizing and storing the received health information and emotional information in the server; means for analyzing the health information and emotional information stored in the server using an AI model; means for identifying optimal treatments and dietary suggestions based on the analysis results and notifying the doctor and the user; means for retransmitting the results of the treatment performed by the doctor and the user's dietary feedback information to the server; means for storing the retransmitted treatment results and dietary feedback information in a database and updating the AI ​​model; and means for coordinating with a food delivery service to make dietary suggestions available for immediate ordering. This enables integrated management of a user's health condition and emotional information, enabling the provision of more accurate treatments and individually optimized meals.

[0402]

[0403] "Health information" refers to medical data such as a user's diagnosis results, treatment history, and allergy information.

[0404] "Emotional information" refers to data related to the user's feelings, such as stress, anxiety, and joy.

[0405] "Server" refers to the database and computing device that stores the health and emotional information received from the user and analyzes it using the AI ​​model.

[0406] An "AI model" is a computational model that uses artificial intelligence and refers to an algorithm that analyzes a user's health and emotional information and derives optimal treatment and dietary suggestions.

[0407] "Anonymization" refers to the process of removing personally identifiable information from received data to protect the privacy of that data.

[0408] "Treatment" refers to a specific medical procedure that a doctor performs based on the user's health condition.

[0409] "Dietary suggestions" refers to the dietary and nutritional intake plans that the AI ​​model recommends to the user based on the analysis results.

[0410] "Notification" refers to the act of informing a user or a doctor of analysis results or suggestions.

[0411] "Feedback information" refers to information reported by a user as a result of the treatment or diet they have undertaken.

[0412] "Food delivery service" refers to a company or system that provides a service of quickly delivering meals specified by a user.

[0413] "Encryption processing" refers to a technology that encodes data to keep it confidential and prevent it from being leaked to third parties.

[0414]

[0415] The present invention is a system for proposing optimal treatments and diets based on a user's health information and emotional information. Specific embodiments of the present invention will be described below.

[0416] Hardware and software used

[0417] User device: A smartphone is used by the user to input health and emotional information.

[0418] Server: Uses cloud servers for data storage and processing.

[0419] Database: Firebase is used to store health and emotional information.

[0420] AI model: Use TensorFlow or PyTorch to analyze the data.

[0421] Emotion Engine: Uses Affectiva SDK to analyze user emotional information.

[0422] System Operation

[0423] 1. Enter your information:

[0424] Users input health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.) through a smartphone app, which then sends this information to a server.

[0425] 2. Transmission and storage of information:

[0426] The server anonymizes the health and emotional information received from the user and stores it securely in Firebase.

[0427] 3. Analysis by AI model:

[0428] The server retrieves the data stored in Firebase and analyzes it using TensorFlow or PyTorch-based AI models. Based on the analysis results, it generates optimal treatment and dietary recommendations for the user.

[0429] 4. Notification of results and collaboration:

[0430] The server then sends the analysis results to the user and their doctor via push notification. The server also works with food delivery services to provide meal suggestions, allowing users to instantly order the suggested menu items.

[0431] 5. Gather feedback and update the model:

[0432] After the user has eaten, they enter their feedback into the app. This feedback information is sent back to the server and stored in Firebase. The server uses this information to update the AI ​​model and improve its accuracy in the future.

[0433] Specific examples

[0434] For example, a user can input health information such as "I've been feeling tired and unmotivated lately," and also emotional information such as "I'm under a lot of stress at work." The AI ​​model analyzes this information and suggests relaxing herbal teas and meals rich in B vitamins to highly stressed users. This allows the user to receive push notifications suggesting the most suitable meals, which can then be instantly ordered through a delivery service.

[0435] Prompt Sentence Examples

[0436] "I've been suffering from a lack of sleep and am in a mentally unstable state. Please suggest some meals that will replenish my energy and help me relax."

[0437] "I haven't been exercising much lately, so my appetite has decreased. Could you recommend some foods that are easy to digest and gentle on the body?"

[0438] This system enables the integrated management of a user's health status and emotional information, and provides highly accurate treatments and individually optimized diets.

[0439] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0440]

[0441] Step 1: Enter your information

[0442] The user launches the smartphone app and inputs health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.). This information is structured in JSON format and sent to the server via the app. For example, a user might input health information such as "I've been feeling tired and unmotivated lately" and emotional information such as "I'm under a lot of stress at work."

[0443] Step 2: Send and save information

[0444] The health and emotional information sent from the device is received by a server. The server anonymizes the received information by removing any personally identifiable elements. The anonymized data is then stored in Firebase. Examples of input data include "feeling tired, high stress."

[0445] Step 3: Analysis by AI model

[0446] The server retrieves health and emotional information stored in Firebase and inputs it into a TensorFlow or PyTorch-based AI model. The AI ​​model analyzes this data and generates treatment and dietary recommendations that are optimal for the user's condition. For example, it might recommend relaxing herbal teas or meals rich in B vitamins.

[0447] Step 4: Notification of results and collaboration

[0448] The server sends the analysis results generated by the AI ​​model to the user and doctor via push notification. It also works with food delivery services to provide meal suggestions, making the suggested menu items instantly available for ordering. A specific example of a notification might include a recommendation for a relaxing herbal tea and a meal rich in B vitamins.

[0449] Step 5: Gather feedback

[0450] After the user orders and consumes the suggested meal, they enter their feedback through a smartphone app, such as "The herbal tea had a relaxing effect."

[0451] Step 6: Update the model

[0452] The feedback information sent from the device is received by the server and stored in Firebase. The server uses this feedback information to update the AI ​​model and improve the accuracy of future suggestions, thereby continuously improving the entire system.

[0453] 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.

[0454] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0455] 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.

[0456] [Second embodiment]

[0457] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0458] 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.

[0459] 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).

[0460] 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.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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."

[0469] System Overview:

[0470] This invention relates to an AI analysis system that inputs health information and proposes treatment methods. This system includes processes such as anonymizing and storing the health information entered by the user, identifying appropriate treatment methods using an AI model, notifying doctors, and finally using the treatment results for further analysis.

[0471] System configuration:

[0472] The system includes the following means:

[0473] 1. User's device

[0474] 2. Server

[0475] 3. AI Model

[0476] 4. Database

[0477] System behavior:

[0478] When a user enters health information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device back to the server. The server stores the newly obtained treatment results in a database and updates the AI ​​model, improving the accuracy of the next analysis.

[0479] What the program does:

[0480] Entering and submitting health information:

[0481] A user uses a device to input health information such as diagnosis results, symptoms, and treatment history. The input information is encrypted and sent to a server. For example, Mr. Tanaka complains of knee pain and inputs the details into the device.

[0482] Anonymization and storage of information:

[0483] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[0484] Analysis by AI model:

[0485] The data stored on the server is analyzed by an AI model, which uses past treatment data to identify the best treatment based on the health information entered. For example, the AI ​​model identifies successful treatments from similar cases to recommend an effective treatment for knee pain.

[0486] Notification of recommended treatment:

[0487] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan, enabling the doctor to provide optimal treatment efficiently.

[0488] Treatment result feedback:

[0489] The doctor performs the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results.

[0490] Data update and training:

[0491] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[0492] Examples:

[0493] User inputs knee pain

[0494] Tanaka enters details about his knee pain into the device and sends them to the server.

[0495] Anonymization and Analysis of Information

[0496] The server anonymizes the information it receives, stores it in a database, and then analyzes it using an AI model to identify the best treatment for knee pain based on past successful treatments.

[0497] Notification of recommended treatment

[0498] The doctor in charge will be notified of the identified treatment, and the doctor will plan and implement the treatment.

[0499] Treatment result feedback

[0500] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[0501] Through this series of processes, the system will effectively improve the user's health, support doctors' treatment, and contribute to resolving the labor shortage problem in society as a whole.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] The user enters health information from the device. The user accurately fills in the input form with their symptoms, diagnosis results, treatment history, etc. The entered information includes specific descriptions of symptoms and past diagnosis information.

[0505] Step 2:

[0506] The device sends the entered health information to the server. The device encrypts the health information to ensure safe transmission, and then sends the data to the server via the Internet.

[0507] Step 3:

[0508] The server anonymizes the received health information. The server removes personally identifiable information from the received data to generate anonymized data.

[0509] Step 4:

[0510] The server stores the de-identified data in a database, where the de-identified health information is securely recorded and available for subsequent analysis.

[0511] Step 5:

[0512] The server inputs the health information stored in the database into the AI ​​model for analysis. The server supplies the health information to the AI ​​model, which then analyzes the optimal treatment based on past data.

[0513] Step 6:

[0514] The server notifies the doctor of the optimal treatment identified by the AI ​​model, and then sends the analysis results to the doctor's dedicated device, where the doctor receives the information.

[0515] Step 7:

[0516] The doctor will carry out treatment based on the recommended treatment. The doctor will refer to the treatment method notified by the server and plan and carry out specific treatment for the patient.

[0517] Step 8:

[0518] The doctor sends the treatment results from the device to the server. After the treatment is completed, the doctor records the results in detail and reports them to the server using the device.

[0519] Step 9:

[0520] The server stores the received treatment results in a database. Newly obtained treatment results are recorded in the database and are used again as learning data for the AI ​​model.

[0521] Step 10:

[0522] The server updates the AI ​​model based on the latest treatment results stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the quality of subsequent analyses.

[0523] Through this series of steps, the system can effectively manage users' health information and provide doctors with optimal treatment methods, thereby helping users solve their health problems and contributing to alleviating the labor shortage.

[0524] Example 1

[0525] 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."

[0526] Conventional health information analysis systems often lack sufficient protection of the privacy of input information, accuracy of analysis, and re-learning capabilities. Furthermore, they lack the ability to identify effective treatments and provide prompt feedback on the results. This results in inefficient medical support for users and a heavy burden on medical professionals. Furthermore, input information and treatment results are not encrypted, posing a risk of information leaks.

[0527] 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.

[0528] In this invention, the server includes a means for encrypting health information and treatment results sent from the user terminal, a means for anonymizing and storing the received health information, and a means for identifying the optimal treatment based on the analysis results and notifying medical professionals. This ensures privacy protection and enables improved analysis accuracy and rapid treatment identification using AI models. Furthermore, feedback on treatment results advances learning throughout the system, further improving the accuracy of the next analysis.

[0529] 1. "User" refers to the individual or group of people who input health information into the system.

[0530] 2. "Health Information" means data about a user's body, such as diagnostic results, symptoms, and treatment history.

[0531] 3. "Server" refers to the computer system that receives, processes, stores, and analyzes health information sent by users.

[0532] 4. "Anonymization" refers to the process of removing or transforming personally identifiable information so that it can no longer be used to identify the original individual.

[0533] 5. "Storage" means the act of recording received health information and treatment results in a database.

[0534] 6. "Artificial intelligence model" refers to an algorithm that learns from past data and makes predictions and analyses on new data.

[0535] 7. “Analysis” refers to the process of using artificial intelligence models to process input data and derive meaningful results.

[0536] 8. "Therapy" means a medical procedure or method of treatment for a specific health problem.

[0537] 9. "Notification" refers to the act of notifying a specific person or system of analysis results or important information.

[0538] 10. "Healthcare professional" refers to a medical professional, such as a doctor or nurse, who has the qualifications and knowledge to diagnose and treat.

[0539] 11. "Feedback" means the act of re-entering the results and evaluation of treatment into the system to help improve it next time.

[0540] 12. "Encryption" refers to the process of converting data into a form that is unreadable to third parties using a specific key.

[0541] 13. "Database" means a system that can systematically collect, store, manage, and search multiple data.

[0542] The present invention relates to a system that inputs health information, analyzes it, and proposes optimal treatments. This system is composed of a series of processes including users, terminals, servers, artificial intelligence models, and databases.

[0543] First, the user uses the device to input their own health information. The input information includes diagnosis results, symptoms, treatment history, etc. The device then encrypts this information using encryption technology such as AES (Advanced Encryption Standard) and securely transmits it to the server.

[0544] The server anonymizes the received health information. Specifically, it deletes elements that could identify individuals and assigns an anonymization ID, converting the information into a format that does not allow the original individual to be identified. The anonymized information is then stored as is in a database. This database can be a system such as MySQL.

[0545] The server then takes the anonymized data stored in the database and feeds it into an artificial intelligence model, built using the Python libraries TensorFlow and PyTorch, which analyzes the patient's past treatment data to identify the most appropriate treatment.

[0546] The server then notifies the medical professional in charge of the AI ​​model's analysis results via email or a dedicated application, and the medical professional uses the recommended treatment to create a specific treatment plan.

[0547] After the treatment is performed, the medical professional will provide feedback on the treatment results to the server via the device. The device will then re-encrypt this feedback information and send it to the server. The server will then store the treatment results in a database and update the AI ​​model. This will allow the new data to be reflected in the next analysis, improving analysis accuracy.

[0548] As a concrete example, consider the case where a user complains of knee pain. Detailed information about the knee pain is entered into a device and sent to a server. The server anonymizes and stores the information, then analyzes it using an artificial intelligence model to identify the optimal treatment. The analysis results are then notified to the doctor in charge, who then administers the treatment. The treatment results are then fed back to the server, and the entire system continues to learn, improving the accuracy of the next analysis.

[0549] Examples of prompts for a generative AI model might include:

[0550] "Query the AI ​​model for the success rate of a treatment for a 50-year-old man complaining of knee pain."

[0551] "The AI ​​model proposes a list of treatments that have improved knee pain."

[0552] "An AI model identifies optimal treatment options based on past successful knee pain treatments."

[0553] In this way, the system can effectively improve the health status of users and provide valuable support for medical professionals.

[0554] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0555] Step 1:

[0556] Entering and submitting health information

[0557] User: Enters health information. Specifically, the user enters symptoms, diagnosis, and treatment history into the device. For example, the user enters details of knee pain.

[0558] Terminal: The entered information is encrypted using AES and sent to the server.

[0559] Input: Health information provided by the user.

[0560] Output: Encrypted health information.

[0561] Step 2:

[0562] Anonymization and storage of information

[0563] Server: Anonymizes the received health information by removing any personal identifying information and assigning an anonymized ID.

[0564] Server: The anonymized information is stored in a database, for example a MySQL database.

[0565] Input: Encrypted health information.

[0566] Output: Anonymized data.

[0567] Step 3:

[0568] Analysis using AI models

[0569] Server: Retrieves anonymized data stored in a database and inputs it into an artificial intelligence model.

[0570] AI models, using TensorFlow and PyTorch to perform analysis and generate optimal treatment recommendations, for example, identifying the best treatment for knee pain.

[0571] Input: De-identified health information.

[0572] Output: Treatment recommendations as a result of the analysis.

[0573] Step 4:

[0574] Notification of recommended treatment

[0575] Server: Receives the analysis results of the AI ​​model and notifies the medical professional in charge via email or a dedicated application.

[0576] Input: Analysis results.

[0577] Output: Notification to medical professionals.

[0578] Step 5:

[0579] Treatment result feedback

[0580] Medical professionals: record the results of the treatments performed on a dedicated form.

[0581] On the device: Form entry information is encrypted and sent to the server.

[0582] Input: Treatment outcome.

[0583] Output: Encrypted treatment results.

[0584] Step 6:

[0585] Data Update and Training

[0586] Server: Receives the encrypted treatment results and stores them in a database.

[0587] Server: Updates the AI ​​model based on treatment results to improve the accuracy of the next analysis.

[0588] Input: Treatment outcome.

[0589] Output: The updated AI model.

[0590] Each step of this system works to appropriately process the input data and ultimately improve the user's health and provide effective support to medical professionals.

[0591] (Application example 1)

[0592] 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."

[0593] Conventional medical systems have difficulty efficiently collecting and analyzing users' health information and providing optimal treatment. Furthermore, follow-up after treatment is insufficient, especially regarding self-care. This has made continuous health management and providing optimal treatment methods challenging.

[0594] 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.

[0595] In this invention, the server includes means for inputting health information from a user, means for transmitting the input health information to the server, means for anonymizing and storing the received health information in the server, means for analyzing the health information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, means for storing the retransmitted treatment results in a database and updating the AI ​​model, means for selecting an optimal video based on the health information and delivering it to a user terminal, means for inputting feedback after watching the video, and means for further improving the accuracy of the AI ​​model based on the input feedback. This makes it possible to provide individually customized treatments and self-care information based on the user's health information.

[0596] "Health information" refers to data relating to a user's personal health, such as diagnostic results, symptoms, and treatment history.

[0597] A "server" is a computer system that receives, stores, processes, and transmits data over a network.

[0598] "Anonymization" is the process of removing or masking personally identifiable information to protect an individual's privacy.

[0599] "Storage" is the act of recording and safely storing data.

[0600] An "AI model" is an algorithm that has been trained to perform a specific task using artificial intelligence techniques.

[0601] "Analysis" is the process of extracting information from input data and deriving results.

[0602] A "treatment" is a medical procedure or method for solving or improving a user's health problem.

[0603] "Notification" is the act of communicating information or results to other systems or people.

[0604] "Feedback" is information about opinions and results provided by users.

[0605] "Video" is visual content that combines a series of images.

[0606] "Distribution" is the act of transmitting digital content to users over a network.

[0607] A "terminal" is a device that a user directly operates to input and receive information.

[0608] "Encryption" is a technology that converts data to keep it secure and prevents unauthorized access.

[0609] The present invention is a system that collects health information from a user and uses an AI model to suggest optimal treatments and self-care information based on that information. Specific embodiments for carrying out the present invention will be described in detail below.

[0610] System configuration

[0611] This system is realized by combining the following hardware and software elements.

[0612] 1. User Device

[0613] Input and output devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs).

[0614] 2. Server

[0615] A computer system equipped with a high-performance processor and large-capacity storage device. Cloud services such as AWS (Amazon Web Services) and GCP (Google Cloud Platform) can also be used.

[0616] 3. AI Model

[0617] Models trained using machine learning libraries such as TensorFlow and PyTorch analyze a user's health information and recommend optimal treatments.

[0618] 4. Database

[0619] A relational database system, such as MongoDB or MySQL, to securely store anonymized health information and treatment results.

[0620] System Operation

[0621] Entering health information

[0622] Users input their own health information using devices such as smartphones or HMDs, for example, recording detailed symptoms such as knee pain or stiff shoulders, diagnosis results, and treatment history.

[0623] Transmission and anonymization of information

[0624] Health information entered from the device is sent to a server, which then anonymizes the information and stores it in a database while protecting the user's privacy.

[0625] Analysis using AI models

[0626] The data stored on the server is analyzed by an AI model, which uses past treatment data to recommend the optimal treatment and fitness videos for the entered health information.

[0627] Selection and distribution of recommended videos

[0628] Based on the analysis results, videos on optimal training and self-care are selected and delivered to the user's device. For example, a stretching video to relieve knee pain may be suggested.

[0629] Treatment results and feedback

[0630] After the user watches the recommended videos and performs training, the results are input as feedback from the device to the server, which then stores the newly obtained feedback in a database and updates the AI ​​model to improve its accuracy.

[0631] Specific examples

[0632] Example 1: When a user complains of knee pain and inputs it into the system, the AI ​​model uses past data to suggest the optimal stretching method and delivers a training video.

[0633] Example 2: If a user feels stiff shoulders, the system will select the optimal massage method and self-care video and provide it to the user.

[0634] Prompt Sentence Examples

[0635] If a user types in knee pain, recommend the best treatment based on past data. Select training videos to relieve knee pain and provide their URLs.

[0636] This allows users to obtain optimal treatment and self-care information according to their individual health conditions, enabling continuous health management.

[0637] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0638] Step 1:

[0639] Input: The user inputs health information such as knee pain using a device such as a smartphone or HMD.

[0640] Processing: The device collects the information entered by the user and performs encryption processing before sending the data to the server. Encryption uses encryption technology such as AES (Advanced Encryption Standard).

[0641] Output: Encrypted health information is generated and sent to the server.

[0642] Step 2:

[0643] Input: The server that receives the encrypted health information.

[0644] Processing: The server decrypts the encrypted information and anonymizes it by removing any personally identifiable information. Anonymization may include removing identifiers and / or masking the data.

[0645] Output: De-identified health information is generated and stored in a database.

[0646] Step 3:

[0647] Input: De-identified health information stored in a database.

[0648] Processing: The server inputs the stored health information into an AI model for analysis. The AI ​​model, pre-trained using TensorFlow, recommends optimal treatments and self-care methods based on past treatment data.

[0649] Output: The analysis identifies optimal treatments and fitness videos.

[0650] Step 4:

[0651] Input: Analysis results identified by the AI ​​model.

[0652] Processing: The server automatically selects the appropriate video based on the analysis results and generates its URL. The video selection involves comparing metadata and tagging content.

[0653] Output: A URL for the selected video is generated.

[0654] Step 5:

[0655] Input: Server-generated video URL.

[0656] Process: The server delivers the video URL to the user's device, securely using the HTTPS protocol.

[0657] Output: The video URL is displayed on the user's device.

[0658] Step 6:

[0659] Input: User watches videos and performs training on device.

[0660] Processing: After completing the training, the user inputs their feedback into the terminal. The feedback includes the effectiveness of the training and their impressions.

[0661] Output: Feedback data is generated and sent to the server.

[0662] Step 7:

[0663] Input: Feedback data submitted by the user.

[0664] Processing: The server analyzes the received feedback data and stores it in a database. The AI ​​model is updated based on the stored feedback to improve accuracy. An online learning algorithm is used for updating.

[0665] Output: An updated AI model is generated and used for the next analysis.

[0666] These steps enable the present invention to provide personalized treatment and self-care information based on the user's health information.

[0667] 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.

[0668] System Overview:

[0669] This invention relates to an AI analysis system that inputs a user's health and emotional information, performs rigorous analysis, and provides optimal treatment methods. In addition to conventional health information processing, this system incorporates an emotion engine to provide treatment methods that take the user's emotional state into consideration.

[0670] System configuration:

[0671] The system includes the following means:

[0672] 1. User's device

[0673] 2. Server

[0674] 3. AI Model

[0675] 4. Emotion Engine

[0676] 5. Database

[0677] System behavior:

[0678] When a user enters health and emotional information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health and emotional information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device back to the server. The server stores the newly obtained treatment results in a database and updates the AI ​​model to improve the accuracy of the next analysis.

[0679] What the program does:

[0680] Entering and sending health and emotional information:

[0681] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information that is analyzed using the emotion engine. The input information is encrypted and sent to the server. For example, Mr. Tanaka complains of knee pain and inputs the details of the pain and anxiety he feels during treatment into the device.

[0682] Anonymization and storage of information:

[0683] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[0684] Analysis by AI model:

[0685] The data stored on the server is analyzed by an AI model. Based on past treatment data and emotional data, the AI ​​model identifies the optimal treatment method based on the input health and emotional information. For example, if a user is feeling anxious about knee pain, the AI ​​model will recommend the optimal method, including treatment to alleviate that anxiety.

[0686] Notification of recommended treatment:

[0687] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan. This allows the doctor to provide efficient treatment that takes into account the user's health and emotional information.

[0688] Treatment result feedback:

[0689] The doctor administers the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results and changes in his / her emotions.

[0690] Data update and training:

[0691] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[0692] Examples:

[0693] The user inputs knee pain and emotion data.

[0694] Tanaka enters details about his knee pain into the device and sends them to the server, while also inputting his own anxiety using the emotion engine.

[0695] Anonymization and Analysis of Information

[0696] The server anonymizes the information it receives and stores it in a database, after which it analyzes it using an AI model. Based on past successful treatments, it recommends a combination of the best treatment for knee pain and anxiety relief.

[0697] Notification of recommended treatment

[0698] The identified treatment will be notified to the doctor in charge, who will plan and implement the treatment. The doctor will also take into account the emotional information provided and take an appropriate approach to Mr. Tanaka.

[0699] Treatment result feedback

[0700] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[0701] Through this process, the system effectively manages the user's health and emotional state and provides optimal treatment methods, improving the user's overall quality of life and contributing to alleviating labor shortages.

[0702] The processing flow will be explained below.

[0703] Step 1:

[0704] The user inputs health and emotional information from a terminal. The user fills out an input form with their symptoms, diagnosis results, treatment history, and emotional state (e.g., anxiety, joy, anger, etc.). The emotion engine analyzes the user's emotional information in real time and assists in the input.

[0705] Step 2:

[0706] The device sends the entered health and emotional information to a server, which encrypts all data and transmits it to the server using a secure protocol.

[0707] Step 3:

[0708] The server anonymizes the health and emotional information it receives. The server then runs a process to remove personally identifiable information and de-identify the data. The resulting anonymous data is managed in a manner that protects the user's privacy.

[0709] Step 4:

[0710] The server stores the anonymized health and emotional information in a database, where it securely records the information for future analysis.

[0711] Step 5:

[0712] The server inputs the health and emotional information stored in the database into the AI ​​model for analysis. The server utilizes past treatment data and emotional data to perform analysis to identify the most appropriate treatment method for the user's symptoms. The AI ​​model then proposes the optimal treatment, taking into account both the user's health and emotional state.

[0713] Step 6:

[0714] The server notifies the doctor of the optimal treatment identified by the AI ​​model. The server then sends the analysis results to the doctor's dedicated device, where the doctor receives the information. The doctor then formulates a recommended treatment plan, taking into account the user's health and emotional information.

[0715] Step 7:

[0716] The doctor will then carry out treatment based on the recommended treatment. The doctor will plan and carry out specific treatment based on the treatment method and emotional information notified by the server. For example, standard treatment for knee pain will be combined with counseling to alleviate the user's anxiety.

[0717] Step 8:

[0718] The doctor sends the treatment results and changes in the user's emotions from the device to the server. After the treatment is completed, the doctor records the treatment results and the user's emotional state in detail and reports them to the server using the device.

[0719] Step 9:

[0720] The server stores the received treatment results and emotion data in a database. Newly obtained treatment results and emotion data are recorded in the database and will be used for the next analysis.

[0721] Step 10:

[0722] The server updates the AI ​​model based on the latest treatment results and emotion data stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the accuracy of subsequent analyses.

[0723] Through these steps, the system will manage the user's health and emotional information in an advanced manner and provide the most appropriate treatment method quickly and effectively, thereby contributing to resolving the user's health problems and thereby helping to resolve the labor shortage problem in society as a whole.

[0724] Example 2

[0725] 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."

[0726] Conventional health information processing systems have had the challenge of making it difficult to provide treatment methods that take into account the user's psychological state. They also required comprehensive management, including anonymizing received information, securely storing data, and updating AI models to improve analysis accuracy. This resulted in problems that prevented users from fully improving their satisfaction and improving medical efficiency.

[0727] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting health information and emotional information from a user, means for transmitting the input health information and emotional information to the server, means for anonymizing and storing the received health information and emotional information, means for analyzing the health information and emotional information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, and means for storing the retransmitted treatment results in a database and updating the AI ​​model. This makes it possible to comprehensively manage the user's health condition and emotional information and provide an optimal treatment with improved analysis accuracy.

[0728] "Health information" is a general term for medical data such as a user's diagnosis, symptoms, and treatment history.

[0729] "Emotional information" is a general term for data relating to the user's psychological state and emotional fluctuations.

[0730] A "terminal" is an electronic device used by a user to input information, such as a smartphone or a personal computer.

[0731] A "server" is a central processing unit that receives information sent from a user and processes it, such as storing, analyzing, and notifying users.

[0732] "Anonymization" is a process to protect personal information by removing elements that can identify individuals from received information.

[0733] A "database" is an information storage system for safely storing anonymized information and treatment results.

[0734] An "AI model" is an artificial intelligence algorithm that analyzes past data and identifies the optimal treatment method.

[0735] "Analysis results" refers to the optimal treatment methods and recommendations obtained after the AI ​​model analyzes the input data.

[0736] "Notification" refers to the act of transmitting the analysis results from the server to the attending physician.

[0737] "Treatment results" refers to data that records the effects of treatment administered by a doctor and changes in the user's condition.

[0738] "Encryption" is a technology that converts information into a specific code to transmit it securely and prevent unauthorized access.

[0739] The present invention involves inputting a user's health and emotional information, sending it to a server, and analyzing the anonymized information with an AI model to identify the optimal treatment and notify the doctor. The treatment results are then sent back to the server, stored in a database, and the AI ​​model is updated to improve the system's analytical accuracy.

[0740] Enter and submit information

[0741] Users input their own health and emotional information using devices such as smartphones or PCs. Health information includes diagnosis results, symptoms, and treatment history, while emotional information includes psychological state analyzed using an emotion engine. Once the user has completed input, the information is encrypted and sent to the server.

[0742] Examples:

[0743] Mr. Tanaka complains of knee pain, enters detailed information about the pain and his anxiety during treatment into the terminal, and sends it.

[0744] Anonymization and storage of information

[0745] The information received by the server is anonymized by removing any personally identifiable information. This anonymized information is then stored in a highly secure database, ensuring the protection of personal information.

[0746] Analysis using AI models

[0747] The server retrieves the stored health and emotional information and inputs it into an AI model, which analyzes past treatment data and emotional data to identify the optimal treatment method. This AI model uses machine learning libraries such as TensorFlow and PyTorch.

[0748] Examples:

[0749] Data on Tanaka's knee pain and anxiety will be provided to the AI, which will analyze and identify the optimal treatment and anxiety relief methods.

[0750] Notification of recommended treatment

[0751] The server notifies the doctor of the analysis results, who then uses the results to create a specific treatment plan and provide the treatment to the user.

[0752] Treatment outcome feedback and updates

[0753] The doctor performs the treatment and sends the results from the device to the server. The treatment results are then anonymized again and stored in a database. Furthermore, this new treatment data is used to update the AI ​​model, improving the accuracy of the analysis the next time.

[0754] Specific examples of prompts to input to generative AI models

[0755] Below is an example of a prompt sentence to input to the generative AI model.

[0756] "A user enters data on their knee pain and anxiety via a device. Please explain in detail the process by which this information is anonymized, fed into an AI model to analyze the optimal treatment, and then communicates the results to the doctor."

[0757] This invention takes into account the psychological state of the user and provides optimal treatment, thereby increasing user satisfaction and improving the quality of medical care. Furthermore, continuous data updates can improve analysis accuracy, which is expected to have long-term medical effects.

[0758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0759] Step 1:

[0760] The user inputs health and emotional information

[0761] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information. This input data is collected as text and numerical data based on the device's input form. Once input is complete, the data is sent by pressing the send button to proceed to the next step.

[0762] Input: Diagnosis results, symptoms, treatment history, emotional information (text and numerical data)

[0763] Output: Data submitted from the input form

[0764] Specific actions: For example, if Tanaka enters details of his knee pain and anxiety, he will enter data such as "Right knee pain, level 7 (out of 10)" and "Anxiety about treatment level 3 (out of 5)" into the terminal form.

[0765] Step 2:

[0766] The device sends the input information to the server

[0767] The device encrypts the health and emotional information entered by the user and sends it to the server using an encryption algorithm such as AES.

[0768] Input: Health and emotional information entered by the user

[0769] Output: Encrypted data

[0770] Specific operation: Tanaka's input data is AES encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[0771] Step 3:

[0772] The server anonymizes the information

[0773] The server decrypts the encrypted data it receives, removes any personally identifiable information, and anonymizes it, assigning it a new unique ID.

[0774] Input: Encrypted user data

[0775] Output: Anonymized data

[0776] Specific operation: After Tanaka's data is decrypted, specific personal information such as name and address is removed and it is saved in the format "User ID: 12345".

[0777] Step 4:

[0778] The server stores the anonymized information in a database

[0779] The anonymized data is stored in a highly secure database, which is implemented using SQL and NoSQL technologies.

[0780] Input: Anonymized data

[0781] Output: Data stored in the database

[0782] Specific operation: Anonymized data on Tanaka's knee pain and anxiety is stored in an "anonymous database."

[0783] Step 5:

[0784] The server inputs the data into the AI ​​model

[0785] The server extracts the necessary patient information from the database and inputs it into the AI ​​model, which uses machine learning libraries such as TensorFlow and PyTorch.

[0786] Input: De-identified data extracted from the database

[0787] Output: Data input into the AI ​​model

[0788] Specific operation: Data on Tanaka's knee pain and anxiety is input into the AI ​​model by the server.

[0789] Step 6:

[0790] AI models analyze data and identify optimal treatment options

[0791] The AI ​​model uses deep learning techniques to analyze past treatment data and emotional data to identify the optimal treatment method.

[0792] Input: Data fed into the AI ​​model

[0793] Output: Recommendation of optimal treatment method

[0794] Specific operation: The AI ​​model analyzes Tanaka's data and outputs the result, "Knee treatment: physical therapy, emotional relaxation method: cognitive behavioral therapy."

[0795] Step 7:

[0796] The server notifies the doctor of the analysis results

[0797] The server then notifies the doctor of the analysis results via email or a dedicated medical application.

[0798] Input: Analysis results of the AI ​​model

[0799] Output:Notify doctor

[0800] Specific operation: The server sends the results of Tanaka's optimal treatment to his doctor via email.

[0801] Step 8:

[0802] The doctor administers the treatment

[0803] The doctor in charge will then provide treatment to the user based on the analysis results after receiving the notification, and treatment methods such as physical therapy or counseling will be selected.

[0804] Input: Treatment notified by the server

[0805] Output: Treatment performed

[0806] Specific action: The doctor will administer physical therapy and cognitive behavioral therapy to Tanaka.

[0807] Step 9:

[0808] The doctor sends the treatment results from the device to the server.

[0809] The doctor enters the treatment results into the terminal, encrypts them, and sends them to the server, again using an encryption algorithm such as AES.

[0810] Input: Treatment results

[0811] Output: Encrypted treatment outcome data

[0812] Specific operation: The doctor enters Tanaka's treatment results into the terminal and sends the AES-encrypted data to the server.

[0813] Step 10:

[0814] The server stores the treatment results in a database and updates the AI ​​model.

[0815] The server receives and anonymizes the treatment results, stores them in a database, and updates the AI ​​model based on this new data.

[0816] Input: Encrypted treatment outcome data

[0817] Output: De-identified treatment outcome data, updated AI model

[0818] Specific operation: Tanaka's treatment result data is anonymized and stored in a database, and the AI ​​model is retrained with new data.

[0819] (Application example 2)

[0820] 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."

[0821] Conventional medical systems identify treatment options based solely on the user's health information, making it difficult to provide optimal treatment and dietary recommendations that reflect the user's emotional state. Furthermore, there was no system that effectively collected users' treatment results and dietary feedback and quickly reflected the results in collaboration with food delivery services. This resulted in a lack of tools to improve users' overall health and quality of life.

[0822] The identification processing by the identification 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 inputting health information and emotional information from a user; means for transmitting the input health information and emotional information to the server; means for anonymizing and storing the received health information and emotional information in the server; means for analyzing the health information and emotional information stored in the server using an AI model; means for identifying optimal treatments and dietary suggestions based on the analysis results and notifying the doctor and the user; means for retransmitting the results of the treatment performed by the doctor and the user's dietary feedback information to the server; means for storing the retransmitted treatment results and dietary feedback information in a database and updating the AI ​​model; and means for coordinating with a food delivery service to make dietary suggestions available for immediate ordering. This enables integrated management of a user's health condition and emotional information, enabling the provision of more accurate treatments and individually optimized meals.

[0823]

[0824] "Health information" refers to medical data such as a user's diagnosis results, treatment history, and allergy information.

[0825] "Emotional information" refers to data related to the user's feelings, such as stress, anxiety, and joy.

[0826] "Server" refers to the database and computing device that stores the health and emotional information received from the user and analyzes it using the AI ​​model.

[0827] An "AI model" is a computational model that uses artificial intelligence and refers to an algorithm that analyzes a user's health and emotional information and derives optimal treatment and dietary suggestions.

[0828] "Anonymization" refers to the process of removing personally identifiable information from received data to protect the privacy of that data.

[0829] "Treatment" refers to a specific medical procedure that a doctor performs based on the user's health condition.

[0830] "Dietary suggestions" refers to the dietary and nutritional intake plans that the AI ​​model recommends to the user based on the analysis results.

[0831] "Notification" refers to the act of informing a user or a doctor of analysis results or suggestions.

[0832] "Feedback information" refers to information reported by a user as a result of the treatment or diet they have undertaken.

[0833] "Food delivery service" refers to a company or system that provides a service of quickly delivering meals specified by a user.

[0834] "Encryption processing" refers to a technology that encodes data to keep it confidential and prevent it from being leaked to third parties.

[0835]

[0836] The present invention is a system for proposing optimal treatments and diets based on a user's health information and emotional information. Specific embodiments of the present invention will be described below.

[0837] Hardware and software used

[0838] User device: A smartphone is used by the user to input health and emotional information.

[0839] Server: Uses cloud servers for data storage and processing.

[0840] Database: Firebase is used to store health and emotional information.

[0841] AI model: Use TensorFlow or PyTorch to analyze the data.

[0842] Emotion Engine: Uses Affectiva SDK to analyze user emotional information.

[0843] System Operation

[0844] 1. Enter your information:

[0845] Users input health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.) through a smartphone app, which then sends this information to a server.

[0846] 2. Transmission and storage of information:

[0847] The server anonymizes the health and emotional information received from the user and stores it securely in Firebase.

[0848] 3. Analysis by AI model:

[0849] The server retrieves the data stored in Firebase and analyzes it using TensorFlow or PyTorch-based AI models. Based on the analysis results, it generates optimal treatment and dietary recommendations for the user.

[0850] 4. Notification of results and collaboration:

[0851] The server then sends the analysis results to the user and their doctor via push notification. The server also works with food delivery services to provide meal suggestions, allowing users to instantly order the suggested menu items.

[0852] 5. Gather feedback and update the model:

[0853] After the user has eaten, they enter their feedback into the app. This feedback information is sent back to the server and stored in Firebase. The server uses this information to update the AI ​​model and improve its accuracy in the future.

[0854] Specific examples

[0855] For example, a user can input health information such as "I've been feeling tired and unmotivated lately," and also emotional information such as "I'm under a lot of stress at work." The AI ​​model analyzes this information and suggests relaxing herbal teas and meals rich in B vitamins to highly stressed users. This allows the user to receive push notifications suggesting the most suitable meals, which can then be instantly ordered through a delivery service.

[0856] Prompt Sentence Examples

[0857] "I've been suffering from a lack of sleep and am in a mentally unstable state. Please suggest some meals that will replenish my energy and help me relax."

[0858] "I haven't been exercising much lately, so my appetite has decreased. Could you recommend some foods that are easy to digest and gentle on the body?"

[0859] This system enables the integrated management of a user's health status and emotional information, and provides highly accurate treatments and individually optimized diets.

[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0861]

[0862] Step 1: Enter your information

[0863] The user launches the smartphone app and inputs health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.). This information is structured in JSON format and sent to the server via the app. For example, a user might input health information such as "I've been feeling tired and unmotivated lately" and emotional information such as "I'm under a lot of stress at work."

[0864] Step 2: Send and save information

[0865] The health and emotional information sent from the device is received by a server. The server anonymizes the received information by removing any personally identifiable elements. The anonymized data is then stored in Firebase. Examples of input data include "feeling tired, high stress."

[0866] Step 3: Analysis by AI model

[0867] The server retrieves health and emotional information stored in Firebase and inputs it into a TensorFlow or PyTorch-based AI model. The AI ​​model analyzes this data and generates treatment and dietary recommendations that are optimal for the user's condition. For example, it might recommend relaxing herbal teas or meals rich in B vitamins.

[0868] Step 4: Notification of results and collaboration

[0869] The server sends the analysis results generated by the AI ​​model to the user and doctor via push notification. It also works with food delivery services to provide meal suggestions, making the suggested menu items instantly available for ordering. A specific example of a notification might include a recommendation for a relaxing herbal tea and a meal rich in B vitamins.

[0870] Step 5: Gather feedback

[0871] After the user orders and consumes the suggested meal, they enter their feedback through a smartphone app, such as "The herbal tea had a relaxing effect."

[0872] Step 6: Update the model

[0873] The feedback information sent from the device is received by the server and stored in Firebase. The server uses this feedback information to update the AI ​​model and improve the accuracy of future suggestions, thereby continuously improving the entire system.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] [Third embodiment]

[0878] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0879] 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.

[0880] 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).

[0881] 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.

[0882] 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.

[0883] 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).

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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."

[0890] System Overview:

[0891] This invention relates to an AI analysis system that inputs health information and proposes treatment methods. This system includes processes such as anonymizing and storing the health information entered by the user, identifying appropriate treatment methods using an AI model, notifying doctors, and finally using the treatment results for further analysis.

[0892] System configuration:

[0893] The system includes the following means:

[0894] 1. User's device

[0895] 2. Server

[0896] 3. AI Model

[0897] 4. Database

[0898] System behavior:

[0899] When a user enters health information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device back to the server. The server stores the newly obtained treatment results in a database and updates the AI ​​model, improving the accuracy of the next analysis.

[0900] What the program does:

[0901] Entering and submitting health information:

[0902] A user uses a device to input health information such as diagnosis results, symptoms, and treatment history. The input information is encrypted and sent to a server. For example, Mr. Tanaka complains of knee pain and inputs the details into the device.

[0903] Anonymization and storage of information:

[0904] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[0905] Analysis by AI model:

[0906] The data stored on the server is analyzed by an AI model, which uses past treatment data to identify the best treatment based on the health information entered. For example, the AI ​​model identifies successful treatments from similar cases to recommend an effective treatment for knee pain.

[0907] Notification of recommended treatment:

[0908] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan, enabling the doctor to provide optimal treatment efficiently.

[0909] Treatment result feedback:

[0910] The doctor performs the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results.

[0911] Data update and training:

[0912] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[0913] Examples:

[0914] User inputs knee pain

[0915] Tanaka enters details about his knee pain into the device and sends them to the server.

[0916] Anonymization and Analysis of Information

[0917] The server anonymizes the information it receives, stores it in a database, and then analyzes it using an AI model to identify the best treatment for knee pain based on past successful treatments.

[0918] Notification of recommended treatment

[0919] The doctor in charge will be notified of the identified treatment, and the doctor will plan and implement the treatment.

[0920] Treatment result feedback

[0921] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[0922] Through this series of processes, the system will effectively improve the user's health, support doctors' treatment, and contribute to resolving the labor shortage problem in society as a whole.

[0923] The processing flow will be explained below.

[0924] Step 1:

[0925] The user enters health information from the device. The user accurately fills in the input form with their symptoms, diagnosis results, treatment history, etc. The entered information includes specific descriptions of symptoms and past diagnosis information.

[0926] Step 2:

[0927] The device sends the entered health information to the server. The device encrypts the health information to ensure safe transmission, and then sends the data to the server via the Internet.

[0928] Step 3:

[0929] The server anonymizes the received health information. The server removes personally identifiable information from the received data to generate anonymized data.

[0930] Step 4:

[0931] The server stores the de-identified data in a database, where the de-identified health information is securely recorded and available for subsequent analysis.

[0932] Step 5:

[0933] The server inputs the health information stored in the database into the AI ​​model for analysis. The server supplies the health information to the AI ​​model, which then analyzes the optimal treatment based on past data.

[0934] Step 6:

[0935] The server notifies the doctor of the optimal treatment identified by the AI ​​model, and then sends the analysis results to the doctor's dedicated device, where the doctor receives the information.

[0936] Step 7:

[0937] The doctor will carry out treatment based on the recommended treatment. The doctor will refer to the treatment method notified by the server and plan and carry out specific treatment for the patient.

[0938] Step 8:

[0939] The doctor sends the treatment results from the device to the server. After the treatment is completed, the doctor records the results in detail and reports them to the server using the device.

[0940] Step 9:

[0941] The server stores the received treatment results in a database. Newly obtained treatment results are recorded in the database and are used again as learning data for the AI ​​model.

[0942] Step 10:

[0943] The server updates the AI ​​model based on the latest treatment results stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the quality of subsequent analyses.

[0944] Through this series of steps, the system can effectively manage users' health information and provide doctors with optimal treatment methods, thereby helping users solve their health problems and contributing to alleviating the labor shortage.

[0945] Example 1

[0946] 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."

[0947] Conventional health information analysis systems often lack sufficient protection of the privacy of input information, accuracy of analysis, and re-learning capabilities. Furthermore, they lack the ability to identify effective treatments and provide prompt feedback on the results. This results in inefficient medical support for users and a heavy burden on medical professionals. Furthermore, input information and treatment results are not encrypted, posing a risk of information leaks.

[0948] 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.

[0949] In this invention, the server includes a means for encrypting health information and treatment results sent from the user terminal, a means for anonymizing and storing the received health information, and a means for identifying the optimal treatment based on the analysis results and notifying medical professionals. This ensures privacy protection and enables improved analysis accuracy and rapid treatment identification using AI models. Furthermore, feedback on treatment results advances learning throughout the system, further improving the accuracy of the next analysis.

[0950] 1. "User" refers to the individual or group of people who input health information into the system.

[0951] 2. "Health Information" means data about a user's body, such as diagnostic results, symptoms, and treatment history.

[0952] 3. "Server" refers to the computer system that receives, processes, stores, and analyzes health information sent by users.

[0953] 4. "Anonymization" refers to the process of removing or transforming personally identifiable information so that it can no longer be used to identify the original individual.

[0954] 5. "Storage" means the act of recording received health information and treatment results in a database.

[0955] 6. "Artificial intelligence model" refers to an algorithm that learns from past data and makes predictions and analyses on new data.

[0956] 7. “Analysis” refers to the process of using artificial intelligence models to process input data and derive meaningful results.

[0957] 8. "Therapy" means a medical procedure or method of treatment for a specific health problem.

[0958] 9. "Notification" refers to the act of notifying a specific person or system of analysis results or important information.

[0959] 10. "Healthcare professional" refers to a medical professional, such as a doctor or nurse, who has the qualifications and knowledge to diagnose and treat.

[0960] 11. "Feedback" means the act of re-entering the results and evaluation of treatment into the system to help improve it next time.

[0961] 12. "Encryption" refers to the process of converting data into a form that is unreadable to third parties using a specific key.

[0962] 13. "Database" means a system that can systematically collect, store, manage, and search multiple data.

[0963] The present invention relates to a system that inputs health information, analyzes it, and proposes optimal treatments. This system is composed of a series of processes including users, terminals, servers, artificial intelligence models, and databases.

[0964] First, the user uses the device to input their own health information. The input information includes diagnosis results, symptoms, treatment history, etc. The device then encrypts this information using encryption technology such as AES (Advanced Encryption Standard) and securely transmits it to the server.

[0965] The server anonymizes the received health information. Specifically, it deletes elements that could identify individuals and assigns an anonymization ID, converting the information into a format that does not allow the original individual to be identified. The anonymized information is then stored as is in a database. This database can be a system such as MySQL.

[0966] The server then takes the anonymized data stored in the database and feeds it into an artificial intelligence model, built using the Python libraries TensorFlow and PyTorch, which analyzes the patient's past treatment data to identify the most appropriate treatment.

[0967] The server then notifies the medical professional in charge of the AI ​​model's analysis results via email or a dedicated application, and the medical professional uses the recommended treatment to create a specific treatment plan.

[0968] After the treatment is performed, the medical professional will provide feedback on the treatment results to the server via the device. The device will then re-encrypt this feedback information and send it to the server. The server will then store the treatment results in a database and update the AI ​​model. This will allow the new data to be reflected in the next analysis, improving analysis accuracy.

[0969] As a concrete example, consider the case where a user complains of knee pain. Detailed information about the knee pain is entered into a device and sent to a server. The server anonymizes and stores the information, then analyzes it using an artificial intelligence model to identify the optimal treatment. The analysis results are then notified to the doctor in charge, who then administers the treatment. The treatment results are then fed back to the server, and the entire system continues to learn, improving the accuracy of the next analysis.

[0970] Examples of prompts for a generative AI model might include:

[0971] "Query the AI ​​model for the success rate of a treatment for a 50-year-old man complaining of knee pain."

[0972] "The AI ​​model proposes a list of treatments that have improved knee pain."

[0973] "An AI model identifies optimal treatment options based on past successful knee pain treatments."

[0974] In this way, the system can effectively improve the health status of users and provide valuable support for medical professionals.

[0975] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0976] Step 1:

[0977] Entering and submitting health information

[0978] User: Enters health information. Specifically, the user enters symptoms, diagnosis, and treatment history into the device. For example, the user enters details of knee pain.

[0979] Terminal: The entered information is encrypted using AES and sent to the server.

[0980] Input: Health information provided by the user.

[0981] Output: Encrypted health information.

[0982] Step 2:

[0983] Anonymization and storage of information

[0984] Server: Anonymizes the received health information by removing any personal identifying information and assigning an anonymized ID.

[0985] Server: The anonymized information is stored in a database, for example a MySQL database.

[0986] Input: Encrypted health information.

[0987] Output: Anonymized data.

[0988] Step 3:

[0989] Analysis using AI models

[0990] Server: Retrieves anonymized data stored in a database and inputs it into an artificial intelligence model.

[0991] AI models, using TensorFlow and PyTorch to perform analysis and generate optimal treatment recommendations, for example, identifying the best treatment for knee pain.

[0992] Input: De-identified health information.

[0993] Output: Treatment recommendations as a result of the analysis.

[0994] Step 4:

[0995] Notification of recommended treatment

[0996] Server: Receives the analysis results of the AI ​​model and notifies the medical professional in charge via email or a dedicated application.

[0997] Input: Analysis results.

[0998] Output: Notification to medical professionals.

[0999] Step 5:

[1000] Treatment result feedback

[1001] Medical professionals: record the results of the treatments performed on a dedicated form.

[1002] On the device: Form entry information is encrypted and sent to the server.

[1003] Input: Treatment outcome.

[1004] Output: Encrypted treatment results.

[1005] Step 6:

[1006] Data Update and Training

[1007] Server: Receives the encrypted treatment results and stores them in a database.

[1008] Server: Updates the AI ​​model based on treatment results to improve the accuracy of the next analysis.

[1009] Input: Treatment outcome.

[1010] Output: The updated AI model.

[1011] Each step of this system works to appropriately process the input data and ultimately improve the user's health and provide effective support to medical professionals.

[1012] (Application example 1)

[1013] 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."

[1014] Conventional medical systems have difficulty efficiently collecting and analyzing users' health information and providing optimal treatment. Furthermore, follow-up after treatment is insufficient, especially regarding self-care. This has made continuous health management and providing optimal treatment methods challenging.

[1015] 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.

[1016] In this invention, the server includes means for inputting health information from a user, means for transmitting the input health information to the server, means for anonymizing and storing the received health information in the server, means for analyzing the health information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, means for storing the retransmitted treatment results in a database and updating the AI ​​model, means for selecting an optimal video based on the health information and delivering it to a user terminal, means for inputting feedback after watching the video, and means for further improving the accuracy of the AI ​​model based on the input feedback. This makes it possible to provide individually customized treatments and self-care information based on the user's health information.

[1017] "Health information" refers to data relating to a user's personal health, such as diagnostic results, symptoms, and treatment history.

[1018] A "server" is a computer system that receives, stores, processes, and transmits data over a network.

[1019] "Anonymization" is the process of removing or masking personally identifiable information to protect an individual's privacy.

[1020] "Storage" is the act of recording and safely storing data.

[1021] An "AI model" is an algorithm that has been trained to perform a specific task using artificial intelligence techniques.

[1022] "Analysis" is the process of extracting information from input data and deriving results.

[1023] A "treatment" is a medical procedure or method for solving or improving a user's health problem.

[1024] "Notification" is the act of communicating information or results to other systems or people.

[1025] "Feedback" is information about opinions and results provided by users.

[1026] "Video" is visual content that combines a series of images.

[1027] "Distribution" is the act of transmitting digital content to users over a network.

[1028] A "terminal" is a device that a user directly operates to input and receive information.

[1029] "Encryption" is a technology that converts data to keep it secure and prevents unauthorized access.

[1030] The present invention is a system that collects health information from a user and uses an AI model to suggest optimal treatments and self-care information based on that information. Specific embodiments for carrying out the present invention will be described in detail below.

[1031] System configuration

[1032] This system is realized by combining the following hardware and software elements.

[1033] 1. User Device

[1034] Input and output devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs).

[1035] 2. Server

[1036] A computer system equipped with a high-performance processor and large-capacity storage device. Cloud services such as AWS (Amazon Web Services) and GCP (Google Cloud Platform) can also be used.

[1037] 3. AI Model

[1038] Models trained using machine learning libraries such as TensorFlow and PyTorch analyze a user's health information and recommend optimal treatments.

[1039] 4. Database

[1040] A relational database system, such as MongoDB or MySQL, to securely store anonymized health information and treatment results.

[1041] System Operation

[1042] Entering health information

[1043] Users input their own health information using devices such as smartphones or HMDs, for example, recording detailed symptoms such as knee pain or stiff shoulders, diagnosis results, and treatment history.

[1044] Transmission and anonymization of information

[1045] Health information entered from the device is sent to a server, which then anonymizes the information and stores it in a database while protecting the user's privacy.

[1046] Analysis using AI models

[1047] The data stored on the server is analyzed by an AI model, which uses past treatment data to recommend the optimal treatment and fitness videos for the entered health information.

[1048] Selection and distribution of recommended videos

[1049] Based on the analysis results, videos on optimal training and self-care are selected and delivered to the user's device. For example, a stretching video to relieve knee pain may be suggested.

[1050] Treatment results and feedback

[1051] After the user watches the recommended videos and performs training, the results are input as feedback from the device to the server, which then stores the newly obtained feedback in a database and updates the AI ​​model to improve its accuracy.

[1052] Specific examples

[1053] Example 1: When a user complains of knee pain and inputs it into the system, the AI ​​model uses past data to suggest the optimal stretching method and delivers a training video.

[1054] Example 2: If a user feels stiff shoulders, the system will select the optimal massage method and self-care video and provide it to the user.

[1055] Prompt Sentence Examples

[1056] If a user types in knee pain, recommend the best treatment based on past data. Select training videos to relieve knee pain and provide their URLs.

[1057] This allows users to obtain optimal treatment and self-care information according to their individual health conditions, enabling continuous health management.

[1058] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1059] Step 1:

[1060] Input: The user inputs health information such as knee pain using a device such as a smartphone or HMD.

[1061] Processing: The device collects the information entered by the user and performs encryption processing before sending the data to the server. Encryption uses encryption technology such as AES (Advanced Encryption Standard).

[1062] Output: Encrypted health information is generated and sent to the server.

[1063] Step 2:

[1064] Input: The server that receives the encrypted health information.

[1065] Processing: The server decrypts the encrypted information and anonymizes it by removing any personally identifiable information. Anonymization may include removing identifiers and / or masking the data.

[1066] Output: De-identified health information is generated and stored in a database.

[1067] Step 3:

[1068] Input: De-identified health information stored in a database.

[1069] Processing: The server inputs the stored health information into an AI model for analysis. The AI ​​model, pre-trained using TensorFlow, recommends optimal treatments and self-care methods based on past treatment data.

[1070] Output: The analysis identifies optimal treatments and fitness videos.

[1071] Step 4:

[1072] Input: Analysis results identified by the AI ​​model.

[1073] Processing: The server automatically selects the appropriate video based on the analysis results and generates its URL. The video selection involves comparing metadata and tagging content.

[1074] Output: A URL for the selected video is generated.

[1075] Step 5:

[1076] Input: Server-generated video URL.

[1077] Process: The server delivers the video URL to the user's device, securely using the HTTPS protocol.

[1078] Output: The video URL is displayed on the user's device.

[1079] Step 6:

[1080] Input: User watches videos and performs training on device.

[1081] Processing: After completing the training, the user inputs their feedback into the terminal. The feedback includes the effectiveness of the training and their impressions.

[1082] Output: Feedback data is generated and sent to the server.

[1083] Step 7:

[1084] Input: Feedback data submitted by the user.

[1085] Processing: The server analyzes the received feedback data and stores it in a database. The AI ​​model is updated based on the stored feedback to improve accuracy. An online learning algorithm is used for updating.

[1086] Output: An updated AI model is generated and used for the next analysis.

[1087] These steps enable the present invention to provide personalized treatment and self-care information based on the user's health information.

[1088] 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.

[1089] System Overview:

[1090] This invention relates to an AI analysis system that inputs a user's health and emotional information, performs rigorous analysis, and provides optimal treatment methods. In addition to conventional health information processing, this system incorporates an emotion engine to provide treatment methods that take the user's emotional state into consideration.

[1091] System configuration:

[1092] The system includes the following means:

[1093] 1. User's device

[1094] 2. Server

[1095] 3. AI Model

[1096] 4. Emotion Engine

[1097] 5. Database

[1098] System behavior:

[1099] When a user enters health and emotional information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health and emotional information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device back to the server. The server stores the newly obtained treatment results in a database and updates the AI ​​model to improve the accuracy of the next analysis.

[1100] What the program does:

[1101] Entering and sending health and emotional information:

[1102] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information that is analyzed using the emotion engine. The input information is encrypted and sent to the server. For example, Mr. Tanaka complains of knee pain and inputs the details of the pain and anxiety he feels during treatment into the device.

[1103] Anonymization and storage of information:

[1104] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[1105] Analysis by AI model:

[1106] The data stored on the server is analyzed by an AI model. Based on past treatment data and emotional data, the AI ​​model identifies the optimal treatment method based on the input health and emotional information. For example, if a user is feeling anxious about knee pain, the AI ​​model will recommend the optimal method, including treatment to alleviate that anxiety.

[1107] Notification of recommended treatment:

[1108] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan. This allows the doctor to provide efficient treatment that takes into account the user's health and emotional information.

[1109] Treatment result feedback:

[1110] The doctor administers the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results and changes in his / her emotions.

[1111] Data update and training:

[1112] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[1113] Examples:

[1114] The user inputs knee pain and emotion data.

[1115] Tanaka enters details about his knee pain into the device and sends them to the server, while also inputting his own anxiety using the emotion engine.

[1116] Anonymization and Analysis of Information

[1117] The server anonymizes the information it receives and stores it in a database, after which it analyzes it using an AI model. Based on past successful treatments, it recommends a combination of the best treatment for knee pain and anxiety relief.

[1118] Notification of recommended treatment

[1119] The identified treatment will be notified to the doctor in charge, who will plan and implement the treatment. The doctor will also take into account the emotional information provided and take an appropriate approach to Mr. Tanaka.

[1120] Treatment result feedback

[1121] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[1122] Through this process, the system effectively manages the user's health and emotional state and provides optimal treatment methods, improving the user's overall quality of life and contributing to alleviating labor shortages.

[1123] The processing flow will be explained below.

[1124] Step 1:

[1125] The user inputs health and emotional information from a terminal. The user fills out an input form with their symptoms, diagnosis results, treatment history, and emotional state (e.g., anxiety, joy, anger, etc.). The emotion engine analyzes the user's emotional information in real time and assists in the input.

[1126] Step 2:

[1127] The device sends the entered health and emotional information to a server, which encrypts all data and transmits it to the server using a secure protocol.

[1128] Step 3:

[1129] The server anonymizes the health and emotional information it receives. The server then runs a process to remove personally identifiable information and de-identify the data. The resulting anonymous data is managed in a manner that protects the user's privacy.

[1130] Step 4:

[1131] The server stores the anonymized health and emotional information in a database, where it securely records the information for future analysis.

[1132] Step 5:

[1133] The server inputs the health and emotional information stored in the database into the AI ​​model for analysis. The server utilizes past treatment data and emotional data to perform analysis to identify the most appropriate treatment method for the user's symptoms. The AI ​​model then proposes the optimal treatment, taking into account both the user's health and emotional state.

[1134] Step 6:

[1135] The server notifies the doctor of the optimal treatment identified by the AI ​​model. The server then sends the analysis results to the doctor's dedicated device, where the doctor receives the information. The doctor then formulates a recommended treatment plan, taking into account the user's health and emotional information.

[1136] Step 7:

[1137] The doctor will then carry out treatment based on the recommended treatment. The doctor will plan and carry out specific treatment based on the treatment method and emotional information notified by the server. For example, standard treatment for knee pain will be combined with counseling to alleviate the user's anxiety.

[1138] Step 8:

[1139] The doctor sends the treatment results and changes in the user's emotions from the device to the server. After the treatment is completed, the doctor records the treatment results and the user's emotional state in detail and reports them to the server using the device.

[1140] Step 9:

[1141] The server stores the received treatment results and emotion data in a database. Newly obtained treatment results and emotion data are recorded in the database and will be used for the next analysis.

[1142] Step 10:

[1143] The server updates the AI ​​model based on the latest treatment results and emotion data stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the accuracy of subsequent analyses.

[1144] Through these steps, the system will manage the user's health and emotional information in an advanced manner and provide the most appropriate treatment method quickly and effectively, thereby contributing to resolving the user's health problems and thereby helping to resolve the labor shortage problem in society as a whole.

[1145] Example 2

[1146] 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."

[1147] Conventional health information processing systems have had the challenge of making it difficult to provide treatment methods that take into account the user's psychological state. They also required comprehensive management, including anonymizing received information, securely storing data, and updating AI models to improve analysis accuracy. This resulted in problems that prevented users from fully improving their satisfaction and improving medical efficiency.

[1148] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting health information and emotional information from a user, means for transmitting the input health information and emotional information to the server, means for anonymizing and storing the received health information and emotional information, means for analyzing the health information and emotional information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, and means for storing the retransmitted treatment results in a database and updating the AI ​​model. This makes it possible to comprehensively manage the user's health condition and emotional information and provide an optimal treatment with improved analysis accuracy.

[1149] "Health information" is a general term for medical data such as a user's diagnosis, symptoms, and treatment history.

[1150] "Emotional information" is a general term for data relating to the user's psychological state and emotional fluctuations.

[1151] A "terminal" is an electronic device used by a user to input information, such as a smartphone or a personal computer.

[1152] A "server" is a central processing unit that receives information sent from a user and processes it, such as storing, analyzing, and notifying users.

[1153] "Anonymization" is a process to protect personal information by removing elements that can identify individuals from received information.

[1154] A "database" is an information storage system for safely storing anonymized information and treatment results.

[1155] An "AI model" is an artificial intelligence algorithm that analyzes past data and identifies the optimal treatment method.

[1156] "Analysis results" refers to the optimal treatment methods and recommendations obtained after the AI ​​model analyzes the input data.

[1157] "Notification" refers to the act of transmitting the analysis results from the server to the attending physician.

[1158] "Treatment results" refers to data that records the effects of treatment administered by a doctor and changes in the user's condition.

[1159] "Encryption" is a technology that converts information into a specific code to transmit it securely and prevent unauthorized access.

[1160] The present invention involves inputting a user's health and emotional information, sending it to a server, and analyzing the anonymized information with an AI model to identify the optimal treatment and notify the doctor. The treatment results are then sent back to the server, stored in a database, and the AI ​​model is updated to improve the system's analytical accuracy.

[1161] Enter and submit information

[1162] Users input their own health and emotional information using devices such as smartphones or PCs. Health information includes diagnosis results, symptoms, and treatment history, while emotional information includes psychological state analyzed using an emotion engine. Once the user has completed input, the information is encrypted and sent to the server.

[1163] Examples:

[1164] Mr. Tanaka complains of knee pain, enters detailed information about the pain and his anxiety during treatment into the terminal, and sends it.

[1165] Anonymization and storage of information

[1166] The information received by the server is anonymized by removing any personally identifiable information. This anonymized information is then stored in a highly secure database, ensuring the protection of personal information.

[1167] Analysis using AI models

[1168] The server retrieves the stored health and emotional information and inputs it into an AI model, which analyzes past treatment data and emotional data to identify the optimal treatment method. This AI model uses machine learning libraries such as TensorFlow and PyTorch.

[1169] Examples:

[1170] Data on Tanaka's knee pain and anxiety will be provided to the AI, which will analyze and identify the optimal treatment and anxiety relief methods.

[1171] Notification of recommended treatment

[1172] The server notifies the doctor of the analysis results, who then uses the results to create a specific treatment plan and provide the treatment to the user.

[1173] Treatment outcome feedback and updates

[1174] The doctor performs the treatment and sends the results from the device to the server. The treatment results are then anonymized again and stored in a database. Furthermore, this new treatment data is used to update the AI ​​model, improving the accuracy of the analysis the next time.

[1175] Specific examples of prompts to input to generative AI models

[1176] Below is an example of a prompt sentence to input to the generative AI model.

[1177] "A user enters data on their knee pain and anxiety via a device. Please explain in detail the process by which this information is anonymized, fed into an AI model to analyze the optimal treatment, and then communicates the results to the doctor."

[1178] This invention takes into account the psychological state of the user and provides optimal treatment, thereby increasing user satisfaction and improving the quality of medical care. Furthermore, continuous data updates can improve analysis accuracy, which is expected to have long-term medical effects.

[1179] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1180] Step 1:

[1181] The user inputs health and emotional information

[1182] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information. This input data is collected as text and numerical data based on the device's input form. Once input is complete, the data is sent by pressing the send button to proceed to the next step.

[1183] Input: Diagnosis results, symptoms, treatment history, emotional information (text and numerical data)

[1184] Output: Data submitted from the input form

[1185] Specific actions: For example, if Tanaka enters details of his knee pain and anxiety, he will enter data such as "Right knee pain, level 7 (out of 10)" and "Anxiety about treatment level 3 (out of 5)" into the terminal form.

[1186] Step 2:

[1187] The device sends the input information to the server

[1188] The device encrypts the health and emotional information entered by the user and sends it to the server using an encryption algorithm such as AES.

[1189] Input: Health and emotional information entered by the user

[1190] Output: Encrypted data

[1191] Specific operation: Tanaka's input data is AES encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[1192] Step 3:

[1193] The server anonymizes the information

[1194] The server decrypts the encrypted data it receives, removes any personally identifiable information, and anonymizes it, assigning it a new unique ID.

[1195] Input: Encrypted user data

[1196] Output: Anonymized data

[1197] Specific operation: After Tanaka's data is decrypted, specific personal information such as name and address is removed and it is saved in the format "User ID: 12345".

[1198] Step 4:

[1199] The server stores the anonymized information in a database

[1200] The anonymized data is stored in a highly secure database, which is implemented using SQL and NoSQL technologies.

[1201] Input: Anonymized data

[1202] Output: Data stored in the database

[1203] Specific operation: Anonymized data on Tanaka's knee pain and anxiety is stored in an "anonymous database."

[1204] Step 5:

[1205] The server inputs the data into the AI ​​model

[1206] The server extracts the necessary patient information from the database and inputs it into the AI ​​model, which uses machine learning libraries such as TensorFlow and PyTorch.

[1207] Input: De-identified data extracted from the database

[1208] Output: Data input into the AI ​​model

[1209] Specific operation: Data on Tanaka's knee pain and anxiety is input into the AI ​​model by the server.

[1210] Step 6:

[1211] AI models analyze data and identify optimal treatment options

[1212] The AI ​​model uses deep learning techniques to analyze past treatment data and emotional data to identify the optimal treatment method.

[1213] Input: Data fed into the AI ​​model

[1214] Output: Recommendation of optimal treatment method

[1215] Specific operation: The AI ​​model analyzes Tanaka's data and outputs the result, "Knee treatment: physical therapy, emotional relaxation method: cognitive behavioral therapy."

[1216] Step 7:

[1217] The server notifies the doctor of the analysis results

[1218] The server then notifies the doctor of the analysis results via email or a dedicated medical application.

[1219] Input: Analysis results of the AI ​​model

[1220] Output:Notify doctor

[1221] Specific operation: The server sends the results of Tanaka's optimal treatment to his doctor via email.

[1222] Step 8:

[1223] The doctor administers the treatment

[1224] The doctor in charge will then provide treatment to the user based on the analysis results after receiving the notification, and treatment methods such as physical therapy or counseling will be selected.

[1225] Input: Treatment notified by the server

[1226] Output: Treatment performed

[1227] Specific action: The doctor will administer physical therapy and cognitive behavioral therapy to Tanaka.

[1228] Step 9:

[1229] The doctor sends the treatment results from the device to the server.

[1230] The doctor enters the treatment results into the terminal, encrypts them, and sends them to the server, again using an encryption algorithm such as AES.

[1231] Input: Treatment results

[1232] Output: Encrypted treatment outcome data

[1233] Specific operation: The doctor enters Tanaka's treatment results into the terminal and sends the AES-encrypted data to the server.

[1234] Step 10:

[1235] The server stores the treatment results in a database and updates the AI ​​model.

[1236] The server receives and anonymizes the treatment results, stores them in a database, and updates the AI ​​model based on this new data.

[1237] Input: Encrypted treatment outcome data

[1238] Output: De-identified treatment outcome data, updated AI model

[1239] Specific operation: Tanaka's treatment result data is anonymized and stored in a database, and the AI ​​model is retrained with new data.

[1240] (Application example 2)

[1241] 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."

[1242] Conventional medical systems identify treatment options based solely on the user's health information, making it difficult to provide optimal treatment and dietary recommendations that reflect the user's emotional state. Furthermore, there was no system that effectively collected users' treatment results and dietary feedback and quickly reflected the results in collaboration with food delivery services. This resulted in a lack of tools to improve users' overall health and quality of life.

[1243] The identification processing by the identification 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 inputting health information and emotional information from a user; means for transmitting the input health information and emotional information to the server; means for anonymizing and storing the received health information and emotional information in the server; means for analyzing the health information and emotional information stored in the server using an AI model; means for identifying optimal treatments and dietary suggestions based on the analysis results and notifying the doctor and the user; means for retransmitting the results of the treatment performed by the doctor and the user's dietary feedback information to the server; means for storing the retransmitted treatment results and dietary feedback information in a database and updating the AI ​​model; and means for coordinating with a food delivery service to make dietary suggestions available for immediate ordering. This enables integrated management of a user's health condition and emotional information, enabling the provision of more accurate treatments and individually optimized meals.

[1244]

[1245] "Health information" refers to medical data such as a user's diagnosis results, treatment history, and allergy information.

[1246] "Emotional information" refers to data related to the user's feelings, such as stress, anxiety, and joy.

[1247] "Server" refers to the database and computing device that stores the health and emotional information received from the user and analyzes it using the AI ​​model.

[1248] An "AI model" is a computational model that uses artificial intelligence and refers to an algorithm that analyzes a user's health and emotional information and derives optimal treatment and dietary suggestions.

[1249] "Anonymization" refers to the process of removing personally identifiable information from received data to protect the privacy of that data.

[1250] "Treatment" refers to a specific medical procedure that a doctor performs based on the user's health condition.

[1251] "Dietary suggestions" refers to the dietary and nutritional intake plans that the AI ​​model recommends to the user based on the analysis results.

[1252] "Notification" refers to the act of informing a user or a doctor of analysis results or suggestions.

[1253] "Feedback information" refers to information reported by a user as a result of the treatment or diet they have undertaken.

[1254] "Food delivery service" refers to a company or system that provides a service of quickly delivering meals specified by a user.

[1255] "Encryption processing" refers to a technology that encodes data to keep it confidential and prevent it from being leaked to third parties.

[1256]

[1257] The present invention is a system for proposing optimal treatments and diets based on a user's health information and emotional information. Specific embodiments of the present invention will be described below.

[1258] Hardware and software used

[1259] User device: A smartphone is used by the user to input health and emotional information.

[1260] Server: Uses cloud servers for data storage and processing.

[1261] Database: Firebase is used to store health and emotional information.

[1262] AI model: Use TensorFlow or PyTorch to analyze the data.

[1263] Emotion Engine: Uses Affectiva SDK to analyze user emotional information.

[1264] System Operation

[1265] 1. Enter your information:

[1266] Users input health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.) through a smartphone app, which then sends this information to a server.

[1267] 2. Transmission and storage of information:

[1268] The server anonymizes the health and emotional information received from the user and stores it securely in Firebase.

[1269] 3. Analysis by AI model:

[1270] The server retrieves the data stored in Firebase and analyzes it using TensorFlow or PyTorch-based AI models. Based on the analysis results, it generates optimal treatment and dietary recommendations for the user.

[1271] 4. Notification of results and collaboration:

[1272] The server then sends the analysis results to the user and their doctor via push notification. The server also works with food delivery services to provide meal suggestions, allowing users to instantly order the suggested menu items.

[1273] 5. Gather feedback and update the model:

[1274] After the user has eaten, they enter their feedback into the app. This feedback information is sent back to the server and stored in Firebase. The server uses this information to update the AI ​​model and improve its accuracy in the future.

[1275] Specific examples

[1276] For example, a user can input health information such as "I've been feeling tired and unmotivated lately," and also emotional information such as "I'm under a lot of stress at work." The AI ​​model analyzes this information and suggests relaxing herbal teas and meals rich in B vitamins to highly stressed users. This allows the user to receive push notifications suggesting the most suitable meals, which can then be instantly ordered through a delivery service.

[1277] Prompt Sentence Examples

[1278] "I've been suffering from a lack of sleep and am in a mentally unstable state. Please suggest some meals that will replenish my energy and help me relax."

[1279] "I haven't been exercising much lately, so my appetite has decreased. Could you recommend some foods that are easy to digest and gentle on the body?"

[1280] This system enables the integrated management of a user's health status and emotional information, and provides highly accurate treatments and individually optimized diets.

[1281] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1282]

[1283] Step 1: Enter your information

[1284] The user launches the smartphone app and inputs health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.). This information is structured in JSON format and sent to the server via the app. For example, a user might input health information such as "I've been feeling tired and unmotivated lately" and emotional information such as "I'm under a lot of stress at work."

[1285] Step 2: Send and save information

[1286] The health and emotional information sent from the device is received by a server. The server anonymizes the received information by removing any personally identifiable elements. The anonymized data is then stored in Firebase. Examples of input data include "feeling tired, high stress."

[1287] Step 3: Analysis by AI model

[1288] The server retrieves health and emotional information stored in Firebase and inputs it into a TensorFlow or PyTorch-based AI model. The AI ​​model analyzes this data and generates treatment and dietary recommendations that are optimal for the user's condition. For example, it might recommend relaxing herbal teas or meals rich in B vitamins.

[1289] Step 4: Notification of results and collaboration

[1290] The server sends the analysis results generated by the AI ​​model to the user and doctor via push notification. It also works with food delivery services to provide meal suggestions, making the suggested menu items instantly available for ordering. A specific example of a notification might include a recommendation for a relaxing herbal tea and a meal rich in B vitamins.

[1291] Step 5: Gather feedback

[1292] After the user orders and consumes the suggested meal, they enter their feedback through a smartphone app, such as "The herbal tea had a relaxing effect."

[1293] Step 6: Update the model

[1294] The feedback information sent from the device is received by the server and stored in Firebase. The server uses this feedback information to update the AI ​​model and improve the accuracy of future suggestions, thereby continuously improving the entire system.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] [Fourth embodiment]

[1299] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1300] 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.

[1301] 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).

[1302] 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.

[1303] 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.

[1304] 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).

[1305] 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.

[1306] 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.

[1307] 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.

[1308] 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.

[1309] 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.

[1310] 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.

[1311] 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."

[1312] System Overview:

[1313] This invention relates to an AI analysis system that inputs health information and proposes treatment methods. This system includes processes such as anonymizing and storing the health information entered by the user, identifying appropriate treatment methods using an AI model, notifying doctors, and finally using the treatment results for further analysis.

[1314] System configuration:

[1315] The system includes the following means:

[1316] 1. User's device

[1317] 2. Server

[1318] 3. AI Model

[1319] 4. Database

[1320] System behavior:

[1321] When a user enters health information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device back to the server. The server stores the newly obtained treatment results in a database and updates the AI ​​model, improving the accuracy of the next analysis.

[1322] What the program does:

[1323] Entering and submitting health information:

[1324] A user uses a device to input health information such as diagnosis results, symptoms, and treatment history. The input information is encrypted and sent to a server. For example, Mr. Tanaka complains of knee pain and inputs the details into the device.

[1325] Anonymization and storage of information:

[1326] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[1327] Analysis by AI model:

[1328] The data stored on the server is analyzed by an AI model, which uses past treatment data to identify the best treatment based on the health information entered. For example, the AI ​​model identifies successful treatments from similar cases to recommend an effective treatment for knee pain.

[1329] Notification of recommended treatment:

[1330] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan, enabling the doctor to provide optimal treatment efficiently.

[1331] Treatment result feedback:

[1332] The doctor performs the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results.

[1333] Data update and training:

[1334] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[1335] Examples:

[1336] User inputs knee pain

[1337] Tanaka enters details about his knee pain into the device and sends them to the server.

[1338] Anonymization and Analysis of Information

[1339] The server anonymizes the information it receives, stores it in a database, and then analyzes it using an AI model to identify the best treatment for knee pain based on past successful treatments.

[1340] Notification of recommended treatment

[1341] The doctor in charge will be notified of the identified treatment, and the doctor will plan and implement the treatment.

[1342] Treatment result feedback

[1343] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[1344] Through this series of processes, the system will effectively improve the user's health, support doctors' treatment, and contribute to resolving the labor shortage problem in society as a whole.

[1345] The processing flow will be explained below.

[1346] Step 1:

[1347] The user enters health information from the device. The user accurately fills in the input form with their symptoms, diagnosis results, treatment history, etc. The entered information includes specific descriptions of symptoms and past diagnosis information.

[1348] Step 2:

[1349] The device sends the entered health information to the server. The device encrypts the health information to ensure safe transmission, and then sends the data to the server via the Internet.

[1350] Step 3:

[1351] The server anonymizes the received health information. The server removes personally identifiable information from the received data to generate anonymized data.

[1352] Step 4:

[1353] The server stores the de-identified data in a database, where the de-identified health information is securely recorded and available for subsequent analysis.

[1354] Step 5:

[1355] The server inputs the health information stored in the database into the AI ​​model for analysis. The server supplies the health information to the AI ​​model, which then analyzes the optimal treatment based on past data.

[1356] Step 6:

[1357] The server notifies the doctor of the optimal treatment identified by the AI ​​model, and then sends the analysis results to the doctor's dedicated device, where the doctor receives the information.

[1358] Step 7:

[1359] The doctor will carry out treatment based on the recommended treatment. The doctor will refer to the treatment method notified by the server and plan and carry out specific treatment for the patient.

[1360] Step 8:

[1361] The doctor sends the treatment results from the device to the server. After the treatment is completed, the doctor records the results in detail and reports them to the server using the device.

[1362] Step 9:

[1363] The server stores the received treatment results in a database. Newly obtained treatment results are recorded in the database and are used again as learning data for the AI ​​model.

[1364] Step 10:

[1365] The server updates the AI ​​model based on the latest treatment results stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the quality of subsequent analyses.

[1366] Through this series of steps, the system can effectively manage users' health information and provide doctors with optimal treatment methods, thereby helping users solve their health problems and contributing to alleviating the labor shortage.

[1367] Example 1

[1368] 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."

[1369] Conventional health information analysis systems often lack sufficient protection of the privacy of input information, accuracy of analysis, and re-learning capabilities. Furthermore, they lack the ability to identify effective treatments and provide prompt feedback on the results. This results in inefficient medical support for users and a heavy burden on medical professionals. Furthermore, input information and treatment results are not encrypted, posing a risk of information leaks.

[1370] 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.

[1371] In this invention, the server includes a means for encrypting health information and treatment results sent from the user terminal, a means for anonymizing and storing the received health information, and a means for identifying the optimal treatment based on the analysis results and notifying medical professionals. This ensures privacy protection and enables improved analysis accuracy and rapid treatment identification using AI models. Furthermore, feedback on treatment results advances learning throughout the system, further improving the accuracy of the next analysis.

[1372] 1. "User" refers to the individual or group of people who input health information into the system.

[1373] 2. "Health Information" means data about a user's body, such as diagnostic results, symptoms, and treatment history.

[1374] 3. "Server" refers to the computer system that receives, processes, stores, and analyzes health information sent by users.

[1375] 4. "Anonymization" refers to the process of removing or transforming personally identifiable information so that it can no longer be used to identify the original individual.

[1376] 5. "Storage" means the act of recording received health information and treatment results in a database.

[1377] 6. "Artificial intelligence model" refers to an algorithm that learns from past data and makes predictions and analyses on new data.

[1378] 7. “Analysis” refers to the process of using artificial intelligence models to process input data and derive meaningful results.

[1379] 8. "Therapy" means a medical procedure or method of treatment for a specific health problem.

[1380] 9. "Notification" refers to the act of notifying a specific person or system of analysis results or important information.

[1381] 10. "Healthcare professional" refers to a medical professional, such as a doctor or nurse, who has the qualifications and knowledge to diagnose and treat.

[1382] 11. "Feedback" means the act of re-entering the results and evaluation of treatment into the system to help improve it next time.

[1383] 12. "Encryption" refers to the process of converting data into a form that is unreadable to third parties using a specific key.

[1384] 13. "Database" means a system that can systematically collect, store, manage, and search multiple data.

[1385] The present invention relates to a system that inputs health information, analyzes it, and proposes optimal treatments. This system is composed of a series of processes including users, terminals, servers, artificial intelligence models, and databases.

[1386] First, the user uses the device to input their own health information. The input information includes diagnosis results, symptoms, treatment history, etc. The device then encrypts this information using encryption technology such as AES (Advanced Encryption Standard) and securely transmits it to the server.

[1387] The server anonymizes the received health information. Specifically, it deletes elements that could identify individuals and assigns an anonymization ID, converting the information into a format that does not allow the original individual to be identified. The anonymized information is then stored as is in a database. This database can be a system such as MySQL.

[1388] The server then takes the anonymized data stored in the database and feeds it into an artificial intelligence model, built using the Python libraries TensorFlow and PyTorch, which analyzes the patient's past treatment data to identify the most appropriate treatment.

[1389] The server then notifies the medical professional in charge of the AI ​​model's analysis results via email or a dedicated application, and the medical professional uses the recommended treatment to create a specific treatment plan.

[1390] After the treatment is performed, the medical professional will provide feedback on the treatment results to the server via the device. The device will then re-encrypt this feedback information and send it to the server. The server will then store the treatment results in a database and update the AI ​​model. This will allow the new data to be reflected in the next analysis, improving analysis accuracy.

[1391] As a concrete example, consider the case where a user complains of knee pain. Detailed information about the knee pain is entered into a device and sent to a server. The server anonymizes and stores the information, then analyzes it using an artificial intelligence model to identify the optimal treatment. The analysis results are then notified to the doctor in charge, who then administers the treatment. The treatment results are then fed back to the server, and the entire system continues to learn, improving the accuracy of the next analysis.

[1392] Examples of prompts for a generative AI model might include:

[1393] "Query the AI ​​model for the success rate of a treatment for a 50-year-old man complaining of knee pain."

[1394] "The AI ​​model proposes a list of treatments that have improved knee pain."

[1395] "An AI model identifies optimal treatment options based on past successful knee pain treatments."

[1396] In this way, the system can effectively improve the health status of users and provide valuable support for medical professionals.

[1397] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1398] Step 1:

[1399] Entering and submitting health information

[1400] User: Enters health information. Specifically, the user enters symptoms, diagnosis, and treatment history into the device. For example, the user enters details of knee pain.

[1401] Terminal: The entered information is encrypted using AES and sent to the server.

[1402] Input: Health information provided by the user.

[1403] Output: Encrypted health information.

[1404] Step 2:

[1405] Anonymization and storage of information

[1406] Server: Anonymizes the received health information by removing any personal identifying information and assigning an anonymized ID.

[1407] Server: The anonymized information is stored in a database, for example a MySQL database.

[1408] Input: Encrypted health information.

[1409] Output: Anonymized data.

[1410] Step 3:

[1411] Analysis using AI models

[1412] Server: Retrieves anonymized data stored in a database and inputs it into an artificial intelligence model.

[1413] AI models, using TensorFlow and PyTorch to perform analysis and generate optimal treatment recommendations, for example, identifying the best treatment for knee pain.

[1414] Input: De-identified health information.

[1415] Output: Treatment recommendations as a result of the analysis.

[1416] Step 4:

[1417] Notification of recommended treatment

[1418] Server: Receives the analysis results of the AI ​​model and notifies the medical professional in charge via email or a dedicated application.

[1419] Input: Analysis results.

[1420] Output: Notification to medical professionals.

[1421] Step 5:

[1422] Treatment result feedback

[1423] Medical professionals: record the results of the treatments performed on a dedicated form.

[1424] On the device: Form entry information is encrypted and sent to the server.

[1425] Input: Treatment outcome.

[1426] Output: Encrypted treatment results.

[1427] Step 6:

[1428] Data Update and Training

[1429] Server: Receives the encrypted treatment results and stores them in a database.

[1430] Server: Updates the AI ​​model based on treatment results to improve the accuracy of the next analysis.

[1431] Input: Treatment outcome.

[1432] Output: The updated AI model.

[1433] Each step of this system works to appropriately process the input data and ultimately improve the user's health and provide effective support to medical professionals.

[1434] (Application example 1)

[1435] 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."

[1436] Conventional medical systems have difficulty efficiently collecting and analyzing users' health information and providing optimal treatment. Furthermore, follow-up after treatment is insufficient, especially regarding self-care. This has made continuous health management and providing optimal treatment methods challenging.

[1437] 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.

[1438] In this invention, the server includes means for inputting health information from a user, means for transmitting the input health information to the server, means for anonymizing and storing the received health information in the server, means for analyzing the health information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, means for storing the retransmitted treatment results in a database and updating the AI ​​model, means for selecting an optimal video based on the health information and delivering it to a user terminal, means for inputting feedback after watching the video, and means for further improving the accuracy of the AI ​​model based on the input feedback. This makes it possible to provide individually customized treatments and self-care information based on the user's health information.

[1439] "Health information" refers to data relating to a user's personal health, such as diagnostic results, symptoms, and treatment history.

[1440] A "server" is a computer system that receives, stores, processes, and transmits data over a network.

[1441] "Anonymization" is the process of removing or masking personally identifiable information to protect an individual's privacy.

[1442] "Storage" is the act of recording and safely storing data.

[1443] An "AI model" is an algorithm that has been trained to perform a specific task using artificial intelligence techniques.

[1444] "Analysis" is the process of extracting information from input data and deriving results.

[1445] A "treatment" is a medical procedure or method for solving or improving a user's health problem.

[1446] "Notification" is the act of communicating information or results to other systems or people.

[1447] "Feedback" is information about opinions and results provided by users.

[1448] "Video" is visual content that combines a series of images.

[1449] "Distribution" is the act of transmitting digital content to users over a network.

[1450] A "terminal" is a device that a user directly operates to input and receive information.

[1451] "Encryption" is a technology that converts data to keep it secure and prevents unauthorized access.

[1452] The present invention is a system that collects health information from a user and uses an AI model to suggest optimal treatments and self-care information based on that information. Specific embodiments for carrying out the present invention will be described in detail below.

[1453] System configuration

[1454] This system is realized by combining the following hardware and software elements.

[1455] 1. User Device

[1456] Input and output devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs).

[1457] 2. Server

[1458] A computer system equipped with a high-performance processor and large-capacity storage device. Cloud services such as AWS (Amazon Web Services) and GCP (Google Cloud Platform) can also be used.

[1459] 3. AI Model

[1460] Models trained using machine learning libraries such as TensorFlow and PyTorch analyze a user's health information and recommend optimal treatments.

[1461] 4. Database

[1462] A relational database system, such as MongoDB or MySQL, to securely store anonymized health information and treatment results.

[1463] System Operation

[1464] Entering health information

[1465] Users input their own health information using devices such as smartphones or HMDs, for example, recording detailed symptoms such as knee pain or stiff shoulders, diagnosis results, and treatment history.

[1466] Transmission and anonymization of information

[1467] Health information entered from the device is sent to a server, which then anonymizes the information and stores it in a database while protecting the user's privacy.

[1468] Analysis using AI models

[1469] The data stored on the server is analyzed by an AI model, which uses past treatment data to recommend the optimal treatment and fitness videos for the entered health information.

[1470] Selection and distribution of recommended videos

[1471] Based on the analysis results, videos on optimal training and self-care are selected and delivered to the user's device. For example, a stretching video to relieve knee pain may be suggested.

[1472] Treatment results and feedback

[1473] After the user watches the recommended videos and performs training, the results are input as feedback from the device to the server, which then stores the newly obtained feedback in a database and updates the AI ​​model to improve its accuracy.

[1474] Specific examples

[1475] Example 1: When a user complains of knee pain and inputs it into the system, the AI ​​model uses past data to suggest the optimal stretching method and delivers a training video.

[1476] Example 2: If a user feels stiff shoulders, the system will select the optimal massage method and self-care video and provide it to the user.

[1477] Prompt Sentence Examples

[1478] If a user types in knee pain, recommend the best treatment based on past data. Select training videos to relieve knee pain and provide their URLs.

[1479] This allows users to obtain optimal treatment and self-care information according to their individual health conditions, enabling continuous health management.

[1480] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1481] Step 1:

[1482] Input: The user inputs health information such as knee pain using a device such as a smartphone or HMD.

[1483] Processing: The device collects the information entered by the user and performs encryption processing before sending the data to the server. Encryption uses encryption technology such as AES (Advanced Encryption Standard).

[1484] Output: Encrypted health information is generated and sent to the server.

[1485] Step 2:

[1486] Input: The server that receives the encrypted health information.

[1487] Processing: The server decrypts the encrypted information and anonymizes it by removing any personally identifiable information. Anonymization may include removing identifiers and / or masking the data.

[1488] Output: De-identified health information is generated and stored in a database.

[1489] Step 3:

[1490] Input: De-identified health information stored in a database.

[1491] Processing: The server inputs the stored health information into an AI model for analysis. The AI ​​model, pre-trained using TensorFlow, recommends optimal treatments and self-care methods based on past treatment data.

[1492] Output: The analysis identifies optimal treatments and fitness videos.

[1493] Step 4:

[1494] Input: Analysis results identified by the AI ​​model.

[1495] Processing: The server automatically selects the appropriate video based on the analysis results and generates its URL. The video selection involves comparing metadata and tagging content.

[1496] Output: A URL for the selected video is generated.

[1497] Step 5:

[1498] Input: Server-generated video URL.

[1499] Process: The server delivers the video URL to the user's device, securely using the HTTPS protocol.

[1500] Output: The video URL is displayed on the user's device.

[1501] Step 6:

[1502] Input: User watches videos and performs training on device.

[1503] Processing: After completing the training, the user inputs their feedback into the terminal. The feedback includes the effectiveness of the training and their impressions.

[1504] Output: Feedback data is generated and sent to the server.

[1505] Step 7:

[1506] Input: Feedback data submitted by the user.

[1507] Processing: The server analyzes the received feedback data and stores it in a database. The AI ​​model is updated based on the stored feedback to improve accuracy. An online learning algorithm is used for updating.

[1508] Output: An updated AI model is generated and used for the next analysis.

[1509] These steps enable the present invention to provide personalized treatment and self-care information based on the user's health information.

[1510] 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.

[1511] System Overview:

[1512] This invention relates to an AI analysis system that inputs a user's health and emotional information, performs rigorous analysis, and provides optimal treatment methods. In addition to conventional health information processing, this system incorporates an emotion engine to provide treatment methods that take the user's emotional state into consideration.

[1513] System configuration:

[1514] The system includes the following means:

[1515] 1. User's device

[1516] 2. Server

[1517] 3. AI Model

[1518] 4. Emotion Engine

[1519] 5. Database

[1520] System behavior:

[1521] When a user enters health and emotional information from their device, the information is sent to a server. The server anonymizes the received information and stores it in a database. The server then inputs the stored health and emotional information into an AI model for analysis. The AI ​​model identifies the optimal treatment method, and the server notifies the doctor of its recommendation. The doctor then performs the treatment, and the results are sent from the device back to the server. The server stores the newly obtained treatment results in a database and updates the AI ​​model to improve the accuracy of the next analysis.

[1522] What the program does:

[1523] Entering and sending health and emotional information:

[1524] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information that is analyzed using the emotion engine. The input information is encrypted and sent to the server. For example, Mr. Tanaka complains of knee pain and inputs the details of the pain and anxiety he feels during treatment into the device.

[1525] Anonymization and storage of information:

[1526] The server anonymizes the information it receives, removing any personally identifiable information and storing it securely in a database. The anonymized data is then made available for analysis while protecting the user's privacy.

[1527] Analysis by AI model:

[1528] The data stored on the server is analyzed by an AI model. Based on past treatment data and emotional data, the AI ​​model identifies the optimal treatment method based on the input health and emotional information. For example, if a user is feeling anxious about knee pain, the AI ​​model will recommend the optimal method, including treatment to alleviate that anxiety.

[1529] Notification of recommended treatment:

[1530] The server notifies the doctor of the results of the AI ​​model's analysis. The doctor then uses the recommended treatment as a reference to create a specific treatment plan. This allows the doctor to provide efficient treatment that takes into account the user's health and emotional information.

[1531] Treatment result feedback:

[1532] The doctor administers the treatment, records the results, and sends them to the server from the device. For example, Mr. Tanaka receives treatment and reports the results and changes in his / her emotions.

[1533] Data update and training:

[1534] The server stores the received treatment results in a database and updates the AI ​​model. This update allows the results to be reflected in the next analysis. Continually adding data and updating the model improves the analysis accuracy of the entire system.

[1535] Examples:

[1536] The user inputs knee pain and emotion data.

[1537] Tanaka enters details about his knee pain into the device and sends them to the server, while also inputting his own anxiety using the emotion engine.

[1538] Anonymization and Analysis of Information

[1539] The server anonymizes the information it receives and stores it in a database, after which it analyzes it using an AI model. Based on past successful treatments, it recommends a combination of the best treatment for knee pain and anxiety relief.

[1540] Notification of recommended treatment

[1541] The identified treatment will be notified to the doctor in charge, who will plan and implement the treatment. The doctor will also take into account the emotional information provided and take an appropriate approach to Mr. Tanaka.

[1542] Treatment result feedback

[1543] The doctor reports the treatment results from the device to the server, which then stores the results in a database and updates the AI ​​model.

[1544] Through this process, the system effectively manages the user's health and emotional state and provides optimal treatment methods, improving the user's overall quality of life and contributing to alleviating labor shortages.

[1545] The processing flow will be explained below.

[1546] Step 1:

[1547] The user inputs health and emotional information from a terminal. The user fills out an input form with their symptoms, diagnosis results, treatment history, and emotional state (e.g., anxiety, joy, anger, etc.). The emotion engine analyzes the user's emotional information in real time and assists in the input.

[1548] Step 2:

[1549] The device sends the entered health and emotional information to a server, which encrypts all data and transmits it to the server using a secure protocol.

[1550] Step 3:

[1551] The server anonymizes the health and emotional information it receives. The server then runs a process to remove personally identifiable information and de-identify the data. The resulting anonymous data is managed in a manner that protects the user's privacy.

[1552] Step 4:

[1553] The server stores the anonymized health and emotional information in a database, where it securely records the information for future analysis.

[1554] Step 5:

[1555] The server inputs the health and emotional information stored in the database into the AI ​​model for analysis. The server utilizes past treatment data and emotional data to perform analysis to identify the most appropriate treatment method for the user's symptoms. The AI ​​model then proposes the optimal treatment, taking into account both the user's health and emotional state.

[1556] Step 6:

[1557] The server notifies the doctor of the optimal treatment identified by the AI ​​model. The server then sends the analysis results to the doctor's dedicated device, where the doctor receives the information. The doctor then formulates a recommended treatment plan, taking into account the user's health and emotional information.

[1558] Step 7:

[1559] The doctor will then carry out treatment based on the recommended treatment. The doctor will plan and carry out specific treatment based on the treatment method and emotional information notified by the server. For example, standard treatment for knee pain will be combined with counseling to alleviate the user's anxiety.

[1560] Step 8:

[1561] The doctor sends the treatment results and changes in the user's emotions from the device to the server. After the treatment is completed, the doctor records the treatment results and the user's emotional state in detail and reports them to the server using the device.

[1562] Step 9:

[1563] The server stores the received treatment results and emotion data in a database. Newly obtained treatment results and emotion data are recorded in the database and will be used for the next analysis.

[1564] Step 10:

[1565] The server updates the AI ​​model based on the latest treatment results and emotion data stored in the database. The AI ​​model learns new data and improves its analysis accuracy. This continuous data update improves the accuracy of subsequent analyses.

[1566] Through these steps, the system will manage the user's health and emotional information in an advanced manner and provide the most appropriate treatment method quickly and effectively, thereby contributing to resolving the user's health problems and thereby helping to resolve the labor shortage problem in society as a whole.

[1567] Example 2

[1568] 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."

[1569] Conventional health information processing systems have had the challenge of making it difficult to provide treatment methods that take into account the user's psychological state. They also required comprehensive management, including anonymizing received information, securely storing data, and updating AI models to improve analysis accuracy. This resulted in problems that prevented users from fully improving their satisfaction and improving medical efficiency.

[1570] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting health information and emotional information from a user, means for transmitting the input health information and emotional information to the server, means for anonymizing and storing the received health information and emotional information, means for analyzing the health information and emotional information stored in the server using an AI model, means for identifying an optimal treatment based on the analysis results and notifying a doctor, means for retransmitting the results of the treatment performed by the doctor to the server, and means for storing the retransmitted treatment results in a database and updating the AI ​​model. This makes it possible to comprehensively manage the user's health condition and emotional information and provide an optimal treatment with improved analysis accuracy.

[1571] "Health information" is a general term for medical data such as a user's diagnosis, symptoms, and treatment history.

[1572] "Emotional information" is a general term for data relating to the user's psychological state and emotional fluctuations.

[1573] A "terminal" is an electronic device used by a user to input information, such as a smartphone or a personal computer.

[1574] A "server" is a central processing unit that receives information sent from a user and processes it, such as storing, analyzing, and notifying users.

[1575] "Anonymization" is a process to protect personal information by removing elements that can identify individuals from received information.

[1576] A "database" is an information storage system for safely storing anonymized information and treatment results.

[1577] An "AI model" is an artificial intelligence algorithm that analyzes past data and identifies the optimal treatment method.

[1578] "Analysis results" refers to the optimal treatment methods and recommendations obtained after the AI ​​model analyzes the input data.

[1579] "Notification" refers to the act of transmitting the analysis results from the server to the attending physician.

[1580] "Treatment results" refers to data that records the effects of treatment administered by a doctor and changes in the user's condition.

[1581] "Encryption" is a technology that converts information into a specific code to transmit it securely and prevent unauthorized access.

[1582] The present invention involves inputting a user's health and emotional information, sending it to a server, and analyzing the anonymized information with an AI model to identify the optimal treatment and notify the doctor. The treatment results are then sent back to the server, stored in a database, and the AI ​​model is updated to improve the system's analytical accuracy.

[1583] Enter and submit information

[1584] Users input their own health and emotional information using devices such as smartphones or PCs. Health information includes diagnosis results, symptoms, and treatment history, while emotional information includes psychological state analyzed using an emotion engine. Once the user has completed input, the information is encrypted and sent to the server.

[1585] Examples:

[1586] Mr. Tanaka complains of knee pain, enters detailed information about the pain and his anxiety during treatment into the terminal, and sends it.

[1587] Anonymization and storage of information

[1588] The information received by the server is anonymized by removing any personally identifiable information. This anonymized information is then stored in a highly secure database, ensuring the protection of personal information.

[1589] Analysis using AI models

[1590] The server retrieves the stored health and emotional information and inputs it into an AI model, which analyzes past treatment data and emotional data to identify the optimal treatment method. This AI model uses machine learning libraries such as TensorFlow and PyTorch.

[1591] Examples:

[1592] Data on Tanaka's knee pain and anxiety will be provided to the AI, which will analyze and identify the optimal treatment and anxiety relief methods.

[1593] Notification of recommended treatment

[1594] The server notifies the doctor of the analysis results, who then uses the results to create a specific treatment plan and provide the treatment to the user.

[1595] Treatment outcome feedback and updates

[1596] The doctor performs the treatment and sends the results from the device to the server. The treatment results are then anonymized again and stored in a database. Furthermore, this new treatment data is used to update the AI ​​model, improving the accuracy of the analysis the next time.

[1597] Specific examples of prompts to input to generative AI models

[1598] Below is an example of a prompt sentence to input to the generative AI model.

[1599] "A user enters data on their knee pain and anxiety via a device. Please explain in detail the process by which this information is anonymized, fed into an AI model to analyze the optimal treatment, and then communicates the results to the doctor."

[1600] This invention takes into account the psychological state of the user and provides optimal treatment, thereby increasing user satisfaction and improving the quality of medical care. Furthermore, continuous data updates can improve analysis accuracy, which is expected to have long-term medical effects.

[1601] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1602] Step 1:

[1603] The user inputs health and emotional information

[1604] The user uses the device to input diagnosis results, symptoms, treatment history, and emotional information. This input data is collected as text and numerical data based on the device's input form. Once input is complete, the data is sent by pressing the send button to proceed to the next step.

[1605] Input: Diagnosis results, symptoms, treatment history, emotional information (text and numerical data)

[1606] Output: Data submitted from the input form

[1607] Specific actions: For example, if Tanaka enters details of his knee pain and anxiety, he will enter data such as "Right knee pain, level 7 (out of 10)" and "Anxiety about treatment level 3 (out of 5)" into the terminal form.

[1608] Step 2:

[1609] The device sends the input information to the server

[1610] The device encrypts the health and emotional information entered by the user and sends it to the server using an encryption algorithm such as AES.

[1611] Input: Health and emotional information entered by the user

[1612] Output: Encrypted data

[1613] Specific operation: Tanaka's input data is AES encrypted and sent to the server via a secure communication protocol (e.g., HTTPS).

[1614] Step 3:

[1615] The server anonymizes the information

[1616] The server decrypts the encrypted data it receives, removes any personally identifiable information, and anonymizes it, assigning it a new unique ID.

[1617] Input: Encrypted user data

[1618] Output: Anonymized data

[1619] Specific operation: After Tanaka's data is decrypted, specific personal information such as name and address is removed and it is saved in the format "User ID: 12345".

[1620] Step 4:

[1621] The server stores the anonymized information in a database

[1622] The anonymized data is stored in a highly secure database, which is implemented using SQL and NoSQL technologies.

[1623] Input: Anonymized data

[1624] Output: Data stored in the database

[1625] Specific operation: Anonymized data on Tanaka's knee pain and anxiety is stored in an "anonymous database."

[1626] Step 5:

[1627] The server inputs the data into the AI ​​model

[1628] The server extracts the necessary patient information from the database and inputs it into the AI ​​model, which uses machine learning libraries such as TensorFlow and PyTorch.

[1629] Input: De-identified data extracted from the database

[1630] Output: Data input into the AI ​​model

[1631] Specific operation: Data on Tanaka's knee pain and anxiety is input into the AI ​​model by the server.

[1632] Step 6:

[1633] AI models analyze data and identify optimal treatment options

[1634] The AI ​​model uses deep learning techniques to analyze past treatment data and emotional data to identify the optimal treatment method.

[1635] Input: Data fed into the AI ​​model

[1636] Output: Recommendation of optimal treatment method

[1637] Specific operation: The AI ​​model analyzes Tanaka's data and outputs the result, "Knee treatment: physical therapy, emotional relaxation method: cognitive behavioral therapy."

[1638] Step 7:

[1639] The server notifies the doctor of the analysis results

[1640] The server then notifies the doctor of the analysis results via email or a dedicated medical application.

[1641] Input: Analysis results of the AI ​​model

[1642] Output:Notify doctor

[1643] Specific operation: The server sends the results of Tanaka's optimal treatment to his doctor via email.

[1644] Step 8:

[1645] The doctor administers the treatment

[1646] The doctor in charge will then provide treatment to the user based on the analysis results after receiving the notification, and treatment methods such as physical therapy or counseling will be selected.

[1647] Input: Treatment notified by the server

[1648] Output: Treatment performed

[1649] Specific action: The doctor will administer physical therapy and cognitive behavioral therapy to Tanaka.

[1650] Step 9:

[1651] The doctor sends the treatment results from the device to the server.

[1652] The doctor enters the treatment results into the terminal, encrypts them, and sends them to the server, again using an encryption algorithm such as AES.

[1653] Input: Treatment results

[1654] Output: Encrypted treatment outcome data

[1655] Specific operation: The doctor enters Tanaka's treatment results into the terminal and sends the AES-encrypted data to the server.

[1656] Step 10:

[1657] The server stores the treatment results in a database and updates the AI ​​model.

[1658] The server receives and anonymizes the treatment results, stores them in a database, and updates the AI ​​model based on this new data.

[1659] Input: Encrypted treatment outcome data

[1660] Output: De-identified treatment outcome data, updated AI model

[1661] Specific operation: Tanaka's treatment result data is anonymized and stored in a database, and the AI ​​model is retrained with new data.

[1662] (Application example 2)

[1663] 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."

[1664] Conventional medical systems identify treatment options based solely on the user's health information, making it difficult to provide optimal treatment and dietary recommendations that reflect the user's emotional state. Furthermore, there was no system that effectively collected users' treatment results and dietary feedback and quickly reflected the results in collaboration with food delivery services. This resulted in a lack of tools to improve users' overall health and quality of life.

[1665] The identification processing by the identification 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 inputting health information and emotional information from a user; means for transmitting the input health information and emotional information to the server; means for anonymizing and storing the received health information and emotional information in the server; means for analyzing the health information and emotional information stored in the server using an AI model; means for identifying optimal treatments and dietary suggestions based on the analysis results and notifying the doctor and the user; means for retransmitting the results of the treatment performed by the doctor and the user's dietary feedback information to the server; means for storing the retransmitted treatment results and dietary feedback information in a database and updating the AI ​​model; and means for coordinating with a food delivery service to make dietary suggestions available for immediate ordering. This enables integrated management of a user's health condition and emotional information, enabling the provision of more accurate treatments and individually optimized meals.

[1666]

[1667] "Health information" refers to medical data such as a user's diagnosis results, treatment history, and allergy information.

[1668] "Emotional information" refers to data related to the user's feelings, such as stress, anxiety, and joy.

[1669] "Server" refers to the database and computing device that stores the health and emotional information received from the user and analyzes it using the AI ​​model.

[1670] An "AI model" is a computational model that uses artificial intelligence and refers to an algorithm that analyzes a user's health and emotional information and derives optimal treatment and dietary suggestions.

[1671] "Anonymization" refers to the process of removing personally identifiable information from received data to protect the privacy of that data.

[1672] "Treatment" refers to a specific medical procedure that a doctor performs based on the user's health condition.

[1673] "Dietary suggestions" refers to the dietary and nutritional intake plans that the AI ​​model recommends to the user based on the analysis results.

[1674] "Notification" refers to the act of informing a user or a doctor of analysis results or suggestions.

[1675] "Feedback information" refers to information reported by a user as a result of the treatment or diet they have undertaken.

[1676] "Food delivery service" refers to a company or system that provides a service of quickly delivering meals specified by a user.

[1677] "Encryption processing" refers to a technology that encodes data to keep it confidential and prevent it from being leaked to third parties.

[1678]

[1679] The present invention is a system for proposing optimal treatments and diets based on a user's health information and emotional information. Specific embodiments of the present invention will be described below.

[1680] Hardware and software used

[1681] User device: A smartphone is used by the user to input health and emotional information.

[1682] Server: Uses cloud servers for data storage and processing.

[1683] Database: Firebase is used to store health and emotional information.

[1684] AI model: Use TensorFlow or PyTorch to analyze the data.

[1685] Emotion Engine: Uses Affectiva SDK to analyze user emotional information.

[1686] System Operation

[1687] 1. Enter your information:

[1688] Users input health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.) through a smartphone app, which then sends this information to a server.

[1689] 2. Transmission and storage of information:

[1690] The server anonymizes the health and emotional information received from the user and stores it securely in Firebase.

[1691] 3. Analysis by AI model:

[1692] The server retrieves the data stored in Firebase and analyzes it using TensorFlow or PyTorch-based AI models. Based on the analysis results, it generates optimal treatment and dietary recommendations for the user.

[1693] 4. Notification of results and collaboration:

[1694] The server then sends the analysis results to the user and their doctor via push notification. The server also works with food delivery services to provide meal suggestions, allowing users to instantly order the suggested menu items.

[1695] 5. Gather feedback and update the model:

[1696] After the user has eaten, they enter their feedback into the app. This feedback information is sent back to the server and stored in Firebase. The server uses this information to update the AI ​​model and improve its accuracy in the future.

[1697] Specific examples

[1698] For example, a user can input health information such as "I've been feeling tired and unmotivated lately," and also emotional information such as "I'm under a lot of stress at work." The AI ​​model analyzes this information and suggests relaxing herbal teas and meals rich in B vitamins to highly stressed users. This allows the user to receive push notifications suggesting the most suitable meals, which can then be instantly ordered through a delivery service.

[1699] Prompt Sentence Examples

[1700] "I've been suffering from a lack of sleep and am in a mentally unstable state. Please suggest some meals that will replenish my energy and help me relax."

[1701] "I haven't been exercising much lately, so my appetite has decreased. Could you recommend some foods that are easy to digest and gentle on the body?"

[1702] This system enables the integrated management of a user's health status and emotional information, and provides highly accurate treatments and individually optimized diets.

[1703] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1704]

[1705] Step 1: Enter your information

[1706] The user launches the smartphone app and inputs health information (diagnosis results, treatment history, allergy information, etc.) and emotional information (stress, anxiety, etc.). This information is structured in JSON format and sent to the server via the app. For example, a user might input health information such as "I've been feeling tired and unmotivated lately" and emotional information such as "I'm under a lot of stress at work."

[1707] Step 2: Send and save information

[1708] The health and emotional information sent from the device is received by a server. The server anonymizes the received information by removing any personally identifiable elements. The anonymized data is then stored in Firebase. Examples of input data include "feeling tired, high stress."

[1709] Step 3: Analysis by AI model

[1710] The server retrieves health and emotional information stored in Firebase and inputs it into a TensorFlow or PyTorch-based AI model. The AI ​​model analyzes this data and generates treatment and dietary recommendations that are optimal for the user's condition. For example, it might recommend relaxing herbal teas or meals rich in B vitamins.

[1711] Step 4: Notification of results and collaboration

[1712] The server sends the analysis results generated by the AI ​​model to the user and doctor via push notification. It also works with food delivery services to provide meal suggestions, making the suggested menu items instantly available for ordering. A specific example of a notification might include a recommendation for a relaxing herbal tea and a meal rich in B vitamins.

[1713] Step 5: Gather feedback

[1714] After the user orders and consumes the suggested meal, they enter their feedback through a smartphone app, such as "The herbal tea had a relaxing effect."

[1715] Step 6: Update the model

[1716] The feedback information sent from the device is received by the server and stored in Firebase. The server uses this feedback information to update the AI ​​model and improve the accuracy of future suggestions, thereby continuously improving the entire system.

[1717] 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.

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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).

[1724] 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.

[1725] 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."

[1726] 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.

[1727] 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).

[1728] 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.

[1729] 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.

[1730] 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.

[1731] 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.

[1732] 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.

[1733] 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.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] The following is further disclosed regarding the above embodiment.

[1739] (Claim 1)

[1740] a means for inputting health information from a user;

[1741] means for transmitting the input health information to a server;

[1742] means for anonymizing and storing the received health information in a server;

[1743] A method for analyzing health information stored on a server using an AI model;

[1744] A means to identify optimal treatment options based on the analysis results and notify physicians;

[1745] means for transmitting the results of the treatment performed by the doctor to the server again;

[1746] A means for storing the resubmitted treatment results in a database and updating the AI ​​model;

[1747] A system including:

[1748] (Claim 2)

[1749] 10. The system of claim 1, wherein the user's health information includes diagnostic results and treatment history.

[1750] (Claim 3)

[1751] 2. The system according to claim 1, wherein encryption processing is performed when the treatment results are transmitted.

[1752] "Example 1"

[1753] (Claim 1)

[1754] a means for inputting health information from a user;

[1755] means for transmitting the input health information to a server;

[1756] means for anonymizing and storing the received health information in a server;

[1757] A means for analyzing the health information stored on the server using an artificial intelligence model;

[1758] A means to identify and inform medical professionals about optimal treatment options based on the analysis results;

[1759] means for transmitting the results of the treatment performed by the medical professional back to the server;

[1760] a means for storing the resubmitted treatment results in a database and updating an artificial intelligence model;

[1761] A means for encrypting health information and treatment results transmitted from the user terminal;

[1762] A system including:

[1763] (Claim 2)

[1764] 10. The system of claim 1, wherein the user's health information includes diagnostic results and treatment history.

[1765] (Claim 3)

[1766] The system of claim 1, wherein the accuracy of the next analysis is improved when the artificial intelligence model is updated based on the results of the treatment performed.

[1767] "Application Example 1"

[1768] (Claim 1)

[1769] a means for inputting health information from a user;

[1770] means for transmitting the input health information to a server;

[1771] means for anonymizing and storing the received health information in a server;

[1772] A method for analyzing health information stored on a server using an AI model;

[1773] A means to identify optimal treatment options based on the analysis results and notify physicians;

[1774] means for transmitting the results of the treatment performed by the doctor to the server again;

[1775] A means for storing the resubmitted treatment results in a database and updating the AI ​​model;

[1776] A means for selecting an optimal video based on health information and delivering it to a user terminal;

[1777] A means to enter feedback after watching the video;

[1778] A means to further improve the accuracy of AI models based on input feedback,

[1779] A system including:

[1780] (Claim 2)

[1781] 10. The system of claim 1, wherein the user's health information includes diagnostic results and treatment history.

[1782] (Claim 3)

[1783] The system of claim 1, wherein encryption processing is performed when the treatment results and feedback after watching the video are sent.

[1784] "Example 2: Combining Emotion Engines"

[1785] (Claim 1)

[1786] means for inputting health and emotional information from a user;

[1787] means for transmitting the input health information and emotion information to a server;

[1788] means for anonymizing and storing the received health and emotional information at a server;

[1789] A means for analyzing health information and emotional information stored on a server using an AI model;

[1790] A means to identify optimal treatment options based on the analysis results and notify physicians;

[1791] means for transmitting the results of the treatment performed by the doctor to the server again;

[1792] A means for storing the resubmitted treatment results in a database and updating the AI ​​model;

[1793] A system including:

[1794] (Claim 2)

[1795] 10. The system of claim 1, wherein the user's health information includes diagnostic results, symptoms, and treatment history.

[1796] (Claim 3)

[1797] 2. The system according to claim 1, wherein encryption processing is performed when the treatment results are transmitted.

[1798] "Application example 2 when combining emotion engines"

[1799] (Claim 1)

[1800] means for inputting health and emotional information from a user;

[1801] means for transmitting the input health information and emotion information to a server;

[1802] means for anonymizing and storing the received health and emotional information at a server;

[1803] A means for analyzing health information and emotional information stored on a server using an AI model;

[1804] means for identifying optimal treatment and dietary suggestions based on the analysis results and informing the physician and the user;

[1805] means for transmitting the results of the treatment performed by the doctor and the user's dietary feedback information to the server again;

[1806] a means for storing the resubmitted treatment results and dietary feedback information in a database and updating the AI ​​model;

[1807] A means to link with food delivery services to make meal suggestions instantly available for ordering;

[1808] A system including:

[1809] (Claim 2)

[1810] 10. The system of claim 1, wherein the user's health information includes diagnostic results and treatment history, and the emotional information includes stress and anxiety states.

[1811] (Claim 3)

[1812] 2. The system of claim 1, wherein encryption processing is performed when treatment results and dietary feedback information are transmitted. [Explanation of symbols]

[1813] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for inputting health information from a user; means for transmitting the input health information to a server; means for anonymizing and storing the received health information in a server; A method for analyzing health information stored on a server using an AI model; A means to identify optimal treatment options based on the analysis results and notify physicians; means for transmitting the results of the treatment performed by the doctor to the server again; A means for storing the resubmitted treatment results in a database and updating the AI ​​model; A system including:

2. 10. The system of claim 1, wherein the user's health information includes diagnostic results and treatment history.

3. The system according to claim 1, wherein encryption processing is performed when the treatment results are transmitted.

Images